Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 02/21/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
In reference to claim 1:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“A computer-implemented method of predicting a Seawater intrusion (SWI) index in coastal aquifers based on a plurality of parameters for a sustainable groundwater management, comprising: determining values for each parameter of the plurality of parameters with a sensor network;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine values of each parameter from observation of the sensor network.
“estimating a level of informative contribution of the plurality of parameters and a multicollinearity among the plurality of parameters;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could estimate a level of informative contribution of the plurality of parameters and a multicollinearity among the plurality of parameters.
“selecting one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset.
“partitioning the input dataset into a modeling dataset and a testing dataset;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset.
“dividing the modeling dataset into a training set and a validation set;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person divide the modeling dataset into a training set and a validation set.
“evaluating each model of the plurality of models based on the validation set to obtain a model evaluation, the testing dataset, and a plurality of statistical performance metrics;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could evaluate each model of the plurality of models based on the validation set to obtain a model evaluation, the testing dataset, and a plurality of statistical performance metrics.
“selecting a prediction model from the plurality of models based on the testing dataset, the model evaluation, and the plurality of statistical performance;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select a prediction model from the plurality of models based on the testing dataset, the model evaluation, and the plurality of statistical performance.
“predicting the SWI index [from the prediction model]” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could predict the SWI index.
“creating an adaptive groundwater management strategy based on the SWI index.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could create an adaptive groundwater management strategy based on the SWI index.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“tuning a plurality of hyperparameters based on a grid search strategy for a plurality of models;” (insignificant extra-solution activity MPEP 2106.05(g))
“training each model of the plurality of models based on the training set and the plurality of hyperparameters;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“from the prediction model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“tuning a plurality of hyperparameters based on a grid search strategy for a plurality of models;” (insignificant extra-solution activity: Wall Paragraph 0413; “the parameter tuning process of 1260 can comprise a brute-force grid search, an optimized gradient descent or simulated annealing, or any other space exploration algorithm as known in the art. The models being tuned can undergo separate, independent tuning runs, or alternatively the models can be tuned in an ensemble fashion, with every parameter of every model explored in combination, in order to arrive at the optimal overall set of parameters at 1270 to maximize the benefit of using all the models in an ensemble.” Examiner notes that tuning a plurality of hyperparameters (parameter tuning process) is based on a grid search strategy (brute-force grid search that is known in the art) for a plurality of models)
“training each model of the plurality of models based on the training set and the plurality of hyperparameters;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“from the prediction model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 2:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein the plurality of parameters comprises a bicarbonate concentration, a total dissolved solids concentration, a nitrate concentration, a nitrite concentration, an ammonium concentration, a chloride concentration, a sulphate concentration, a pH, an electrical conductivity, a calcium concentration, a magnesium concentration, a sodium concentration, a potassium concentration, or a combination thereof.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 3:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein predicting the SWI index does not include a chloride concentration in the plurality of parameters.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 4:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
No
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“The method of Claim 1, wherein the plurality of models is a Gradient Boosting Regressor, a Multilayer Perceptron, a Ridge Regression, a Decision Tree, a Random Forest, a SVM regression, a Bagging Regressor, a committee regressor, a stacking regressor, or a combination thereof.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“The method of Claim 1, wherein the plurality of models is a Gradient Boosting Regressor, a Multilayer Perceptron, a Ridge Regression, a Decision Tree, a Random Forest, a SVM regression, a Bagging Regressor, a committee regressor, a stacking regressor, or a combination thereof.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 5:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein the plurality of statistical performance metrics is a correlation coefficient, a mean absolute error, a mean square error, a Bayesian information criterion, an Akaike information criterion, or a combination thereof.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 6:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein the selecting the prediction model further comprises: ranking the plurality of models based on the model evaluation to obtain a rank;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could rank the plurality of models based on the model evaluation to obtain a rank.
“creating a committee of models and a stack of models based on the rank; and” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could group models to create a committee of models and a stack of models based on the rank.
“selecting the prediction model from the group consisting of the plurality of models, the committee of models, and the stack of models based on the rank;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select the prediction model from the group consisting of the plurality of models, the committee of models, and the stack of models based on the rank.
“wherein the committee of models comprises a set of preferred models of the plurality of models based on the rank, and the stack of models comprises a set of second-preferred models of the plurality of models based on the rank.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 7:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“and the predicting step further comprises calculating an arithmetic average of a plurality of SWI indexes obtained from the committee of models.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could calculate an arithmetic average of a plurality of SWI indexes obtained from the committee of models.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“The method of Claim 6, wherein the prediction model is the committee of models” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“The method of Claim 6, wherein the prediction model is the committee of models” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 8:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
No
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“The method of Claim 7, wherein the set of preferred models comprises three (3) models of the plurality of models.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“The method of Claim 7, wherein the set of preferred models comprises three (3) models of the plurality of models.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 9:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“and the predicting step further comprises: creating a stacking validation set based on the plurality of SWI indexes obtained from the stack of models and the validation set;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could create a stacking validation set based on the plurality of SWI indexes obtained from the stack of models and the validation set.
“selecting a final prediction model from the stack of models based on the rank;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select a final prediction model from the stack of models based on the rank.
“predicting the SWI index [with a trained final prediction model.]” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could predict the SWI index.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“The method of Claim 6, wherein the prediction model is the stack of models,” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“training the final prediction model based on the stacking validation set; and” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“with a trained final prediction model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“The method of Claim 6, wherein the prediction model is the stack of models,” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“training the final prediction model based on the stacking validation set; and” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“with a trained final prediction model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 10:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
No
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“The method of Claim 9, wherein the set of second-preferred models comprises four (4) models of the plurality of models.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“The method of Claim 9, wherein the set of second-preferred models comprises four (4) models of the plurality of models.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 11:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 2, wherein the plurality of parameters consists of bicarbonate, a total dissolved solids, nitrate, nitrite, ammonium, chloride, sulphate, a pH, an electrical conductivity, calcium, magnesium, sodium, potassium.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“and the prediction model is the Ridge Regression” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“and the prediction model is the Ridge Regression” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 12:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 2, wherein the plurality of parameters consists of bicarbonate, a total dissolved solids, nitrate, nitrite, ammonium, chloride, sulphate, a pH, an electrical conductivity, calcium, magnesium, sodium, potassium,” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“and the prediction model is the Multilayer Perceptron.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“and the prediction model is the Multilayer Perceptron.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 13:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein the plurality of parameters further comprises a climate change parameter and a groundwater extraction scenario.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 14:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein the sensor network comprises an ion chromatography, a pH meter, a TDS meter, a titrator, and a water test kit.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 15:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The method of Claim 1, wherein the adaptive ground management strategy comprises ponding surface water and stormwater runoff; recharging the groundwater table; promoting water conservation; and restricting groundwater withdrawals.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 16:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a machine
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“wherein the program instruction is configured to perform a method comprises: determining values for each parameter of the plurality of parameters with a sensor network;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine values of each parameter from observation of the sensor network.
“estimating a level of informative contribution of the plurality of parameters and a multicollinearity among the plurality of parameters;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could estimate a level of informative contribution of the plurality of parameters and a multicollinearity among the plurality of parameters.
“selecting one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset.
“partitioning the input dataset into a modeling dataset and a testing dataset;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset.
“dividing the modeling dataset into a training set and a validation set;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person divide the modeling dataset into a training set and a validation set.
“evaluating each model of the plurality of models based on the validation set to obtain a model evaluation, the testing dataset, and a plurality of statistical performance metrics;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could evaluate each model of the plurality of models based on the validation set to obtain a model evaluation, the testing dataset, and a plurality of statistical performance metrics.
“selecting a prediction model from the plurality of models based on the testing dataset, the model evaluation, and the plurality of statistical performance;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could select a prediction model from the plurality of models based on the testing dataset, the model evaluation, and the plurality of statistical performance.
“predicting a Seawater intrusion (SWI) index [from the prediction model]” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could predict the SWI index.
“creating an adaptive groundwater management strategy based on the SWI index.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could create an adaptive groundwater management strategy based on the SWI index.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“A sustainable groundwater resource management system, comprising: a processor configured to execute a program instruction; a storage device connected to the processor; and a sensor network configured to measure a plurality of parameters and send the plurality of parameters to the storage device in one or more coastal aquifers in arid regions;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“tuning a plurality of hyperparameters based on a grid search strategy for a plurality of models;” (insignificant extra-solution activity MPEP 2106.05(g))
“training each model of the plurality of models based on the training set and the plurality of hyperparameters;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“from the prediction model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“A sustainable groundwater resource management system, comprising: a processor configured to execute a program instruction; a storage device connected to the processor; and a sensor network configured to measure a plurality of parameters and send the plurality of parameters to the storage device in one or more coastal aquifers in arid regions;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“tuning a plurality of hyperparameters based on a grid search strategy for a plurality of models;” (insignificant extra-solution activity: Wall Paragraph 0413; “the parameter tuning process of 1260 can comprise a brute-force grid search, an optimized gradient descent or simulated annealing, or any other space exploration algorithm as known in the art. The models being tuned can undergo separate, independent tuning runs, or alternatively the models can be tuned in an ensemble fashion, with every parameter of every model explored in combination, in order to arrive at the optimal overall set of parameters at 1270 to maximize the benefit of using all the models in an ensemble.” Examiner notes that tuning a plurality of hyperparameters (parameter tuning process) is based on a grid search strategy (brute-force grid search that is known in the art) for a plurality of models)
“training each model of the plurality of models based on the training set and the plurality of hyperparameters;” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“from the prediction model” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 17:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a machine
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of Claim 16, wherein the plurality of parameters excludes a chloride data.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 18:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a machine
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of Claim 17, wherein the plurality of parameters consists of bicarbonate, a total dissolved solids, nitrate, nitrite, ammonium, chloride, sulphate, a pH, an electrical conductivity, calcium, magnesium, sodium, potassium,” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“and the prediction model is the Multilayer Perceptron.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“and the prediction model is the Multilayer Perceptron.” is merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 19:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a machine
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of Claim 16, wherein the sensor network comprises an ion chromatography, a pH meter, a TDS meter, a titrator, and a water test kit.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 20:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a machine
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“The system of Claim 16, wherein the adaptive ground management strategy comprises ponding surface water and stormwater runoff; recharging the groundwater table; promoting water conservation; and restricting groundwater withdrawals.” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)).
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
No
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
No
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-2, 4-5, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Bonifaz”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”)
Regarding claim 1, Tekile teaches A computer-implemented method of predicting a Seawater intrusion (SWI) index in coastal aquifers based on a plurality of parameters for a sustainable groundwater management, comprising: determining values for each parameter of the plurality of parameters with a sensor network; (Tekile Page 3 Paragraph 3; “To assess the suitability of the water for irrigation, the major physicochemical parameters associated with water quality problems were assessed. For salinity problem, electrical conductivity (EC) or total dissolved solids (TDS); for infiltration, calcium, sodium, magnesium, and sulphate as well as EC; for specific ion toxicity, sodium, chloride, boron, and chromium; and for miscellaneous effects, nutrients (nitrate-nitrogen, ammonium-nitrogen, orthophosphate, and potassium), bi carbonate, carbonate, and pH were determined.” Tekile Page 3 Paragraph 4; “Water pH was measured using a pH meter by just inserting the glass electrode… pro 1030 conductivity meter was used to determine EC and TDS,… Boron was tested by photometer method by adding tablet available for this to water sample. Ammonia, nitrate, and orthophosphate were measured using photometer, for which reagents are provided in the form of two tablets for maximum convenience. Carbonate and bicarbonate were measured based on unique colorimetric methods. Sulphate was determined by nephelometric test, based on a single tablet reagent containing barium chloride in a slightly acidic formulation.” Examiner notes that values for each parameter of the plurality of parameters (major physicochemical parameters) are determined with a sensor network (Paragraph 4 shows network of sensors to determine each parameter))
Tekile does not teach estimating a level of informative contribution of the plurality of parameters and a multicollinearity among the plurality of parameters;
However, Mishra does teach estimating a level of informative contribution of the plurality of parameters and a multicollinearity among the plurality of parameters; (Mishra Page 2 Paragraph 1; “The Shapley value decomposition imputes the most likely contribution of each individual” Mishra Page 2 Paragraph 3; “Retrieval of regression coefficients from Shapley value: As explained by Lipovetsky (2006), we may retrieve standardized regression coefficients, denoted by, say, .α Denoting pair-wise correlation matrix among regressors by S, pair-wise correlation vector between regressand and regressors by T and Shapley value vector by V” Examiner notes that Shapley value regression estimates a level of informative contribution of the plurality of parameters (the most likely contribution of each individual) and a multicollinearity among the plurality of parameters (pair-wise correlation matrix among regressors by S, pair-wise correlation vector between regressand and regressors))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile and Mishra. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. One of ordinary skill would have motivation to combine Tekile and Mishra to address the failure in rejecting false null hypothesis cause by multicollinearity “Multicollinearity in empirical data violates the assumption of independence among the regressors in a linear regression model that often leads to failure in rejecting a false null hypothesis. It also may assign wrong sign to coefficients. Shapley value regression is perhaps the best methods to combat this problem.” (Mishra Abstract).
Tekile in view of Mishra does not teach selecting one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset;
However, Rojas does teach selecting one or more parameters of the plurality of parameters based on the level of informative contribution and the multicollinearity to obtain an input dataset; (Rojas Paragraph 0064; “312 shows a set of 5 features extracted from imaging data on top and 3 features extracted from demographic data on bottom using SHAP. Heatmap from left to right shows the feature importance regarding the outcome prediction” Examiner notes that one or more parameters of the plurality of parameters (features) is selected/extracted based on the level of informative contribution and the multicollinearity (SHAP values show the level of informative contribution and the multicollinearity) to obtain an input dataset (feature set 312))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, and Rojas. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. One of ordinary skill would have motivation to combine Tekile, Mishra, and Rojas to efficiently rank the features relative to the task to aid in training a better model “In some embodiments, pipelines such as Local Interpretable Model-Agnostic Explanations (LIME) or Shapley Additive explanations (SHAP), but not limited to those techniques, can be used for ranking features. SHAP provides the Shapley regression values to rank the features relative to the tasks being learned and provides different techniques to compute very efficiently these values, especially in the presence of multi-collinearity among the features.” (Rojas Paragraph 0062).
Tekile in view of Mishra in further view of Rojas does not teach partitioning the input dataset into a modeling dataset and a testing dataset;
dividing the modeling dataset into a training set and a validation set;
tuning a plurality of hyperparameters based on a grid search strategy for a plurality of models;
training each model of the plurality of models based on the training set and the plurality of hyperparameters;
evaluating each model of the plurality of models based on the validation set to obtain a model evaluation, the testing dataset, and a plurality of statistical performance metrics;
However, Bonifaz does teach partitioning the input dataset into a modeling dataset and a testing dataset; (Bonifaz Paragraph 0235; “The training data sets may be divided into three portions: the training set, the validation set, and the verification (or “testing”) set.” Examiner notes that the input data set (training datasets) is partitioned into a modeling dataset (training set and validation set) and a testing dataset (testing set))
dividing the modeling dataset into a training set and a validation set; (Examiner refers to previous mapping to show that the modeling dataset is divided into at training and validation set)
tuning a plurality of hyperparameters based on a grid search strategy for a plurality of models; (Bonifaz Paragraph 0237; “A total of k models are fit and evaluated on the k holdout test sets and the mean performance is reported. Each training dataset is then provided to a hyperparameter optimized procedure, such as grid search or random search, that finds an optimal set of hyperparameters for the model. The evaluation of each set of hyperparameters is performed using k-fold cross-validation that splits up the provided training dataset into k folds.” Examiner notes that a plurality of hyperparameters (set of hyperparameters) is tuned/optimized based on a grid search strategy for a plurality of models (k models))
training each model of the plurality of models based on the training set and the plurality of hyperparameters; (Bonifaz Paragraph 0238; “the data-driven model(s) may be pointed to the training and validation portions of the training data set. Training is an iterative process that adjusts the parametrization of the data-driven model(s) according to the data contained in the training data set.” Examiner notes that each model of the plurality of models (data-driven model(s)) is trained based on the training set (training portions of the training dataset) and the plurality of hyperparameters (hyperparameters of each data-driven model))
evaluating each model of the plurality of models based on the validation set to obtain a model evaluation, the testing dataset, and a plurality of statistical performance metrics; (Bonifaz Paragraph 0238; “With each iteration of training data to adjust the parametrization, the validation data is run on the models and one or more measures of accuracy is determined by comparison of the model output of application parameters with the actual application parameters collected with the training data. For example, generally the standard deviation and mean error of the output will improve for the validation data with each iteration and then the standard deviation and mean error will start to increase with subsequent iterations.” Examiner notes that each model of the plurality of models is evaluated based on the validation set (validation data) to obtain a model evaluation (one or more measures of accuracy), the testing dataset (the testing dataset is the remaining data not used in training and validation), and a plurality of statistical performance metrics (standard deviation and mean error))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, and Bonifaz. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. One of ordinary skill would have motivation to combine Tekile, Mishra, Rojas, and Bonifaz to minimize model overfitting and increase prediction accuracy “The validation set may be used to minimize overfitting. The validation set typically does not adjust the data-driven model as does the training set, but rather verifies that any increase in accuracy over the training data set yields an increase in accuracy over a data set that has not been applied to the data-driven model(s) previously, or at least the data-driven model(s) has/have not been trained on it yet (i.e. validation data set). If the accuracy over the training data set increases, but the accuracy over the validation data set remains the same or decreases, the process is often referred to be “overfitting” the data-driven model(s) and training should cease. Finally, the verification set is used for testing the trained data-driven model(s) to confirm the actual predictive power of the data-driven model(s).” (Bonifaz Paragraph 0235).
Tekile in view of Mishra in further view of Rojas in further view of Bonifaz does not teach selecting a prediction model from the plurality of models based on the testing dataset, the model evaluation, and the plurality of statistical performance;
predicting the [SWI] index from the prediction model; and
However, Jason does teach selecting a prediction model from the plurality of models based on the testing dataset, the model evaluation, and the plurality of statistical performance; (Jason Section “Model Selection Techniques” Paragraph 2; “The training set is used to fit the models; the validation set is used to estimate prediction error for model selection; the test set is used for assessment of the generalization error of the final chosen model.” Examiner notes that the prediction model is selected based on model evaluation and the plurality of statistical performance (prediction error from validation set) and the testing dataset (final assessment of the generalization error of the chosen model))
predicting the [SWI] index from the prediction model; and (Jason Section “Considerations for Model Selection”; “This is because once we choose a model, we will fit a new final model on all available data and start using it to make predictions.” Examiner notes that the selected prediction model (chosen model) is used to make predictions; Model can be configured for predicting SWI index)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, and Jason. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. One of ordinary skill would have motivation to combine Tekile, Mishra, Rojas, Bonifaz, and Jason to choose a “good enough” model to best fit specific requirements needed “All models have some predictive error, given the statistical noise in the data, the incompleteness of the data sample, and the limitations of each different model type. Therefore, the notion of a perfect or best model is not useful. Instead, we must seek a model that is “good enough.”” (Jason Section “Considerations for Model Selection”).
Tekile in view of Mishra in further view of Rojas in further view of Bonifaz in further view of Jason does not teach predicting the SWI index
creating an adaptive groundwater management strategy based on the SWI index.
However, Tomaszkiewicz does teach predicting the SWI index (Tomaszkiewicz Page 4 Paragraph 2 “we demonstrate that combining fsea and GQIPiper(mix) results can be a more representative index for seawater mixing. The newly proposed index is designated as GQISWI (Equation (5)) and is derived equally from values of GQIPi per(mix) (Equation (2)) and GQIfsea (Equation (4)) to ensure that the weaknesses in one index are compensated by the strengths of the other” Examiner notes that cited section shows how to predict/derive the SWI index (Groundwater Quality Index for Seawater Intrusion GQISWI))
creating an adaptive groundwater management strategy based on the SWI index. (Tomaszkiewicz Page 13 Paragraph 2; “The resulting maps provide a helpful and robust visual tool for researchers and policy makers towards defining corrective or adaptive measures.” Examiner notes that based on the SWI index (Quality Index for Seawater Intrusion) an adaptive groundwater management strategy (corrective or adaptive measures) can be created/defined)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, and Tomaszkiewicz. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, and Tomaszkiewicz to represent data in a format that allows the use of GIS framework to identify vulnerable areas prone to seawater intrusion “the formats of such diagrams do not facilitate the geospatial analysis of groundwater quality, thus limiting the ability of spatio-temporal mapping and monitoring. This raises the need to transform the information from current pattern diagrams into a format that can be readily used under a GIS framework to define vulnerable areas prone to seawater intrusion.” (Tomaszkiewicz Abstract).
Regarding claim 2, Tekile teaches The method of Claim 1, wherein the plurality of parameters comprises a bicarbonate concentration, a total dissolved solids concentration, a nitrate concentration, a nitrite concentration, an ammonium concentration, a chloride concentration, a sulphate concentration, a pH, an electrical conductivity, a calcium concentration, a magnesium concentration, a sodium concentration, a potassium concentration, or a combination thereof. (Tekile Table 4 and Page 3 Paragraph 3; “To assess the suitability of the water for irrigation, the major physicochemical parameters associated with water quality problems were assessed. For salinity problem, electrical conductivity (EC) or total dissolved solids (TDS); for infiltration, calcium, sodium, magnesium, and sulphate as well as EC; for specific ion toxicity, sodium, chloride, boron, and chromium; and for miscellaneous effects, nutrients (nitrate-nitrogen, ammonium-nitrogen, orthophosphate, and potassium), bi carbonate, carbonate, and pH were determined.” Tekile Page 9 Paragraph 2; “The concentration of nitrite in the river was from 0.003 mg/L at Bridge One (industry effluent) and Modjo at Highway Bridge to 0.056mg/L at Bridge Two sampling points.” Examiner notes that plurality of parameters comprises Sodium, Calcium, Magnesium, Sulphate concentrations as shown in Table 4)
PNG
media_image1.png
151
679
media_image1.png
Greyscale
Regarding claim 4, Tekile does not teach The method of Claim 1, wherein the plurality of models is a Gradient Boosting Regressor, a Multilayer Perceptron, a Ridge Regression, a Decision Tree, a Random Forest, a SVM regression, a Bagging Regressor, a committee regressor, a stacking regressor, or a combination thereof.
However, Bonifaz does teach The method of Claim 1, wherein the plurality of models is a Gradient Boosting Regressor, a Multilayer Perceptron, a Ridge Regression, a Decision Tree, a Random Forest, a SVM regression, a Bagging Regressor, a committee regressor, a stacking regressor, or a combination thereof. (Bonifaz Paragraph 0232; “The data-driven models may be machine learning algorithm(s). The machine learning algorithm(s) may be ensemble learning algorithm(s), such as gradient boosting machines (GBM), gradient boosting regression trees (GBRT), random forests or a combination thereof.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, and Bonifaz. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. One of ordinary skill would have motivation to combine Tekile, Mishra, Rojas, and Bonifaz to minimize model overfitting and increase prediction accuracy “The validation set may be used to minimize overfitting. The validation set typically does not adjust the data-driven model as does the training set, but rather verifies that any increase in accuracy over the training data set yields an increase in accuracy over a data set that has not been applied to the data-driven model(s) previously, or at least the data-driven model(s) has/have not been trained on it yet (i.e. validation data set). If the accuracy over the training data set increases, but the accuracy over the validation data set remains the same or decreases, the process is often referred to be “overfitting” the data-driven model(s) and training should cease. Finally, the verification set is used for testing the trained data-driven model(s) to confirm the actual predictive power of the data-driven model(s).” (Bonifaz Paragraph 0235).
Regarding claim 5, Tekile does not teach The method of Claim 1, wherein the plurality of statistical performance metrics is a correlation coefficient, a mean absolute error, a mean square error, a Bayesian information criterion, an Akaike information criterion, or a combination thereof.
However, Jason does teach The method of Claim 1, wherein the plurality of statistical performance metrics is a correlation coefficient, a mean absolute error, a mean square error, a Bayesian information criterion, an Akaike information criterion, or a combination thereof. (Jason Section “Probabilistic Measures”; “Four commonly used probabilistic model selection measures include: Akaike Information Criterion (AIC). Bayesian Information Criterion (BIC). Minimum Description Length (MDL). Structural Risk Minimization (SRM).”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, and Jason. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. One of ordinary skill would have motivation to combine Tekile, Mishra, Rojas, Bonifaz, and Jason to choose a “good enough” model to best fit specific requirements needed “All models have some predictive error, given the statistical noise in the data, the incompleteness of the data sample, and the limitations of each different model type. Therefore, the notion of a perfect or best model is not useful. Instead, we must seek a model that is “good enough.”” (Jason Section “Considerations for Model Selection”).
Regarding claim 16, Tekile teaches a sensor network configured to measure a plurality of parameters and send the plurality of parameters to the storage device in one or more coastal aquifers in arid regions; (Tekile Page 3 Paragraph 3; “To assess the suitability of the water for irrigation, the major physicochemical parameters associated with water quality problems were assessed. For salinity problem, electrical conductivity (EC) or total dissolved solids (TDS); for infiltration, calcium, sodium, magnesium, and sulphate as well as EC; for specific ion toxicity, sodium, chloride, boron, and chromium; and for miscellaneous effects, nutrients (nitrate-nitrogen, ammonium-nitrogen, orthophosphate, and potassium), bi carbonate, carbonate, and pH were determined.” Tekile Page 3 Paragraph 4; “Water pH was measured using a pH meter by just inserting the glass electrode… pro 1030 conductivity meter was used to determine EC and TDS,… Boron was tested by photometer method by adding tablet available for this to water sample. Ammonia, nitrate, and orthophosphate were measured using photometer, for which reagents are provided in the form of two tablets for maximum convenience. Carbonate and bicarbonate were measured based on unique colorimetric methods. Sulphate was determined by nephelometric test, based on a single tablet reagent containing barium chloride in a slightly acidic formulation.” Examiner notes that values for each parameter of the plurality of parameters (major physicochemical parameters) are determined with a sensor network (Paragraph 4 shows network of sensors to determine each parameter))
Tekile does not teach A sustainable groundwater resource management system, comprising: a processor configured to execute a program instruction; a storage device connected to the processor; and
However, Rojas does teach A sustainable groundwater resource management system, comprising: a processor configured to execute a program instruction; a storage device connected to the processor; and (Rojas Paragraph 0028; “These computer readable program instructions are stored in various types of computer readable storage media, such as cache 121 and the other storage media discussed below. The program instructions, and associated data, are accessed by processor set 110 to control and direct performance of the inventive methods.”)
Claim 16 is machine of method claim 1 and is accordingly rejected using substantially similar rationale as to that which is set for with respect to claim 1.
Claim(s) 3 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of Seok Hyun Ahn et al; “Prediction of groundwater quality index to assess suitability for drinking purpose using averaged neural network and geospatial analysis” published on Sept 19, 2023 (hereinafter “Ahn”)
Regarding claim 3, Tekile does not teach The method of Claim 1, wherein predicting the SWI index does not include a chloride concentration in the plurality of parameters.
However, Ahn does teach The method of Claim 1, wherein predicting the SWI index does not include a chloride concentration in the plurality of parameters. (Ahn Page 3 Paragraph 3; “Therefore, the analysis and modelling were carried out with 28 parameters (general bacteria, lead, fluorine, arsenic, caesium, mercury, chromium, boron, copper, zinc, chlorine, iron, manganese, aluminium, ammonium, nitrate, sulphate, potassium permanganate consumption, trichloroethylene, dichloromethane, benzene, toluene, ethylbenzene, xylene, 1,4- dioxane, total hardness, colour, and turbidity).” Examiner notes that predicting SWI index (groundwater quality index) is predicted/calculated without Chloride concentration in the plurality of parameters)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz and Ahn. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Ahn teaches applying machine learning algorithms to potabile ground water to accurately predict the groundwater quality. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz and Ahn to leverage machine learning to provide a more holistic, accurate, and actionable framework for groundwater quality assessment on a national scale “Thus, the integration of machine learning algorithms and spatial analysis aims to provide a more holistic, accurate, and actionable framework for groundwater quality assessment on a national scale.” (Ahn Page 2 Paragraph 3).
Regarding claim 17, claim 17 has similar limitations as of claim 3, except it is a system claim (Rojas Paragraph 0028), therefore it is rejected under the same rationale as claim 3.
Claim(s) 6 is rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of W. Curt Lefebvre et al; US 20040249480 A1 filed on Jun 5, 2023 in further view of Shibeshih Mitiku Belachew; US 20240199743 A1 filed on Apr 13, 2022 (hereinafter “Belachew”)
Regarding claim 6, Tekile does not teach selecting the prediction model from the group consisting of the plurality of models, the committee of models, and the stack of models based on the rank;
However, Jason does teach selecting the prediction model from the group consisting of the plurality of models, the committee of models, and the stack of models based on the rank; (Jason Section “What is Model Selection” Paragraph 2; “Model selection is a process that can be applied both across different types of models (e.g. logistic regression, SVM, KNN, etc.) and across models of the same type configured with different model hyperparameters (e.g. different kernels in an SVM).” Examiner notes that the prediction model from the group consisting of the plurality of models, the committee of models, and the stack of models based on the rank (model selection is applied to different types of models) are selected with model selection)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, and Jason. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. One of ordinary skill would have motivation to combine Tekile, Mishra, Rojas, Bonifaz, and Jason to choose a “good enough” model to best fit specific requirements needed “All models have some predictive error, given the statistical noise in the data, the incompleteness of the data sample, and the limitations of each different model type. Therefore, the notion of a perfect or best model is not useful. Instead, we must seek a model that is “good enough.”” (Jason Section “Considerations for Model Selection”).
Tekile in view of Jason does not teach The method of Claim 1, wherein the selecting the prediction model further comprises: ranking the plurality of models based on the model evaluation to obtain a rank;
creating a committee of models [and a stack of models] based on the rank; and
However, Lefebvre does teach teaches The method of Claim 1, wherein the selecting the prediction model further comprises: ranking the plurality of models based on the model evaluation to obtain a rank; (Lefebvre Paragraph 0032; “The evaluation phase ranks each of the models against each other, so that the best model is given the highest rank and the worst model is ranked last. In certain embodiments, the top ranked subset of the committee is used for system control up until the next ranking occurs, at which point the new operative subset of the committee can be substituted.” Examiner notes that the plurality of models (several models incorporated) are ranked based on the model evaluation (The evaluation phase ) to obtain a rank (the best model is given the highest rank and the worst model is ranked last))
creating a committee of models [and a stack of models] based on the rank; and (Examiner refers to previous mapping to show that a committee of models is created based on the rank (top ranked subset of the committee is used)
wherein the committee of models comprises a set of preferred models of the plurality of models based on the rank, [and the stack of models comprises a set of second-preferred models of the plurality of models based on the rank]. (Examiner refers to previous mapping to show that the committee of models is a set of preferred models based on rank (top ranked subset of the committee is used) and that the stack of model comprises a set of second preferred models based on rank (remaining ranked models is a stack of models))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Lefebvre. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Lefebvre to leverage committee of models to evaluate the source of error as statistical or systematic and, furthermore, to select the appropriate form of correction “In certain embodiments using a committee of models, it is possible to evaluate the source of error as statistical or systematic and, furthermore, to select the appropriate form of correction.” (Lefebvre Paragraph 0037).
Tekile in view of Jason in further view of Lefebvre does not teach creating [a committee of models and] a stack of models based on the rank
[wherein the committee of models comprises a set of preferred models of the plurality of models based on the rank,] and the stack of models comprises a set of second-preferred models of the plurality of models based on the rank.
However, Belachew does teach creating [a committee of models and] a stack of models based on the rank (Belachew Paragraph 0097; “This tuning may then lead to a performance benchmark that can select the highest performing models, for example, the n top-performing models. These models may then be combined under a stacking or a winner takes all or a probabilistic importance sampling ensemble strategy.” Examiner notes that a stack of models (These models may then be combined under a stacking strategy) based on the rank (n top-performing models))
[wherein the committee of models comprises a set of preferred models of the plurality of models based on the rank,] and the stack of models comprises a set of second-preferred models of the plurality of models based on the rank. (Examiner refers to previous mapping to show that the stack of models is a set of second preferred models (n top-performing models))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Belachew. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. Belachew teaches forming a stack of models based on a rank. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Belachew to leverage stack of models to boost predictive accuracy, leverage divers algorithmic strengths, and reduce generalization error “a pool of machine learning models may undergo hyperparameter tuning via an extensive randomized grid search, which may be followed by a k-fold cross-validation on the classification task of interest. This tuning may then lead to a performance benchmark that can select the highest performing models, for example, the n top-performing models. These models may then be combined under a stacking or a winner takes all or a probabilistic importance sampling ensemble strategy.” (Belachew Paragraph 0097).
Claim(s) 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of W. Curt Lefebvre et al; US 20040249480 A1 filed on Jun 5, 2023 in further view of Shibeshih Mitiku Belachew; US 20240199743 A1 filed on Apr 13, 2022 (hereinafter “Belachew”) in further view of Jason Brownlee; “Arithmetic, Geometric, and Harmonic Means for Machine Learning” available Jan 05, 2024 (hereinafter “Jason2”)
Regarding claim 7, Tekile does not teach The method of Claim 6, wherein the prediction model is the committee of models,
However, Lefebvre does teach The method of Claim 6, wherein the prediction model is the committee of models, (Lefebvre Paragraph 0032; “The evaluation phase ranks each of the models against each other, so that the best model is given the highest rank and the worst model is ranked last. In certain embodiments, the top ranked subset of the committee is used for system control up until the next ranking occurs, at which point the new operative subset of the committee can be substituted.” Examiner notes that the prediction model is the committee of models)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Lefebvre. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Lefebvre to leverage committee of models to evaluate the source of error as statistical or systematic and, furthermore, to select the appropriate form of correction “In certain embodiments using a committee of models, it is possible to evaluate the source of error as statistical or systematic and, furthermore, to select the appropriate form of correction.” (Lefebvre Paragraph 0037).
Tekile in view of Lefebvre does not teach and the predicting step further comprises calculating an arithmetic average of a plurality of SWI indexes obtained from the committee of models.
However, Jason2 does teach and the predicting step further comprises calculating an arithmetic average of a plurality of SWI indexes obtained from the committee of models. (Jason2 Paragraph 1; “Calculating the average of a variable or a list of numbers is a common operation in machine learning.” Examiner notes that an arithmetic average of the plurality of SWI indexes is calculated (average of a variable or list of numbers) obtained from the committee of models (common operation in machine learning))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Jason2. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Jason2 to simplify the data by finding a single number that represents the most common value in the list of numbers “The central tendency is a single number that represents the most common value for a list of numbers. More technically, it is the value that has the highest probability from the probability distribution that describes all possible values that a variable may have.” (Jason2 Section “What Is the Average?”).
Regarding claim 8, , Tekile does not teach The method of Claim 6, wherein the prediction model is the committee of models,
However, Lefebvre does teach The method of Claim 7, wherein the set of preferred models comprises three (3) models of the plurality of models. (Lefebvre Paragraph 0032; “For statistical significance, a committee of models may contain, for example, ten models.” Examiner notes that set of preferred models used in committee comprises 3 models which included in the 10 models used)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Lefebvre. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Lefebvre to leverage committee of models to evaluate the source of error as statistical or systematic and, furthermore, to select the appropriate form of correction “In certain embodiments using a committee of models, it is possible to evaluate the source of error as statistical or systematic and, furthermore, to select the appropriate form of correction.” (Lefebvre Paragraph 0037).
Claim(s) 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of W. Curt Lefebvre et al; US 20040249480 A1 filed on Jun 5, 2023 in further view of Shibeshih Mitiku Belachew; US 20240199743 A1 filed on Apr 13, 2022 (hereinafter “Belachew”) in further view of Jason Brownlee; “Essence of Stacking Ensembles for Machine Learning” available Dec 10, 2023 (hereinafter “Jason3”)
Regarding claim 9, Tekile does not teach selecting a final prediction model from the stack of models based on the rank;
predicting the SWI index with a trained final prediction model.
However, Jason does teach selecting a final prediction model from the stack of models based on the rank; (Jason Section “Considerations for Model Selection” Paragraph 1; “Fitting models is relatively straightforward, although selecting among them is the true challenge of applied machine learning. Firstly, we need to get over the idea of a “best” model. All models have some predictive error, given the statistical noise in the data, the incompleteness of the data sample, and the limitations of each different model type. Therefore, the notion of a perfect or best model is not useful. Instead, we must seek a model that is “good enough.”” Examiner notes that a final prediction model is selected (“best” model is selected) from the stack of models based on the rank (ranked the best))
predicting the SWI index with a trained final prediction model. (Jason Section “Considerations for Model Selection”; “This is because once we choose a model, we will fit a new final model on all available data and start using it to make predictions.” Examiner notes that the selected prediction model (chosen model) is used to make predictions; Model can be configured for predicting SWI index)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, and Jason. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. One of ordinary skill would have motivation to combine Tekile, Mishra, Rojas, Bonifaz, and Jason to choose a “good enough” model to best fit specific requirements needed “All models have some predictive error, given the statistical noise in the data, the incompleteness of the data sample, and the limitations of each different model type. Therefore, the notion of a perfect or best model is not useful. Instead, we must seek a model that is “good enough.”” (Jason Section “Considerations for Model Selection”).
Tekile in view of Jason does not teach The method of Claim 6, wherein the prediction model is the stack of models,
However, Belachew does teach The method of Claim 6, wherein the prediction model is the stack of models, (Belachew Paragraph 0097; “This tuning may then lead to a performance benchmark that can select the highest performing models, for example, the n top-performing models. These models may then be combined under a stacking or a winner takes all or a probabilistic importance sampling ensemble strategy.” Examiner notes that the prediction model is the stack of models)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Belachew. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. Belachew teaches forming a stack of models based on a rank. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Belachew to leverage stack of models to boost predictive accuracy, leverage divers algorithmic strengths, and reduce generalization error “a pool of machine learning models may undergo hyperparameter tuning via an extensive randomized grid search, which may be followed by a k-fold cross-validation on the classification task of interest. This tuning may then lead to a performance benchmark that can select the highest performing models, for example, the n top-performing models. These models may then be combined under a stacking or a winner takes all or a probabilistic importance sampling ensemble strategy.” (Belachew Paragraph 0097).
Tekile in view of Jason in further view of Belachew does not teach and the predicting step further comprises: creating a stacking validation set based on the plurality of SWI indexes obtained from the stack of models and the validation set;
training the final prediction model based on the stacking validation set; and
However, Jason3 does teach and the predicting step further comprises: creating a stacking validation set based on the plurality of SWI indexes obtained from the stack of models and the validation set; (Jason3 Section “Stacked Generalization”; “For example, the dataset can be split into train, validation, and test datasets. Each base-model can then be fit on the training set and make predictions on the validation dataset. The predictions from the validation set are then used to train the meta-model.” Examiner notes that a stacking validation set (predictions from the validation set) is created based on the plurality of SWI indexes (SWI indexes provided in validation dataset) obtained from the stack of models (diverse collection of models) and the validation set)
training the final prediction model based on the stacking validation set; and (Jason3 Section “Stacked Generalization”; “For example, the dataset can be split into train, validation, and test datasets. Each base-model can then be fit on the training set and make predictions on the validation dataset. The predictions from the validation set are then used to train the meta-model.” Examiner notes that the final prediction model (meta-model) is trained based on the stacking validation set (The predictions from the validation set))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, Belachew, and Jason3. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. Belachew teaches forming a stack of models based on a rank. Belachew teaches stacking ensembles for machine learning. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, Belachew, and Jason3 to leverage stack of models to boost predictive accuracy, leverage divers algorithmic strengths, and reduce generalization error “Broadly conceived, we might think of a weighted average of ensemble models as a generalization and improvement upon voting ensembles, and stacking as a further generalization of a weighted average model.” (Jason3 Section “Essence of Stacking Ensembles”).
Regarding claim 10, Tekile does not teach The method of Claim 9, wherein the set of second-preferred models comprises four (4) models of the plurality of models.
However, Belachew does teach The method of Claim 9, wherein the set of second-preferred models comprises four (4) models of the plurality of models. (Belachew Paragraph 0097; “This tuning may then lead to a performance benchmark that can select the highest performing models, for example, the n top-performing models. These models may then be combined under a stacking or a winner takes all or a probabilistic importance sampling ensemble strategy.” Examiner notes that the prediction model is the stack of models comprising n = 4 models)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Belachew. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Lefebvre teaches forming a committee of models. Belachew teaches forming a stack of models based on a rank. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Lefebvre, and Belachew to leverage stack of models to boost predictive accuracy, leverage divers algorithmic strengths, and reduce generalization error “a pool of machine learning models may undergo hyperparameter tuning via an extensive randomized grid search, which may be followed by a k-fold cross-validation on the classification task of interest. This tuning may then lead to a performance benchmark that can select the highest performing models, for example, the n top-performing models. These models may then be combined under a stacking or a winner takes all or a probabilistic importance sampling ensemble strategy.” (Belachew Paragraph 0097).
Claim(s) 11 is rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of W. Curt Lefebvre et al; US 20040249480 A1 filed on Jun 5, 2023 in further view of Shibeshih Mitiku Belachew; US 20240199743 A1 filed on Apr 13, 2022 (hereinafter “Belachew”) in further view of Jason Brownlee; “How to Develop Ridge Regression Models in Python” available Sep 21, 2023 (hereinafter “Jason4”)
Regarding claim 11, Tekile teaches The method of Claim 2, wherein the plurality of parameters consists of bicarbonate, a total dissolved solids, nitrate, nitrite, ammonium, chloride, sulphate, a pH, an electrical conductivity, calcium, magnesium, sodium, potassium, (Tekile Table 4 and Page 3 Paragraph 3; “To assess the suitability of the water for irrigation, the major physicochemical parameters associated with water quality problems were assessed. For salinity problem, electrical conductivity (EC) or total dissolved solids (TDS); for infiltration, calcium, sodium, magnesium, and sulphate as well as EC; for specific ion toxicity, sodium, chloride, boron, and chromium; and for miscellaneous effects, nutrients (nitrate-nitrogen, ammonium-nitrogen, orthophosphate, and potassium), bi carbonate, carbonate, and pH were determined.” Tekile Page 9 Paragraph 2; “The concentration of nitrite in the river was from 0.003 mg/L at Bridge One (industry effluent) and Modjo at Highway Bridge to 0.056mg/L at Bridge Two sampling points.”)
Tekile does not teach and the prediction model is the Ridge Regression.
However, Jason4 does teach and the prediction model is the Ridge Regression. (Jason2 Paragraph 3; “Ridge Regression is a popular type of regularized linear regression that includes an L2 penalty. This has the effect of shrinking the coefficients for those input variables that do not contribute much to the prediction task.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Jason4. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Jason4 teaches Ride regression models. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Jason4 to leverage Ridge Regression to reduce the coefficients for input variables that do not contribute much to the prediction task “Ridge Regression is a popular type of regularized linear regression that includes an L2 penalty. This has the effect of shrinking the coefficients for those input variables that do not contribute much to the prediction task.” (Jason4 Paragraph 3).
Claim(s) 12 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of Seok Hyun Ahn et al; “Prediction of groundwater quality index to assess suitability for drinking purpose using averaged neural network and geospatial analysis” published on Sept 19, 2023 (hereinafter “Ahn”) in further view of Jason Brownlee; “Crash Course on Multi-Layer Perceptron Neural Networks” available Jul 12, 2023 (hereinafter “Jason”)
Regarding claim 12, Tekile does not teach The method of Claim 3, wherein the plurality of parameters consists of bicarbonate, a total dissolved solids, nitrate, nitrite, ammonium, sulphate, a pH, an electrical conductivity, calcium, magnesium, sodium, potassium,
However, Ahn does teach The method of Claim 3, wherein the plurality of parameters consists of bicarbonate, a total dissolved solids, nitrate, nitrite, ammonium, sulphate, a pH, an electrical conductivity, calcium, magnesium, sodium, potassium, (Ahn Page 3 Paragraph 3; “Therefore, the analysis and modelling were carried out with 28 parameters (general bacteria, lead, fluorine, arsenic, caesium, mercury, chromium, boron, copper, zinc, chlorine, iron, manganese, aluminium, ammonium, nitrate, sulphate, potassium permanganate consumption, trichloroethylene, dichloromethane, benzene, toluene, ethylbenzene, xylene, 1,4- dioxane, total hardness, colour, and turbidity).” Examiner notes that the claims is interpreted as a Markush Claim; the cited portions shows predicting SWI index (groundwater quality index) is predicted/calculated without Chloride concentration in the plurality of parameters that consists of ammonium, sulphate, nitrate, and potassium)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz and Ahn. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Ahn teaches applying machine learning algorithms to potabile ground water to accurately predict the groundwater quality. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz and Ahn to leverage machine learning to provide a more holistic, accurate, and actionable framework for groundwater quality assessment on a national scale “Thus, the integration of machine learning algorithms and spatial analysis aims to provide a more holistic, accurate, and actionable framework for groundwater quality assessment on a national scale.” (Ahn Page 2 Paragraph 3).
Tekile in view of Ahn does not teach and the prediction model is the Multilayer Perceptron.However, Jason5 does teach and the prediction model is the Multilayer Perceptron. (Jason5 Section “Multi-Layer Perceptrons” Paragraph 1; “The field of artificial neural networks is often just called neural networks or multi-layer perceptrons after perhaps the most useful type of neural network. A perceptron is a single neuron model that was a precursor to larger neural networks.” )
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Ahn, and Jason5. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Ahn teaches applying machine learning algorithms to potabile ground water to accurately predict the groundwater quality. Jason5 teaches Multilayer Perceptrons. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Ahn, and Jason5 to develop a robust model for difficult problems “The goal is not to create realistic models of the brain but instead to develop robust algorithms and data structures that we can use to model difficult problems.” (Jason5 Section “Multi-Layer Perceptrons”).
Regarding claim 18, claim 18 has similar limitations as of claim 12, except it is a system claim (Rojas Paragraph 0028), therefore it is rejected under the same rationale as claim 12.
Claim(s) 13 is rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of Mohammed S. Hussain et al; “Management of Seawater Intrusion in Coastal Aquifers: A Review” published Nov 24, 2019 (hereinafter “Hussain”)
Regarding claim 13, Tekile does not teach The method of Claim 1, wherein the plurality of parameters further comprises a climate change parameter and a groundwater extraction scenario.
However, Hussain does teach The method of Claim 1, wherein the plurality of parameters further comprises a climate change parameter and a groundwater extraction scenario. (Hussain Paragraph 1; “The natural factors associated with the climate change and anthropogenic factors due to coastal urbanization and human activities are the main components that exacerbate the SWI problem.” Examiner notes that the plurality of parameters comprises a climate change parameter (natural factors associated with the climate change) and a groundwater extraction scenario (anthropogenic factors due to coastal urbanization and human activities))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Hussain. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Hussain teaches a comprehensive review of available hydraulic and physical management strategies that can be used to reduce and control SWI in coastal aquifers. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Hussain to prevent further degradation of the water quality “Therefore, remedial measures have to be taken to prevent further degradation of the water quality due to SWI.” (Hussain Paragraph 1).
Claim(s) 14 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of Monica Z. Bruckner et al; “Ion Chromatography” available Dec 05, 2023 (hereinafter “Bruckner”) in further view of Noira Corporation; “Karl Fischer Coulometric Titration Explained and Illustrated” available Mar 24, 2023 (hereinafter “Noira”)
Regarding claim 14, Tekile teaches The method of Claim 1, wherein the sensor network comprises [an ion chromatography], a pH meter, a TDS meter, [a titrator], and a water test kit. (Tekile Page 3 Paragraph 4; “Water pH was measured using a pH meter by just inserting the glass electrode… pro 1030 conductivity meter was used to determine EC and TDS,… Boron was tested by photometer method by adding tablet available for this to water sample. Ammonia, nitrate, and orthophosphate were measured using photometer, for which reagents are provided in the form of two tablets for maximum convenience. Carbonate and bicarbonate were measured based on unique colorimetric methods. Sulphate was determined by nephelometric test, based on a single tablet reagent containing barium chloride in a slightly acidic formulation.” Examiner notes that sensor network comprises a ph meter, TDS meter (pro 1030 conductivity meter) and a water test kit (tablets used for colorimetric methods))
Tekile does not teach an ion chromatography
However, Bruckner does teach an ion chromatography (Bruckner Section “What is Ion Chromatography” Paragraph 1; “Ion chromatography is used for water chemistry analysis. Ion chromatographs are able to measure concentrations of major anions, such as fluoride, chloride, nitrate, nitrite, and sulfate, as well as major cations such as lithium, sodium, ammonium, potassium, calcium, and magnesium in the parts-per-billion (ppb) range.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Bruckner. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Bruckner teaches Ion Chromatography. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Bruckner to be able to measure concentration of major anions for water analysis “on chromatographs are able to measure concentrations of major anions, such as fluoride, chloride, nitrate, nitrite, and sulfate, as well as major cations such as lithium, sodium, ammonium, potassium, calcium, and magnesium in the parts-per-billion (ppb) range.” (Bruckner Paragraph 1).
Tekile in view of Bruckner does not teach a titrator
However, Noira does teach a titrator (Noira Section “Coulometric vs. Volumetric” Paragraph 1; “Titration is a chemical analysis that determines the content of a substance, such as water, by adding a reagent of known concentration in carefully measured amounts until a chemical reaction is complete.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Bruckner, and Noira. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Bruckner teaches Ion Chromatography. Noira teaches Karl Fischer Coulometric titration. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Bruckner, and Noira to be able to measure low levels of free, emulsified and dissolved “Unlike other techniques, it can trace low levels of free, emulsified and dissolved (which cannot be detected with other methods such as a crackle test). When used correctly, the test is capable of measuring water levels as low as 1 ppm or 0.0001 percent.” (Noira Paragraph 3).
Regarding claim 19, claim 19 has similar limitations as of claim 14, except it is a system claim (Rojas Paragraph 0028), therefore it is rejected under the same rationale as claim 14.
Claim(s) 15 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Andinet Kebede Tekile; “Suitability Assessment of Surface Water Quality for Irrigation: A Case Study of Modjo River, Ethiopia” published Jan 27, 2023 (hereinafter “Tekile”) in view of Sudhanshu K. Mishra; “Shapley value regression and the resolution of multicollinearity” published 2016 (hereinafter “Mishra”) in further view of Pablo Meyer Rojas et al; US 20250166726 A1 filed on Nov 20, 2023 (hereinafter “Rojas”) in further view of Fernando Bonifaz et al; US 20260216748 A1 filed on Jan 10, 2023 (hereinafter “Rojas”) in further view of Jason Brownlee; “A Gentle Introduction to Model Selection for Machine Learning” available Aug 16, 2023 (hereinafter “Jason”) in further view of M. Tomaszkiewicz et al; “Development of a groundwater quality index for seawater intrusion in coastal aquifers” published April 18, 2014 (hereinafter “Tomaszkiewicz”) in further view of Mohammed S. Hussain et al; “Management of Seawater Intrusion in Coastal Aquifers: A Review” published Nov 24, 2019 (hereinafter “Hussain”) in further view of Fushcia-Ann Hoover et al; “Developing a framework for stormwater management: leveraging ancillary benefits from urban greenspace” published 2019 (hereinafter “Hoover”)
Regarding claim 15, Tekile does not teach recharging the groundwater table;
promoting water conservation;
and restricting groundwater withdrawals.
However, Hussain does teach recharging the groundwater table; (Hussain Page 7 Paragraph 2; “Within the positive or pressure barriers, the aquifer is artificially recharged by high-quality water (e.g., surface water, rainwater, extracted groundwater, treated wastewater, or desalinated water) to maintain the seaward gradient in the system by increasing the inland piezometric heads.”)
promoting water conservation; (Hussain Page 2 Paragraph 4; “Increasing the general public awareness in terms of reducing the water losses in water consumption and supply networks in residential, agricultural, and industrial sectors, and encouraging them to use renewable or recycling resources (e.g., reclaimed treated wastewater and desalinated water) can contribute to the success of water conservation plans, and hence minimize groundwater exploration.”)
and restricting groundwater withdrawals. (Hussain Page 2 Paragraph 2; “Reduction of abstraction from pumping wells is the simplest, most direct and cost-effective measure to maintain the groundwater balance in aquifers and control SWI problems.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Hussain. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Hussain teaches a comprehensive review of available hydraulic and physical management strategies that can be used to reduce and control SWI in coastal aquifers. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, and Hussain to prevent further degradation of the water quality “Therefore, remedial measures have to be taken to prevent further degradation of the water quality due to SWI.” (Hussain Paragraph 1).
Tekile in view of Hussain does not teach The method of Claim 1, wherein the adaptive ground management strategy comprises ponding surface water and stormwater runoff;
Hoover does teach The method of Claim 1, wherein the adaptive ground management strategy comprises ponding surface water and stormwater runoff; (Hoover Page 9 Paragraph 1; “identifying areas of overlap, the community can select a type of greenspace (e.g., rain gardens, street trees, urban parks, etc.) capable of providing recognized benefits (e.g., crime reduction, improved mental health, etc.), and select locations for greenspace to maximize stormwater management needs (e.g., runoff reductions) and ancillary benefits.” Examiner notes that greenspaces are used to pond surface water and stormwater runoff)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Hussain, and Hoover. Tekile teaches a suitability assessment of surface water quality for irrigation. Mishra teaches Shapley value regression and the resolution of multicollinearity. Rojas teaches selecting features based on Shapley regression values. Bonifaz teaches splitting training datasets to facilitate model training. Jason teaches model selection in machine learning. Tomaszkiewicz teaches a groundwater quality index specific to seawater intrusion that aggregates data into a comprehensible format for spatial analysis. Hussain teaches a comprehensive review of available hydraulic and physical management strategies that can be used to reduce and control SWI in coastal aquifers. Hoover teaches methods of leveraging ancillary benefits from urban greenspaces. One of ordinary skill would have motivation to Tekile, Mishra, Rojas, Bonifaz, Jason, Tomaszkiewicz, Hussain, and Hoover to help communities better manage their systems by 1) allowing stakeholders to prioritize and address their needs and concerns within a community, and 2) maximize the ecosystem service benefits received from urban greenspace “The purpose is to help communities better manage their systems by 1) allowing stakeholders to prioritize and address their needs and concerns within a community, and 2) maximize the ecosystem service benefits received from urban greenspace” (Hoover Abstract).
Regarding claim 20, claim 20 has similar limitations as of claim 15, except it is a system claim (Rojas Paragraph 0028), therefore it is rejected under the same rationale as claim 15.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL DUC TRAN whose telephone number is (571)272-6870. The examiner can normally be reached Mon-Fri 8:00-5:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Viker Lamardo can be reached at (571) 270-5871. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/D.D.T./Examiner, Art Unit 2147
/MICHAEL J HUNTLEY/Supervisory Patent Examiner, Art Unit 2129
Prosecution Insights