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 .
Claim Objections
Claims 19 and 20 are objected to because of the following informalities: Claims 19 and 20 are duplicate claims. Examiner notes that claim 20 is withdrawn from consideration for the examining purposes for being a duplicate claim of 19. Appropriate correction is required.
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 1-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more.
Step 1: Claims 1-8 are directed to a method, which is a process, falling under a statutory category of invention. Claims 9-15 are directed to a non-transitory computer readable medium, which is a manufacture, falling under a statutory category of invention. Claim 16-19 are directed to a system, which is a machine, falling under a statutory category of invention. Therefore, claims 1-19 are directed to patent eligible categories of invention.
Regarding claim 1:
Step 2A Prong 1: The following limitations under broadest reasonable interpretation recite abstract ideas:
The limitation “determining a plurality of classified well logs, one from each well log using a first machine learning (ML) network” covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the result of the machine learning network and making a judgment on the classified well logs.
The limitation “determining a classified deep sensing dataset from the deep sensing dataset using a second ML network” covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the result of the machine learning network and making a judgment on the classified deep sensing dataset.
The limitation “training a third ML network to predict the sweep efficiency based, at least in part on the plurality of classified well logs and the classified deep sensing dataset at a location of each of the wellbores” covers a mathematical concept involving mathematical calculations, mathematical equations or formulas, or mathematical relationships as shown by the following paragraphs from the specification:
[0077]: Training may be defined as the process of determining the values of all the weights and biases for each weight array and bias vector encompassed by the neural network (700).
[0078]: “To begin training the weights and biases are assigned initial values. These values may be assigned randomly, assigned according to a prescribed distribution, assigned manually, or by some other assignment mechanism. Once the weights and biases have been initialized, the neural network (700) may act as a function, such that it may receive inputs and produce an output. … The comparison of the neural network (700) output to the target(s) is typically performed by a so-called “loss function”; although other names for this comparison function such as “error function”, “objective function”, “misfit function”, and “cost function” are commonly employed.”
[0080]: “Once the weights and biases have been updated, or altered from their initial values, through a backpropagation step, the neural network (700) will likely produce different outputs. Thus, the procedure of propagating at least one input through the neural network (700), comparing the neural network (700) output with the associated target(s) with a loss function, computing the gradient of the loss function with respect to the weights and biases, and updating the weights and biases with a step guided by the gradient, is repeated until a termination criterion is reached. … Once the termination criterion is satisfied, and the weights and biases are no longer intended to be altered, the neural network (700) is said to be “trained”.”
[0082]: “Thus, by implementing the RNN, the current system state can be modeled as a function of the current sensor measurements and the preceding system state. In practice, the sensor measurements
(
…
x
n
-
1
,
x
n
,
x
n
+
1
,
…
)
that are simultaneously supplied into the network are transformed into a series of predicted systems states
(
…
y
n
-
1
,
y
n
,
y
n
+
1
,
…
)
at the network output through two sets of weights:
w
x
,
w
y
, a bias term
b
and an activation function
φ
(
.
)
:
y
n
=
φ
w
x
T
x
n
+
w
y
y
n
-
1
+
b
Equation (6).”
The limitation “determining the sweep efficiency within the hydrocarbon reservoir using the trained third machine learning network based, at least in part, on the classified deep sensing dataset” covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the result of the machine learning network and making a judgment on the sweep efficiency.
Step 2A Prong 2: The following limitations recite additional elements:
The additional elements “obtaining a well log for each of a plurality of wellbores penetrating the hydrocarbon reservoir” and “obtaining a deep sensing dataset for the hydrocarbon reservoir” do not integrate the judicial exception into a practical application because they are data gathering activities. See MPEP 2106.05(g).
Even when viewed in combination, these additional elements do not integrate the judicial exception into a practical application.
Accordingly, the claim does not recite any additional elements that integrate the judicial exception into a practical application.
Step 2B: Furthermore, the additional elements do not amount to significantly more than the judicial exception.
The limitations “obtaining a well log for each of a plurality of wellbores penetrating the hydrocarbon reservoir” and “obtaining a deep sensing dataset for the hydrocarbon reservoir” amount to data gathering activities that are akin to a well-understood, routine, and conventional activity of receiving or transmitting data over a network. See MPEP 2106.05(d)(II): “i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added))”.
Accordingly, the claim does not recite any additional elements that amount to significantly more than the judicial exception.
Therefore, claim 1 is not eligible.
Regarding claim 2: The limitation “modifying a sweep fluid injection program based, at least in part, upon the determined sweep efficiency” amounts to an additional element. However, this additional element does not integrate the judicial exception into a practical application or amount to significantly more than the judicial exception because it amounts to mere instructions to apply the judicial exception using a generic computer. Specifically, this recites modifying a computer program generically, which amounts to using a generic computer software on a generic computer. See MPEP 2106.05(f).
Regarding claim 3: The limitation “wherein the deep sensing dataset is a deep electromagnetic dataset” merely further limits the deep sensing dataset recited in claim 1. Therefore, this amounts to a mental process for the similar reason.
Regarding claim 4: The limitation “wherein training the third ML network to predict the sweep efficiency further comprises training the third ML network to predict an uncertainty in the sweep efficiency prediction” amounts to a mathematical concept for the similar reason as explained in claim 1 for the training of a third ML network.
Regarding claim 5: The limitation “wherein the sweep efficiency comprises a multi-variate probability distribution for a plurality of subsurface parameters” merely further limits the sweep efficiency recited in claim 1. Therefore, this amounts to a mental process for the similar reason. Furthermore, a multi-variate probability distribution amounts to a mathematical concept.
Regarding claim 6:
The limitation “identifying unreliable well log samples” under broadest reasonable interpretation covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the well log samples and making a judgment on unreliable ones.
The limitation “determining a validated well log by eliminating the unreliable well log samples from the well log” under broadest reasonable interpretation covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally judging on unreliable data and mentally validating the data and disregarding the unreliable data.
The limitation “estimating an uncertainty log based, at least in part, on the validated well log” under broadest reasonable interpretation covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the well log data and mentally evaluating an uncertainty.
This also amounts to a mathematical concept involving mathematical calculations, mathematical equations or formulas, or mathematical relationships as shown by the following paragraph from the specification:
[0058]: “Probability distributions may be a convenient way of capturing both a parameter value and its uncertainty in accordance with one or more embodiments. Further Bayesian statistics may form a convenient framework for combining datasets of varying uncertainties to systematically track the uncertainty of the combined datasets. FIG. 6 depicts probability distribution functions (602, 604, 606) in accordance with one or more embodiments.”
Regarding claim 7:
The limitation “identifying unreliable deep sensing dataset samples” under broadest reasonable interpretation covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the deep sensing dataset samples and making a judgment on unreliable ones.
The limitation “determining a validated deep sensing dataset log by eliminating the unreliable deep sensing dataset samples from the deep sensing dataset” under broadest reasonable interpretation covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally judging on unreliable data and mentally validating the data and disregarding the unreliable data.
The limitation “estimating an uncertainty deep sensing dataset, at least in part, on the validated deep sensing dataset” under broadest reasonable interpretation covers a mental process including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper, but for the recitation of a computer. For example, this covers a person mentally observing the well log data and mentally evaluating an uncertainty.
This also amounts to a mathematical concept involving mathematical calculations, mathematical equations or formulas, or mathematical relationships as shown by the following paragraph from the specification:
[0058]: “Probability distributions may be a convenient way of capturing both a parameter value and its uncertainty in accordance with one or more embodiments. Further Bayesian statistics may form a convenient framework for combining datasets of varying uncertainties to systematically track the uncertainty of the combined datasets. FIG. 6 depicts probability distribution functions (602, 604, 606) in accordance with one or more embodiments.”
Regarding claim 8: The limitation “wherein the first ML network and the second ML network are unsupervised ML networks” merely further limits the first ML network and the second ML network recited in claim 1. Therefore, this amounts to a mental process for the similar reasons.
Regarding claim 9: Claim 9 is substantially similar to claim 1, and therefore the similar analysis is applicable.
Furthermore, the limitation “A non-transitory computer readable medium storing instructions executable by a computer processor, the instructions comprising functionality for” amounts to an additional element which does not integrate the judicial exception into a practical application or amount to significantly more than the judicial exception because it amounts to mere instructions to apply the judicial exception using a generic computer. See MPEP 2106.05(f).
The limitations “receiving a well log for each of a plurality of wellbores penetrating a hydrocarbon reservoir” and “receiving a deep sensing dataset for the hydrocarbon reservoir” amount to additional elements that amount to data gathering activities that are akin to a well-understood, routine, and conventional activity of receiving or transmitting data over a network. See MPEP 2106.05(d)(II): “i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added))”.
Regarding claim 16: Claim 16 is substantially similar to claims 1 and 2, and therefore the similar analysis is applicable.
Furthermore, the limitation “a computer system” amounts to an additional element which does not integrate the judicial exception into a practical application or amount to significantly more than the judicial exception because it amounts to mere instructions to apply the judicial exception using a generic computer. See MPEP 2106.05(f).
The limitation “a fluid injection system configured to pump the modified sweep fluid injection program” amounts to an additional element. However, it does not integrate the judicial exception into a practical application or amount to significantly more than the judicial exception because it amounts to no more than mere instructions to apply the judicial exception and generally linking the use of a judicial exception to a particular technological environment or field of use. Specifically, this amounts to merely applying the result to the field of pumping fluid. See MPEP 2106.05(f) and 2106.05(h).
Regarding claim 17: Claim 17 further limits the fluid injection system recited in claim 16. Therefore, it amounts to mere instructions to apply the judicial exception and generally linking the use of a judicial exception to a particular technological environment or field of use for the similar reasons.
Claims 10-15, 18, and 19 are substantially similar to claims 3-8. Therefore, they are rejected for the similar reasons.
Accordingly, claims 1-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. an abstract idea) without anything significantly more.
Claim Rejections - 35 USC § 103
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-3, 5-10, and 12-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Di et al. (WO2021142406A1), hereinafter Di, in view of Belozerov et al. (“Automatic Well Log Analysis Across Priobskoe Field Using Machine Learning Methods”), hereinafter Belozerov, in further view of Alghazal et al. (US20210285326A1), hereinafter Alghazal.
Regarding claim 1, Di discloses
obtaining a well log for each of a plurality of wellbores penetrating the hydrocarbon reservoir ([0059]: “One or more well logs, and either the same or potentially additional seismic data, may then be received as input, as at 406.”);
obtaining a deep sensing dataset for the hydrocarbon reservoir ([0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”);
determining a classified deep sensing dataset from the deep sensing dataset using a second ML network ([0058]: “A first machine learning model (e.g., a network or engine) may then be trained to extract seismic features in the seismic data, as at 404.”);
training a third ML network to predict the reservoir properties based, at least in part on the plurality of … well logs and the classified deep sensing dataset at a location of each of the wellbores ([0059]: “This input, along with the seismic features extracted by the first machine learning model, may be used to train a second machine learning model to predict subsurface properties, as at 408.”); and
determining the reservoir properties within the hydrocarbon reservoir using the trained third machine learning network based, at least in part, on the classified deep sensing dataset ([0060]: “The second machine learning model may thus be configured to map the (e.g., 3D) seismic data and extracted (e.g., 2D) seismic features to the (e.g., ID) well logs, as will be described in greater detail below. The second machine learning model may then be configured to predict the subsurface properties at any location away from the existing wells”).
Di does not explicitly disclose
determining a plurality of classified well logs, one from each well log using a first machine learning (ML) network;
classified well logs; and
sweep efficiency.
However, Belozerov teaches classifying well logs data using a machine learning model (Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Belozerov on classifying well log data using a machine learning model to generate classified well log data with the teachings from Di on the well log data. The motivation to combine would have been that classifying well log data allows obtaining accurate and balanced assessment of reservoir parameters, and using a machine learning model increases efficiency of such data processing (Belozerov, Pg. 2: “The complexity of using different algorithmized approaches in solving the problems of interpretation is associated with the need to obtain an accurate and balanced assessment of reservoir parameters, as this assessment is the basis for the concept of oilfield development, from reserves estimations to the choice of infrastructure.”) (Belozerov, Pg. 10: “Besides that, interpretation by sample requires big data processing, but high resolution. On the contrary, interpretation by interval is more robust and computationally less expensive. At the same time, that branch depends on intervals' identification which is done based on logs heterogeneity. Both approaches are used in the research and results of both are combined by post-processing.”) (Belozerov, Pg. 20: “In the scope of presented paper, the problem of automatic well logs interpretation was solved using a machine learning approach. The applicability of such a class of algorithms for solving autointepretation problems was confirmed. The study of the initial data showed the presence of many noises with both natural causes and artificial, introduced by man in the processing and interpretation of the data. The probabilistic black-box approach to create a machine learning model for auto-interpretation is, in our opinion, more efficient than the more traditional process algorithmization approach using a set of deterministic heuristics.”).
Therefore, the combination of Di and Belozerov teaches
determining a plurality of classified well logs, one from each well log using a first machine learning (ML) network (Di, [0059]: “One or more well logs, and either the same or potentially additional seismic data, may then be received as input, as at 406.”) (Belozerov, Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”); and
training a third ML network to predict the reservoir properties based, at least in part on the plurality of classified well logs and the classified deep sensing dataset at a location of each of the wellbores (Di, [0059]: “This input, along with the seismic features extracted by the first machine learning model, may be used to train a second machine learning model to predict subsurface properties, as at 408.”) (Belozerov, Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”).
Di/Belozerov does not explicitly teach sweep efficiency.
However, Alghazal teaches predicting sweep efficiency from reservoir properties using a machine learning model based on deep sensing data and well log data ([0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”) ([0044]: “In regard to data preprocessing, rock types and reservoir zones data may be determined from the sponge core data and/or dielectric log data. Likewise, sponge core data and dielectric log data may be scaled. e.g., to a range of [−1, 1], for input to training and/or verification of a machine-learning model.”) ([0052]: “Once the training data is passed through all of the epochs and the model is further updated based on the model's predictions of sponge core data in each epoch, a trained model may be the final result of the machine-learning algorithm.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Alghazal on predicting sweep efficiency from reservoir properties with the teachings from Di/Belozerov on determining reservoir properties using a machine learning model. The motivation to combine would have been that sweep efficiency can be determined from reservoir properties, and determining sweep efficiency enhances the effectiveness of oil recovery process (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. For example, a degree of stimulation by an injection well may depend on the volume of the reservoir contacted by the injected fluid as well as the degree of oil saturation in various regions of the reservoir.”).
Therefore, the combination of Di/Belozerov and Alghazal teaches
training a third ML network to predict the sweep efficiency based, at least in part on the plurality of classified well logs and the classified deep sensing dataset at a location of each of the wellbores (Di, [0059]: “This input, along with the seismic features extracted by the first machine learning model, may be used to train a second machine learning model to predict subsurface properties, as at 408.”) (Belozerov, Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”) (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”); and
determining the sweep efficiency within the hydrocarbon reservoir using the trained third machine learning network based, at least in part, on the classified deep sensing dataset (Di, [0060]: “The second machine learning model may thus be configured to map the (e.g., 3D) seismic data and extracted (e.g., 2D) seismic features to the (e.g., ID) well logs, as will be described in greater detail below. The second machine learning model may then be configured to predict the subsurface properties at any location away from the existing wells”) (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”).
Regarding claim 2, Di/Belozerov teaches the method of claim 1 as above. Di/Belozerov further teaches the method, further comprising
modifying a sweep fluid injection program based on determined reservoir properties (Di, [0029]: “A processor may be provided to analyze the data (locally or remotely), make the decisions and/or actuate the controller. In this manner, oilfield 100 may be selectively adjusted based on the data collected. This technique may be used to optimize (or improve) portions of the field operation, such as controlling drilling, weight on bit, pump rates, or other parameters. … In some cases, well plans may be adjusted to select optimum (or improved) operating conditions, or to avoid problems.”).
Di/Belozerov does not explicitly teach sweep efficiency.
However, Alghazal teaches sweep efficiency determined from predicted reservoir properties (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Alghazal on the sweep efficiency determined from predicted reservoir properties with the teachings from Di/Belozerov on modifying a sweep fluid injection program based on determined reservoir properties. The motivation to combine would have been that sweep efficiency can be determined from reservoir properties, and determining sweep efficiency enhances the effectiveness of oil recovery process (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. For example, a degree of stimulation by an injection well may depend on the volume of the reservoir contacted by the injected fluid as well as the degree of oil saturation in various regions of the reservoir.”).
Therefore, the combination of Di/Belozerov and Alghazal teaches
modifying a sweep fluid injection program based, at least in part, upon the determined sweep efficiency (Di, [0029]: “A processor may be provided to analyze the data (locally or remotely), make the decisions and/or actuate the controller. In this manner, oilfield 100 may be selectively adjusted based on the data collected. This technique may be used to optimize (or improve) portions of the field operation, such as controlling drilling, weight on bit, pump rates, or other parameters. … In some cases, well plans may be adjusted to select optimum (or improved) operating conditions, or to avoid problems.”) (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”).
Regarding claim 3, Di/Belozerov/Alghazal teaches the method of claim 1 as above. Di/Belozerov/Alghazal further teaches the method, wherein
wherein the deep sensing dataset is a deep electromagnetic dataset (Di, [0026]: “The communication subassembly is adapted to send signals to and receive signals from the surface using a communications channel such as mud pulse telemetry, electro-magnetic telemetry, or wired drill pipe communications. The communication subassembly may include, for example, a transmitter that generates a signal, such as an acoustic or electromagnetic signal, which is representative of the measured drilling parameters.”).
Regarding claim 5, Di/Belozerov does not explicitly teach multi-variate probability distribution for a plurality of subsurface parameters.
However, Alghazal teaches
wherein the sweep efficiency comprises a multi-variate probability distribution for a plurality of subsurface parameters ([0049]: “Thus, the training data may be organized where an oil saturation frequency distribution falls into a normal distribution for a particular rock type and/or a particular reservoir zone.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Alghazal on probability distribution for a plurality of subsurface parameters with the teachings from Di/Belozerov on subsurface parameters. The motivation to combine would have been that doing so allows validating the data (Alghazal, [0049]: “Furthermore, the training data may require a sufficient amount of data for training and/or validating the model across various reservoirs. Thus, the training data may be organized where an oil saturation frequency distribution falls into a normal distribution for a particular rock type and/or a particular reservoir zone.”).
Regarding claim 6, Di/Belozerov does not but Alghazal teaches
identifying unreliable well log samples ([0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”);
determining a validated well log by eliminating the unreliable well log samples from the well log ([0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”); and
estimating an uncertainty log based, at least in part, on the validated well log ([0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Alghazal on identifying unreliable data and estimating an uncertainty on the validated data with the teachings from Di/Belozerov on well log data. The motivation to combine would have been that doing so allows validating data used in prediction which would improve the accuracy of the prediction (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable”).
Regarding claim 7, Di/Belozerov teaches deep sensing dataset samples (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”).
Di/Belozerov does not explicitly teach validating such data by identifying and eliminating unreliable samples and estimating an uncertainty.
However, Alghazal teaches validating such data by identifying and eliminating unreliable samples and estimating an uncertainty ([0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) ([0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) ([0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Alghazal on identifying unreliable data and estimating an uncertainty on the validated data with the teachings from Di/Belozerov on deep sensing data. The motivation to combine would have been that doing so allows validating data used in prediction which would improve the accuracy of the prediction (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable”).
Therefore, the combination of Di/Belozerov and Alghazal teaches
identifying unreliable deep sensing dataset samples (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”) (Alghazal, [0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) (Alghazal, [0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”);
determining a validated deep sensing dataset log by eliminating the unreliable deep sensing dataset samples from the deep sensing dataset (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”) (Alghazal, [0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) (Alghazal, [0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”); and
estimating an uncertainty deep sensing dataset, at least in part, on the validated deep sensing dataset (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”) (Alghazal, [0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) (Alghazal, [0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”).
Regarding claim 8, Di/Belozerov/Alghazal teaches the method of claim 1 as above. Di/Belozerov/Alghazal further teaches the method, wherein
wherein the first ML network and the second ML network are unsupervised ML networks (Di, [0056]: “Accordingly, embodiments of the present method may estimate subsurface rock properties using two machine-learning models (e.g., two deep neural networks). For example, the first model may “learn” (e.g., unsupervised or “self’ learning)”).
Regarding claim 9, claim 9 is substantially similar to claim 1, and therefore the similar analysis is applicable.
Furthermore, Di/Belozerov/Alghazal teaches
A non-transitory computer readable medium storing instructions executable by a computer processor (Di, [0005]: “Embodiments of the disclosure also include a non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a processing system, cause the processing system to perform operations.”).
Regarding claim 10, Di/Belozerov/Alghazal teaches the non-transitory computer readable medium of claim 9 as above. Di/Belozerov/Alghazal further teaches the non-transitory computer readable medium, wherein
the deep sensing dataset is a deep electromagnetic dataset (Di, [0026]: “The communication subassembly is adapted to send signals to and receive signals from the surface using a communications channel such as mud pulse telemetry, electro-magnetic telemetry, or wired drill pipe communications. The communication subassembly may include, for example, a transmitter that generates a signal, such as an acoustic or electromagnetic signal, which is representative of the measured drilling parameters.”).
Regarding claim 12, Di/Belozerov/Alghazal teaches the non-transitory computer readable medium of claim 9 as above. Di/Belozerov/Alghazal further teaches the non-transitory computer readable medium, wherein
the sweep efficiency a multi-variate probability distribution for a plurality of subsurface parameters (Alghazal, [0049]: “Thus, the training data may be organized where an oil saturation frequency distribution falls into a normal distribution for a particular rock type and/or a particular reservoir zone.”).
The combination provided for claim 5 is applicable.
Regarding claim 13, Di/Belozerov/Alghazal teaches the non-transitory computer readable medium of claim 9 as above. Di/Belozerov/Alghazal further teaches the non-transitory computer readable medium, wherein determining each of the plurality of classified well logs comprises:
identifying unreliable well log samples (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”);
determining a validated well log by eliminating the unreliable well log samples from the well log (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”); and
estimating an uncertainty log based, at least in part, on the validated well log (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”).
The combination provided for claim 6 is applicable.
Regarding claim 14, Di/Belozerov/Alghazal teaches the non-transitory computer readable medium of claim 9 as above. Di/Belozerov/Alghazal further teaches the non-transitory computer readable medium, determining the classified deep sensing dataset comprises:
identifying unreliable deep sensing dataset samples (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”) (Alghazal, [0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) (Alghazal, [0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”);
determining a validated deep sensing dataset log by eliminating the unreliable deep sensing dataset samples from the deep sensing dataset (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”) (Alghazal, [0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) (Alghazal, [0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”); and
estimating an uncertainty deep sensing dataset, at least in part, on the validated deep sensing dataset (Di, [0057]: “The method 400 may include receiving seismic data as input, as at 402. The seismic data may be gathered from one or more seismic surveys and may seismically represent the subsurface domain in a given area.”) (Alghazal, [0019]: “For example, the reservoir simulator (160) may store well logs (140) and core sample data (150), and further analyze the well log data, the core sample data, seismic data, and/or other types of data to generate and/or update the one or more machine-learning models (170).”) (Alghazal, [0033]: “Another type of logging technique includes dielectric logging. For example, dielectric permittivity may be defined as a physical quantity that describes the propagation of an electromagnetic field through a dielectric medium.”) (Alghazal, [0043]: “In regard to data preparation, sponge core data and/or dielectric log data may be quality checked and filtered to remove any spurious data points from a dataset prior to model training. … Also, sensor saturation points may be removed from the data where high measurement uncertainty exists and/or acquisition tool limitations make the data unreliable.”).
The combination provided for claim 7 is applicable.
Regarding claim 15, Di/Belozerov/Alghazal teaches the non-transitory computer readable medium of claim 9 as above. Di/Belozerov/Alghazal further teaches the non-transitory computer readable medium, wherein
the first ML network and the second ML network are unsupervised ML networks (Di, [0056]: “Accordingly, embodiments of the present method may estimate subsurface rock properties using two machine-learning models (e.g., two deep neural networks). For example, the first model may “learn” (e.g., unsupervised or “self’ learning)”).
Regarding claim 16, claim 16 is substantially similar to claims 1-2, and therefore the similar analysis is applicable.
Furthermore, Di/Belozerov/Alghazal teaches
a computer system (Di, [0075]: “In some embodiments, any of the methods of the present disclosure may be executed by a computing system.”); and
a fluid injection system configured to pump the modified sweep fluid injection program (Di, [0029]: “Surface unit 134 may include transceiver 137 to allow communications between surface unit 134 and various portions of the oilfield 100 or other locations. Surface unit 134 may also be provided with or functionally connected to one or more controllers (not shown) for actuating mechanisms at oilfield 100. Surface unit 134 may then send command signals to oilfield 100 in response to data received. Surface unit 134 may receive commands via transceiver 137 or may itself execute commands to the controller. … In this manner, oilfield 100 may be selectively adjusted based on the data collected. This technique may be used to optimize (or improve) portions of the field operation, such as controlling drilling, weight on bit, pump rates, or other parameters.”).
Regarding claim 17, Di/Belozerov/Alghazal teaches the system of claim 16 as above. Di/Belozerov/Alghazal further system the method, wherein the fluid injection system comprises:
a source of injection fluid; at least one injection fluid pump connected to the source of injection fluid; and a plurality of injection wellbore penetrating the hydrocarbon reservoir and connected to injection fluid pump (Di, [0029]: “Surface unit 134 may include transceiver 137 to allow communications between surface unit 134 and various portions of the oilfield 100 or other locations. Surface unit 134 may also be provided with or functionally connected to one or more controllers (not shown) for actuating mechanisms at oilfield 100. Surface unit 134 may then send command signals to oilfield 100 in response to data received. … This technique may be used to optimize (or improve) portions of the field operation, such as controlling drilling, weight on bit, pump rates, or other parameters.”) (Di, [0033]: “Figure ID illustrates a production operation being performed by production tool 106.4 deployed from a production unit or Christmas tree 129 and into completed wellbore 136 for drawing fluid from the downhole reservoirs into surface facilities 142. The fluid flows from reservoir 104 through perforations in the casing (not shown) and into production tool 106.4 in wellbore 136 and to surface facilities 142 via gathering network 146.”) (Di, [0035]: “Production may also include injection wells for added recovery. One or more gathering facilities may be operatively connected to one or more of the wellsites for selectively collecting downhole fluids from the wellsite(s).”) (Di, [0047]: “Each wellsite 302 has equipment that forms wellbore 336 into the earth. The wellbores extend through subterranean formations 306 including reservoirs 304. These reservoirs 304 contain fluids, such as hydrocarbons. The wellsites draw fluid from the reservoirs and pass them to the processing facilities via surface networks 344. The surface networks 344 have tubing and control mechanisms for controlling the flow of fluids from the wellsite to processing facility 354.”).
Regarding claim 18, Di/Belozerov/Alghazal teaches the system of claim 16 as above. Di/Belozerov/Alghazal further teaches the system, wherein
the deep sensing dataset is a deep electromagnetic dataset (Di, [0026]: “The communication subassembly is adapted to send signals to and receive signals from the surface using a communications channel such as mud pulse telemetry, electro-magnetic telemetry, or wired drill pipe communications. The communication subassembly may include, for example, a transmitter that generates a signal, such as an acoustic or electromagnetic signal, which is representative of the measured drilling parameters.”).
Claim(s) 4, 11, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Di in view of Belozerov in further view of Alghazal in further view of Al-Nasser et al. (US20210224682A1), hereinafter Al-Nasser.
Regarding claim 4, Di/Belozerov/Alghazal does not explicitly teach predict an uncertainty.
However, Al-Nasser teaches determining an uncertainty in the predicted data ([0034]: “The computer system determines a logging frequency 118 by uncertainty bound analysis to determine a gap between the measured and predicted data. A greater bound suggests that the logging frequency 118 should be increased for the targeted hydrocarbon well or areas.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings from Al-Nasser on predict an uncertainty in the sweep efficiency prediction with the teachings from Di/Belozerov/Alghazal on sweep efficiency prediction. The motivation to combine would have been that doing so allows assessing the accuracy of the predicted data which allows modifying the calculations accordingly to improve accuracy (Al-Nasser, [0034]: “The computer system determines a logging frequency 118 by uncertainty bound analysis to determine a gap between the measured and predicted data. A greater bound suggests that the logging frequency 118 should be increased for the targeted hydrocarbon well or areas. On the other hand, a lesser bound suggests that the logging frequency 118 should be decreased.”).
Therefore, the combination of Di/Belozerov/Alghazal and Al-Nasser teaches
wherein training the third ML network to predict the sweep efficiency further comprises training the third ML network to predict an uncertainty in the sweep efficiency prediction (Di, [0059]: “This input, along with the seismic features extracted by the first machine learning model, may be used to train a second machine learning model to predict subsurface properties, as at 408.”) (Belozerov, Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”) (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”) (Al-Nasser, [0034]: “The computer system determines a logging frequency 118 by uncertainty bound analysis to determine a gap between the measured and predicted data. A greater bound suggests that the logging frequency 118 should be increased for the targeted hydrocarbon well or areas.”).
Regarding claim 11, Di/Belozerov/Alghazal teaches the non-transitory computer readable medium of claim 9 as above. Di/Belozerov/Alghazal/Al-Nasser further teaches the non-transitory computer readable medium, wherein
training the third ML network to predict the sweep efficiency further comprises training the third ML network to predict an uncertainty in the sweep efficiency prediction (Di, [0059]: “This input, along with the seismic features extracted by the first machine learning model, may be used to train a second machine learning model to predict subsurface properties, as at 408.”) (Belozerov, Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”) (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”) (Al-Nasser, [0034]: “The computer system determines a logging frequency 118 by uncertainty bound analysis to determine a gap between the measured and predicted data. A greater bound suggests that the logging frequency 118 should be increased for the targeted hydrocarbon well or areas.”).
The combination for claim 4 is applicable.
Regarding claim 19, Di/Belozerov/Alghazal teaches the system of claim 16 as above. Di/Belozerov/Alghazal/Al-Nasser further teaches the system, wherein
training the third ML network to predict the sweep efficiency further comprises training the third ML network to predict an uncertainty in the sweep efficiency prediction (Di, [0059]: “This input, along with the seismic features extracted by the first machine learning model, may be used to train a second machine learning model to predict subsurface properties, as at 408.”) (Belozerov, Pg. 10: “Well logs autointerpretation can be routinely solved by machine learning methods. … In term of machine learning strategy well logs autointerpretation may be resolved by three possible ways: Classification. In this case each depth sample is assigned to some class (lithology code, saturation type).”) (Alghazal, [0066]: “With regard to a reservoir sweep efficiency, a reservoir sweep efficiency may correspond to a measured degree of effectiveness of an enhanced oil recovery process with respect to a reservoir. … Thus, volumetric sweep efficiency of a reservoir may be based on a selected injection pattern, off-pattern wells, fractures in the reservoir, position of gas-oil and oil/water contact interfaces, reservoir thickness, permeability and areal and vertical heterogeneity, and other parameters. For example, sponge core data may be used in connection with other types of core sample data and well log data. … Reservoir sweep efficiency may be used to define the recovery potential of a reservoir region of interest.”) (Al-Nasser, [0034]: “The computer system determines a logging frequency 118 by uncertainty bound analysis to determine a gap between the measured and predicted data. A greater bound suggests that the logging frequency 118 should be increased for the targeted hydrocarbon well or areas.”).
The combination for claim 4 is applicable.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Vallabhaneni et al. (US20220075915A1) discloses training a first machine learning model to generate one or more integrated enhanced logs based, at least in part, on an integrated data set, wherein the integrated data set includes seismic data and well log data.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HEIN JEONG whose telephone number is (703)756-1549. The examiner can normally be reached M-F 9am-5pm ET.
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, Renee Chavez can be reached at (571) 270-1104. 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.
/HEIN JEONG/Examiner, Art Unit 2186
/RENEE D CHAVEZ/Supervisory Patent Examiner, Art Unit 2186
Prosecution Insights