DETAILED ACTION
Claims 1 – 16 have been presented for examination.
This office action is in response to submission of the application on 03/17/2022.
The instant office action relies on Moreno et al. “Application of Critical Drawdown Pressure Prediction in Completion Design to Minimize Sanding in a elastic Gas Reservoir in Saudi Arabia” and Drebit et al. (US 7660670) and Mese et al. (US 7653488) which are cited on the IDS.
Claim Objections
Claim 1 is objected to because of the following informalities: it uses a comma after the “drilling”. However, the other similarly indented limitations use a semi-colon. The interpretation for examination purposes is a semi-colon.
Claim 5 is objected to because of the following informalities: it uses the acronyms MRGC and k-NN which are defined in claims 3 and 4, respectively. However, claim 5 does not depend from claims 3 of 4. The interpretation of the acronyms for examination purposes are as in claims 3 and 4.
Claim 13 is objected to because of the following informalities: the pressure variables in the equation are not explicitly defined. From the limitation the P_CD appears to be critical drawdown pressure, P_F the reservoir pressure, and P_W,Min the minimum well bottom hole flowing pressure P_W. This is the interpretation for examination purposes.
Further, the claim recites “the model” which does not explicitly refer back to the “trained model”. This is the interpretation for examination purposes.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claim 10, 12, 14 and 16 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
With regard to claim 10, it recites “trial and error method” and “best” in “wherein the number of clusters is assessed using a trial and error method by going back and forth and assessing an error margin with different number of clusters to determine which fit best”. The metes and bound of the “trial and error method” are not clear, especially since the claim is to a method and therefore the required steps could be recited. Further, it recites that evaluating a criteria of “fit best” which is a relative term. The limitation is interpreted for examination purposes as any method involving trials and errors and a desirable fit.
With regard to claim 12, it recites “wherein the weighting factors” which lacks proper antecedent basis since there is no recited “weighting factors” in parent claims 1 or 9. Examiner notes that claim 11 recited “weighting factors”. The limitation is interpreted for examination purposes as depending from claim 11.
With regard to claim 14, it recites “DNN” and “CNN” which specific types of “NN”. Therefore, reciting the combination is unclear. Further, there is recited “or any other algorithm” which makes the claim further unclear since it does not appear to limit the scope of the parent claim by allowing any and all possible algorithms for the machine learning. The limitation is interpreted for examination purposes as resulting in any type of trained model.
With regard to claim 16, it recites “the MRGC” in “wherein the MRGC uses the ranking of the FE and MEM data”. However, there is no previously recited “MRGC” in the parent claim. The limitation is interpreted for examination purposes as having proper antecedent basis to a multi-resolution graph-clustering.
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 – 16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Independent claim 1 recites at Step 1 a statutory category (i.e. a process) method for predicting sand production in a formation, comprising the steps: determining a critical drawdown pressure (CDP) from the output of the trained model; and predicting the sand production from the CDP. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “determining” and “predicting” amounts to modeling actions recited at a high-level of generality, in combination with received outputs. Accordingly, the claim recites an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention further claims: drilling a well that penetrates the formation, gathering petrophysical formation evaluation (FE) data and Mechanical Earth Model (MEM) data from the well; entering the FE and MEM data as input into a trained model. The “drilling” in combination with the “gathering” amounts to insignificant data gathering since it is recited at a high-level of generality, and since the “entering” step relies on the received elements in a generic manner (see MPEP 2106.04(d)). The “entering” step also amounts to insignificant data gathering in combination with a trained mode. The claim is directed to an abstract idea.
At Step 2B the claim does not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception. The “drilling” amounts to covers well-understood, routine, and conventional activity since it generally known at the time the application was filed (see the instant application Paragraph 1 in Background Wellbores are drilled into a reservoir of a formation to access the fluids stored in the reservoir.”). The recited “gathering” and “entering” covers well-understood, routine, and conventional activity since it is generic and covers receiving and outputting data by any electronics means (see MPEP 2106.05(d)(II) “i. Receiving or transmitting data over a network”). Considering the additional elements in combination does not add anything more than when considering them individually since they are all data gathering steps. For at least these reasons, the claim is not patent eligible.
Dependent claim 2 – 5, 7 – 8 and 11 - 16 recite(s) at Step 1 the same statutory category as the parent claim(s). Accordingly, the claim(s) recite(s) an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention further claims: Claim 2 wherein the FE and MEM data are gathered as plots showing data points versus depth of the well; Claim 3 wherein the trained model comprises multi-resolution graph-based clustering (MRGC); Claim 4 wherein the trained model comprises a k-nearest neighbors (k-NN) algorithm; Claim 5 wherein the trained model comprises MRGC and k-NN, wherein the MRGC algorithm is performed after the k-NN algorithm; Claim 7 wherein the FE data comprises porosity, permeability, and water saturation of the formation; Claim 8 wherein the MEM data comprises stress, fluid pressure, temperature, fluid content, pore pressure and magnitude and orientation of the maximum, intermediate and minimum principal and horizontal stresses, inclination of the wellbore (dip), and unconfined compressive strength; Claim 11 wherein at least one of the FE and MEM data are weighted with weighting factors; Claim 12 wherein the weighting factors decrease as function of the depth of a well; Claim 13 wherein the model calculates the CDP by the maximum difference between a reservoir pressure and a minimum well bottom hole flowing pressure Pw that the formation withstands without sand being produced along with the formation fluid: Pcv = PF - Pw Min; Claim 14 wherein the trained model comprises any machine learning algorithm such as Extra Trees algorithm, XGBoost algorithm, Neural Networks (NN), Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), or any other algorithm; Claim 15 wherein the FE and MEM data are ranked in a statistical analysis that compares offset data against the impact of change per data point and rank inputs per impact; Claim 16 wherein the MRGC uses the ranking of the FE and MEM data. For example, the “FE and MEM data are” and “FE data comprises” and “MEM data comprises” and “FE and MEM data are” and “weighting factors decrease” and “FE and MEM data are ranked” amount to insignificant data gathering since they further limit the content of the data in the parent claim 1 “gathering” or parent claim 11 “FE and MEM data are” without further limited how the data is gathered (see MPEP 2106.04(d)). The ”trained model comprises” and “model calculates” amounts to insignificant data gathering since it further limits the “entering” of the parent claim 1 with regard to the specific trained model without modifying how the data is entered (see Claim Rejections - 35 USC § 112 regarding “model calculates”). The “MRGC uses” amounts to insignificant data gathering since it further limits an MRGC algorithm merely using ranked data (see Claim Rejections - 35 USC § 112). The claim is directed to an abstract idea. At Step 2B the claim(s) do not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception. The recited “FE and MEM data are” and “FE data comprises” and “MEM data comprises” and “FE and MEM data are” and “weighting factors decrease” and “FE and MEM data are ranked” and ”trained model comprises” and “MRGC uses” covers well-understood, routine, and conventional activity since it is generic and covers gathering and entering data by any electronics means (see MPEP 2106.05(d)(II) “i. Receiving or transmitting data over a network”). Considering the additional elements in combination does not add anything more than when considering them individually since they are all data gathering steps. For at least these reasons, the claim(s) are not patent eligible.
Dependent claims 6 and 9 – 10 recite(s)at Step 1 the same statutory category as the parent claim(s), and further recite(s): Claim 6 wherein the trained model is trained by classifying a training dataset with k-NN, and blind-testing the classified dataset with the training dataset and the testing dataset; Claim 9 wherein a number of clusters is assessed as a result of the training of the trained model; Claim 10 wherein the number of clusters is assessed using a trial and error method by going back and forth and assessing an error margin with different number of clusters to determine which fit best. At Step 2A, Prong I the recited limitations, alone or in combination, amount to steps that, under its broadest reasonable interpretation, cover performance of the limitations in the mind in combination with using a pen and paper (see MPEP 2106.04(a)(2)(III)). For example, the “classifying” and “blind-testing” cover any analytical process for performing the intended result. Looking at the disclosure, there is no algorithm for performing the “classifying” and “blind-testing”, and nothing preclude performance in the mind using judgements and evaluations from a dataset. The “assessed” and “going back and forth and assessing” requires no more than judgement and evaluations. Accordingly, the claim(s) recite(s) an abstract idea.
At Step 2A, Prong II this judicial exception is not integrated into a practical application since the claimed invention does not recite any further limitation. The claim is directed to an abstract idea.
At Step 2B the claims do not recite additional elements that, alone or in an ordered combination, are sufficient to amount to significantly more than the judicial exception since there are no further limitations recited. For at least these reasons, the claims are not patent eligible.
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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1 – 6, 9 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Moreno et al. “Application of Critical Drawdown Pressure Prediction in Completion Design to Minimize Sanding in a elastic Gas Reservoir in Saudi Arabia” (henceforth “Moreno”) in view of Pirrone et al. “HOW MACHINE LEARNING EDUCES INTRINSIC PETROPHYSICAL KNOWLEDGE FROM LEGACY DATA: A CASE HISTORY FROM A MATURE FIELD” (henceforth “Pirrone”). Moreno and Pirrone are analogous art because they solve the same problem of predicting sand formation, and because they are from the same field of oil and gas exploration.
With regard to claim 1, Moreno teaches a method for predicting sand production in a formation, comprising the steps: (Abstract “The objective of this paper is to present and highlight the applications of geomechanics in predicting critical drawdown pressure during the completion design and flowback test design with the ultimate purpose of minimizing the sand production”)
drilling a well that penetrates the formation, (Page 1 a well can be drilled in a formation “The first case is Well_ A drilled in a Devonian elastic reservoir, this vertical gas well was perforated with 60 degrees phasing guns”)
gathering petrophysical formation evaluation (FE) data and Mechanical Earth Model (MEM) data from the well; (Page 3, Top data from wells is obtained (petrophysical formation evaluation) to form an earth model “An initial data udit is carried out assess the data available to build a Mechanical Earth Model. The MEM is a mathematical representation of all geomechanics knowledge available for a well location, field or basin … Data from the offset wells were used to build and calibrate the MEM”)
determining a critical drawdown pressure (CDP) from the output of a trained model; and (Page 4, Top the calibrated model is used to predict failure criterion “Sand production onset is triggered by three chronological steps as it is shown in Figure-4: 1.) Rock exceeds its failure criteria, this is mainly composed of a failure criterion and a constitutive model … The output of the calibrated geomechanical model will be used to calculate CDP using a failure criteria model”)
predicting the sand production from the CDP. (Page 4, Bottom “The CDP will be reported on the foot-by-foot bases in order to identify interval(s) that are potentially prone to produce sand.”)
Moreno does not appear to explicitly disclose: entering the FE and MEM data as input into a trained model.
However, Pirrone teaches:
entering FE and MEM data as input into a trained model. (Page 2, Bottom “The methodology presented in this paper consists of the following steps (Fig 1): 1. Selection of a reliable and statistically representative training set consisting of open-hole logs and petrophysical parameters coming from their modeling; 2. Learning phase on the training set by means of MRGC approach; 3. Definition of the proper template in term of K-nearest-neighbors (KNN) process for petrophysical log prediction; Blind test of data-driven formation evaluation”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 2, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the FE and MEM data are gathered as plots showing data points versus depth of the well. (Pirrone Figure 2 desired data can be displayed in plot format vs depth
PNG
media_image1.png
193
351
media_image1.png
Greyscale
)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 3, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the trained model comprises multi-resolution graph-based clustering (MRGC). (Pirrone Page 2, Bottom “The methodology presented in this paper consists of the following steps (Fig 1): 1. Selection of a reliable and statistically representative training set consisting of open-hole logs and petrophysical parameters coming from their modeling; 2. Learning phase on the training set by means of MRGC approach; 3. Definition of the proper template in term of K-nearest-neighbors (KNN) process for petrophysical log prediction; Blind test of data-driven formation evaluation”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 4, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the trained model comprises a k-nearest neighbors (k-NN) algorithm. (Pirrone Figure 1
PNG
media_image2.png
296
442
media_image2.png
Greyscale
)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 5, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the trained model comprises MRGC and k-NN,
wherein the MRGC algorithm is performed after the k-NN algorithm. (Pirrone Abstract “The implemented methodology takes advantage of the Multi-Resolution Graph-based Clustering (MRGC) approach that gathers its knowledge by recognizing patterns in well logs by means of non-parametric K-nearest-neighbor and graph data representation.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 6, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the trained model is trained by classifying a training dataset with k-NN, and blind-testing the classified dataset with the training dataset and the testing dataset. (Pirrone Page 2, Bottom “The methodology presented in this paper consists of the following steps (Fig 1): 1. Selection of a reliable and statistically representative training set consisting of open-hole logs and petrophysical parameters coming from their modeling; 2. Learning phase on the training set by means of MRGC approach; 3. Definition of the proper template in term of K-nearest-neighbors (KNN) process for petrophysical log prediction; 4. Blind test of data-driven formation evaluation.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 9, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein a number of clusters is assessed as a result of the training of the trained model. (Pirrone Page 3, Top “Then, NI is used to build the Kernel Representative Index (KRI) in order to select the cluster kernels and their optimal number”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
With regard to claim 14, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the trained model comprises any machine learning algorithm such as Extra Trees algorithm, XGBoost algorithm, Neural Networks (NN), Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), or any other algorithm. (Pirrone Abstract “The implemented methodology takes advantage of the Multi-Resolution Graph-based Clustering (MRGC) approach that gathers its knowledge by recognizing patterns in well logs by means of non-parametric K-nearest-neighbor and graph data representation.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno with the steps of training a model using MRGC disclosed by Pirrone. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of desired petrophysical parameters for any related analyses (Pirrone Abstract “This allows the system to learn through experience how log measurements are related to important petrophysical parameters (e.g. porosity, water saturation, and permeability).”)
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Moreno in view of Pirrone, and further in view of Nouri et al. “Sand-Production Prediction: A New Set of Criteria for Modeling Based on Large-Scale Transient Experiments and Numerical Investigation” (henceforth “Nouri”). Moreno and Pirrone and Nouri are analogous art because they solve the same problem of predicting sand formation, and because they are from the same field of oil and gas exploration.
With regard to claim 7, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and does not appear to explicitly disclose: wherein the FE data comprises porosity, permeability, and water saturation of the formation.
However, Nouri teaches:
wherein FE data comprises porosity, permeability, and water saturation of the formation. (Page 228, Left “hey used an elastic/perfectly plastic deformation model with Mohr-Coulomb yield criterion. In their model, cohesion, elastic modulus, permeability, and sand-production coefficient are all linked to porosity by a set of calibration parameters … In many unconsolidated formations, onset of sanding is often observed to be concomitant with water cut (Tronvoll et al. 2001; Vaziri et al. 2002). Han and Dusseault (2002) and Vaziri et al. (2002) proposed various possible mechanisms that may hasten the instability depending on the degree of water saturation and the cement mineralogy”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the data collection for modeling disclosed by Nouri. One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of sand production (Nouri Abstract).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Moreno in view of Pirrone, and further in view of Mese et al. (US 7653488) (henceforth “Mese (488)”). Moreno and Pirrone and Mese (488) are analogous art because they solve the same problem of predicting sand formation, and because they are from the same field of oil and gas exploration.
With regard to claim 8, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and further teaches:
wherein the MEM data comprises inclination of the wellbore (dip), and (Moreno Page 2, Middle “The magnitudes of the tangential and radial stresses acting on a borehole or opening are controlled by The magnitude and orientation of the principal reservoir (far field) stresses, the inclination of the well bore/perforation cavity stress field with the reservoir stress field, for the porn-elastic condition ( effective stress), the pore pressure in the reservoir at any time, and the well flowing pressures”)
unconfined compressive strength. (Moreno Page 4, Middle “Shear failure occurs when the tangential effective stress around the perforation exceeds the formation compressive strength causing failure.”)
Moreno in view of Pirrone does not appear to explicitly disclose: wherein the MEM data comprises stress, fluid pressure, temperature, fluid content, pore pressure and magnitude and orientation of the maximum intermediate and minimum principal and horizontal stresses.
However, Mese (488) teaches:
wherein MEM data comprises stress, (Col. 8, Lines 14 – 24 direction of principal stresses are known, and could coincide with horizontal stresses
PNG
media_image3.png
187
376
media_image3.png
Greyscale
)
fluid pressure, temperature, fluid content, pore pressure and (Abstract “A relationship among a second set of characteristics of the wellbore is determined using an effective stress model, wherein the second set comprises a drawdown pressure, a production rate, pore pressure, a temperature and a viscosity of a fluid in the wellbore, a fluid flow pressure in the wellbore, a drag force of fluid flow in the wellbore, and a type of fluid flow in the well bore. A critical total strain is determined for the formation using the first set of characteristics and the relationship.”)
magnitude and orientation of the maximum, intermediate and minimum principal stresses and horizontal stresses, (Col. 8, Lines 14 – 24 direction of principal stresses are known, and could coincide with horizontal stresses
PNG
media_image3.png
187
376
media_image3.png
Greyscale
, and Col. 15, Lines 23 – 26 orientation of horizontal stress is already known as being horizontal (orientation) “Graph 800 considers all three major stresses, including maximum horizontal stress, minimum horizontal stress, and intermediate stresses.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the data collection for modeling disclosed by Mese (488). One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation sand production (Mese (488) Abstract).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Moreno in view of Pirrone, and further in view of Ye et al. “A NEW TOOL FOR ELECTRO-FACIES ANALYSIS: MULTI-RESOLUTION GRAPH-BASED CLUSTERING” (henceforth “Ye”). Moreno and Pirrone and Ye are analogous are because they are from the same field of oil and gas exploration.
With regard to claim 10, Moreno in view of Pirrone teaches all the elements of the parent claim 9, and does not appear to explicitly disclose: wherein the number of clusters is assessed using a trial and error method by going back and forth and assessing an error margin with different number of clusters to determine which fit best.
However, Ye teaches:
wherein a number of clusters is assessed using a trial and error method by going back and forth and assessing an error margin with different number of clusters to determine which fit best. (Page 2, Right a set of electrofacies after having clusters merged could be reexamained and reinterpreted, where this process could be desirably repeated (trial and error method by going back and forth) “* The density patterns seen on the crossplots and the patterns shown by the log curves could be used as efficient guidelines for merging small dusters in.to geologically pertinent electrofacies. * Whenever a sedimentologist was given an electrofacies description emphasizing patterns displayed rum, by logs, he had a different look at the cores. In reexamination often led to reinterpretation of both types of data.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the cluster merging disclosed by Ye. One of ordinary skill in the art would have been motivated to make this modification in order to better represent the lithofacies (Ye Page 2, Right).
Claims 11 – 12 are rejected under 35 U.S.C. 103 as being unpatentable over Moreno in view of Pirrone, and further in view of Marx et al. (CA 2794094) (henceforth “Marx (094)”). Moreno and Pirrone and Marx (094) are analogous are because they are from the same field of oil and gas exploration.
With regard to claim 11, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and does not appear to explicitly disclose: wherein at least one of the FE and MEM data are weighted with weighting factors.
However, Marx (094) teaches:
wherein at least one of the FE and MEM data are weighted with weighting factors. (Paragraph 102 “According to an embodiment, the prediction engine 20 may be implemented by a computer program which may receive various data inputs that may be converted to a unified format using a conversion program … According to an embodiment, a depth-weighted smoother with a 1-meter window (e.g. the depth point has 0.2 m sampling frequency, 1 meter window corresponds to 5 data points). The weight assigned to each data point in each window is inversely proportional to the depth interval between it and the current point.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the data processing for prediction disclosed by Marx (094). One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of sand production (Marx (094) Abstract).
With regard to claim 12, Moreno in view of Pirrone teaches all the elements of the parent claim 9, and further teaches: (see Claim Rejections - 35 USC § 112 for dependency from claim 11)
wherein the weighting factors decrease as function of the depth of a well. (Marx (094) Paragraph 102 “The weight assigned to each data point in each window is inversely proportional to the depth interval between it and the current point.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the data processing for prediction disclosed by Marx (094). One of ordinary skill in the art would have been motivated to make this modification in order to enhance interpretation of sand production (Marx (094) Abstract).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Moreno in view of Pirrone, and further in view of Drebit et al. (US 7660670) (henceforth “Drebit (670)”). Moreno and Pirrone and Drebit (670) are analogous art because they solve the same problem of predicting sand formation, and because they are from the same field of oil and gas exploration.
With regard to claim 13, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and does not appear to explicitly disclose: wherein the model calculates the CDP by the maximum difference between a reservoir pressure and a minimum well bottom hole flowing pressure Pw that the formation withstands without sand being produced along with the formation fluid: Pcv = PF - Pw Min.
However, Drebit (670) teaches:
wherein a model calculates CDP by the maximum difference between a reservoir pressure and a minimum well bottom hole flowing pressure Pw that the formation withstands without sand being produced along with the formation fluid: Pcv = PF - Pw Min·(Col. 8, Lines 25 – 27 difference between A and B is reasonably interpreted as A – B “The CDPP is measured as pressure difference between the formation and the well bore … Secondly, a criteria is established relating to the level of CDPP sufficient to initiate sand failure in the proximity of target drilling area according to a geomechanics based model”, and Col. 4, Lines 39 – 42 it is reasonably inferred that there is a minimum bottom hole pressure that can be used for production since having higher productivity would decrease the pressure in the well bore while eventually producing sand as the upper limit of the productivity “The productivity is directly related to the sand strength. Inducing failure of a pay sand, by exceeding its critical drawdown pressure (CDPP), creates a producing sand.”)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the critical drawdown evaluation disclosed by Drebit (670). One of ordinary skill in the art would have been motivated to make this modification in order to evaluate a well for sand production (Drebit (670) Col. 4, Lines 39 – 42).
Claims 15 – 16 are rejected under 35 U.S.C. 103 as being unpatentable over Moreno in view of Pirrone, and further in view of Tian et al. “Multi-resolution graph-based clustering analysis for lithofacies identification from well log data: Case study of intraplatform bank gas fields, Amu Darya Basin” (henceforth “Tian”). Moreno and Pirrone and Tian are analogous art because they are from the same field of oil and gas exploration.
With regard to claim 15, Moreno in view of Pirrone teaches all the elements of the parent claim 1, and does not appear to explicitly disclose: wherein the FE and MEM data are ranked in a statistical analysis that compares offset data against the impact of change per data point and rank inputs per impact.
However, Tian teaches:
an FE and MEM data are ranked in a statistical analysis that compares offset data against the impact of change per data point and rank inputs per impact. (Page 601, Left “To identify the clusters, the NI of each point in the data set was calculated. Subsequently, small natural groups of the points were formed based on the NI to determine a KNN attraction for each point. Independently, an optimal number of clusters was calculated based on the KRI. Finally, the terminal clusters were formed by merging the small clusters”, and Page 600, Right NI based difference from min, then normalized to create an index for each datapoint
PNG
media_image4.png
157
149
media_image4.png
Greyscale
)
It would have been obvious to one of ordinary skill in the art to combine the method of predicting CDP disclosed by Moreno in view of Pirrone with the NI to divide the training data disclosed by Tian. One of ordinary skill in the art would have been motivated to make this modification in order to enhance the modeling of the earth (Tian Abstract).
With regard to claim 16, Moreno in view of Pirrone, and further in view of Tiran teaches all the elements of the parent claim 15, and further teaches:
wherein the MRGC uses the ranking of the FE and MEM data. (Tian Page 601, Left and Figure 2 the NI is used in the clustering, which is then used for MRGC algorithm
PNG
media_image5.png
196
352
media_image5.png
Greyscale
)
Examiner General Comments
With regard to the prior art rejection(s), any cited portion of the relied upon reference(s), either by pointing to specific sections or as quotations, is intended to be interpreted in the context of the reference(s) as a whole as would be understood by one of ordinary skill in the art. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in their entirety as potentially teaching all or part of the claimed invention since the entire reference is considered to provide disclosure relating to the cited portions. Further, the claims and only the claims form the metes and bounds of the invention. Office personnel are to give the claims their broadest reasonable interpretation in light of the supporting disclosure. Unclaimed limitations appearing in the specification are not read into the claim. Prior art was referenced using terminology familiar to one of ordinary skill in the art. Such an approach is broad in concept and can be either explicit or implicit in meaning. Examiner’s notes are provided with the cited references to assist the applicant to better understand how the examiner interprets the applied prior art. Such comments are entirely consistent with the intent and spirit of compact prosecution.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALFRED H. WECHSELBERGER whose telephone number is (571)272-8988. The examiner can normally be reached M - F, 10am to 6pm.
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, Emerson Puente can be reached at 571-272-3652. 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.
/ALFRED H. WECHSELBERGER/ExaminerArt Unit 2187
/EMERSON C PUENTE/Supervisory Patent Examiner, Art Unit 2187