DETAILED ACTION
Claims 1-14 are presented for examination.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Drawings
The drawings received on 10 May 2022 are accepted.
Claim Objections
Claim 8 is objected to because of the following informalities:
Claim 8 is missing a period at the end.
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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 13 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 pre-AIA the applicant regards as the invention.
Claim 13 recites the limitation "the measurements". There is insufficient antecedent basis for this limitation in the claim. Examiner suggests amending claim 13 to depend from claim 12.
Claim Rejections - 35 USC § 101 – Software per se
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 8-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter in the form of software per se. See MPEP §2106.03.
Claim 8 is directed to “A computer program.” Claim8, taken as a whole, fails to include a particular machine (hardware component) or otherwise limit the claims to one of the four categories of statutory subject matter. Each component can reasonably be interpreted as software. Software, by itself, is nonstatutory subject matter. See MPEP §2106.03(I). Software is not one of the four categories of statutory subject matter. Accordingly, when all of the components are interpreted as software, claim 8 is directed to software per se.
Claims 9-14 further recite additional software steps which fail restrict the claim to one of the four categories of statutory subject matter.
Examiner recommends amending claim 8 as follows:
A non-transitory computer readable medium storing a computer program
Dependent claims 9-14 would require corresponding amendment to their preambles to maintain consistency with claim 8.
Claim Rejections - 35 USC § 101 – Abstract Idea
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 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
To determine if a claim is directed to patent ineligible subject matter, the Court has guided the Office to apply the Alice/Mayo test, which requires:
1. Determining if the claim falls within a statutory category;
2A. Determining if the claim is directed to a patent ineligible judicial exception consisting of a law of nature, a natural phenomenon, or abstract idea; and
2B. If the claim is directed to a judicial exception, determining if the claim recites limitations or elements that amount to significantly more than the judicial exception.
See MPEP §2106.
Step 2A is a two prong inquiry. MPEP §2106.04(II)(A). Under 2A(i), the first prong, examiners evaluate whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim. Abstract ideas include mathematical concepts, certain methods of organizing human activity, and mental processes. MPEP §2106.04(a)(2). Under 2A(ii), the second prong, examiners determine whether any additional limitations integrates the judicial exception into a practical application. MPEP §2106.04(d).
Claim 1 step 2A(i):
The claim(s) recite:
1. A method for simulating a physical property of a subsurface formation, comprising:
…, generating a discretized model of the subsurface formation in space and time, the discretized model comprising at least one physical parameter of the subsurface formation and a relationship between the at least one physical parameter and the physical property;
…, calculating, for each spatial location and at each time in the discretized model, a time independent solution to the relationship;
…, defining a context of a selected number of grid cells surrounding each spatial location;
…, performing dimensionality reduction on each context;
inputting, …, each dimensionality reduced context as a separate earth model to train a machine learning system to determine a relationship between the dimensionality reduced context and the physical property; and
…, using the trained machine learning system to estimate the physical property at each spatial location and at each time.
Simulating the physical property as recited in the preamble corresponds with a mathematical concept(s) as recited in the body of the claim.
Generating a discretized model of the subsurface corresponds with a mathematical construction of a mathematical model. The parameters of the model are numerical values. The relationships between parameters and physical properties corresponds with a mathematical relationship.
Calculating a time dependent solution is a recitation of performing calculations.
Defining a “context” as claimed corresponds with a mathematical construction of the respective numerical parameters of the context.
Performing the dimensionality reduction is performing respective mathematical operations.
Inputting the context numerical values to train a machine learning system to determine the mathematical relationship between the context and physical properties is further recitation of mathematical subject matter. The training of the machine learning model corresponds with mathematical calculations. Specification paragraph 28 states “The neural network here mimics partial differential operators in the governing equations.”
Using the trained machine learning system to estimate the physical properties corresponds to performing the respective mathematical calculations of the machine learning system.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 1 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
in a programmable computer, …
in the computer, …
in the computer, …
in the computer, …
….
The computer is recited at a high-level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts no more than mere instructions to apply the exception using a generic computer. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. See MPEP §2106.05(b) (“Merely adding a generic computer, generic computer components, or a programmed computer to perform generic computer functions does not automatically overcome an eligibility rejection. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 223-24, 110 USPQ2d 1976, 1983-84 (2014).”).
Claim 1 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Limitations analyzed under MPEP §2106.05(b) in step 2A(ii) above are analyzed the same here in step 2B.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claims 2 and 9 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
2. The method of claim 1 wherein the time independent solution comprises solution to a Poisson equation.
A solution to a Poisson equation is mathematical subject matter.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claims 2 and 9 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claims 2 and 9 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claims 3 and 10 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
3. The method of claim 1 wherein the at least one physical property comprises formation fluid pressure.
The representation of the physical property within the discretized model is a numerical value regardless of what that numerical value represents.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claims 3 and 10 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claims 3 and 10 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claims 4 and 11 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
4. The method of claim 1 wherein the at least one physical parameter comprises formation porosity and corresponding permeability.
The representation of the physical parameter within the discretized model is a numerical value regardless of what that numerical value represents.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claims 4 and 11 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claims 4 and 11 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claims 5 and 12 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claims 5 and 12 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
5. The method of claim 1 wherein the at least one physical parameter is obtained using measurements made of subsurface formations.
Obtaining measurement values “using measurements” is a generic recitation of data gathering. Mere data gathering is insignificant extra solution activity. See MPEP §2106.05(g).
Claims 5 and 12 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
The claim(s) recite:
5. The method of claim 1 wherein the at least one physical parameter is obtained using measurements made of subsurface formations.
MPEP §2106.05(d) provides an example:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claims 6 and 13 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claims 6 and 13 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
6. The method of claim 5 wherein the measurements comprise at least one of well log measurements, surface reflection seismic surveys and measurements made on samples of the subsurface formation.
Well log measurements, surface reflection seismic surveys, and “measurements made” on samples, as a group, is a generic recitation of data gathering. Mere data gathering is insignificant extra solution activity. See MPEP §2106.05(g).
Claims 6 and 13 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
The claim(s) recite:
6. The method of claim 5 wherein the measurements comprise at least one of well log measurements, surface reflection seismic surveys and measurements made on samples of the subsurface formation.
US patent 5,668,369 Oraby [herein “Oraby”] provides the necessary Berkheimer evidence. Oraby column 1 lines 14-16 states “Well logs are commonly used in the field of oil and gas production and exploration to determine the nature and attributes of the geological formations.” Oraby column 1 line 25 states “conventional well logs.” Conventional well logs are conventional. Commonly used well logs are routine. Accordingly, at least well log measurements are well understood, routine, or conventional.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claims 7 and 14 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
7. The method of claim 1 wherein the dimensionality reduction comprises principal component analysis.
Principal component analysis (PCA) is a mathematical technique and thus mathematical subject matter.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claims 7 and 14 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claims 7 and 14 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 8 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
to perform actions, comprising:
generating a discretized model of the subsurface formation in space and time, the discretized model comprising at least one physical parameter of the subsurface formation and a relationship between the at least one physical parameter and the physical property;
calculating, for each spatial location and at each time in the discretized model, a time independent solution to the relationship;
defining a context of a selected number of grid cells surrounding each spatial location;
performing dimensionality reduction on each context;
inputting each dimensionality reduced context as a separate earth model to train a machine learning system to determine a relationship between the dimensionality reduced context and the physical property; and
using the trained machine learning system to estimate the physical property at each spatial location and at each time.
Generating a discretized model of the subsurface corresponds with a mathematical construction of a mathematical model. The parameters of the model are numerical values. The relationships between parameters and physical properties corresponds with a mathematical relationship.
Calculating a time dependent solution is a recitation of performing calculations.
Defining a “context” as claimed corresponds with a mathematical construction of the respective numerical parameters of the context.
Performing the dimensionality reduction is performing respective mathematical operations.
Inputting the context numerical values to train a machine learning system to determine the mathematical relationship between the context and physical properties is further recitation of mathematical subject matter. The training of the machine learning model corresponds with mathematical calculations. Specification paragraph 28 states “The neural network here mimics partial differential operators in the governing equations.”
Using the trained machine learning system to estimate the physical properties corresponds to performing the respective mathematical calculations of the machine learning system.
This falls within the mathematical concepts grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 8 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
8. A computer program stored in a non-transitory computer readable medium, the program having logic operable to cause a programmable computer to ….
The computer program and computer readable medium is recited at a high-level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. See MPEP §2106.05(b) (“Merely adding a generic computer, generic computer components, or a programmed computer to perform generic computer functions does not automatically overcome an eligibility rejection. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 223-24, 110 USPQ2d 1976, 1983-84 (2014).”).
Claim 8 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Limitations analyzed under MPEP §2106.05(b) in step 2A(ii) above are analyzed the same here in step 2B.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
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.
Claims 1-14
Claims 1-14 are rejected under 35 U.S.C. 103 as being unpatentable over Chaki, S. “Reservoir Characterization: A Machine Learning Approach” Thesis, Indian Institute of Tech. (2015) [herein “Chaki”] in view of US patent 11,313,994 B2 Salman, et al. [herein “Salman”] and US patent 6,993,433 B2 Chavarria, et al. (cited in IDS dated 10 May 2022) [herein “Chavarria”].
Claim 1 recites “1. A method for simulating a physical property of a subsurface formation.” Chaki page 48 last paragraph discloses “Other petrophysical properties such as porosity, permeability, shale fraction, etc. can be modelled from seismic attributes using the frameworks proposed in this chapter.” Modeling porosity and/or permeability corresponds with a simulation of a physical property.
Claim 1 further recites “comprising: in a programmable computer … in the computer” Chaki does not explicitly disclose a computer; however, in analogous art of geophysical deep learning, Salman column 20 lines 16-18 teaches “computers 554, each computer may include one or more processors (e.g., or processing cores) 556 and memory 558 for storing instructions.”
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki and Salman. One having ordinary skill in the art would have found motivation to use computer implementation into the system of machine learning reservoir characterization for the advantageous purpose of “processing and/or control of data such as, for example, one or more of log data and seismic data.” See Salman column 1 lines 27-29.
Claim 1 further recites “generating a discretized model of the subsurface formation in space and time, the discretized model comprising at least one physical parameter of the subsurface formation and a relationship between the at least one physical parameter and the physical property.” Chaki abstract discloses:
’Reservoir Characterization (RC)’ can be defined as the act of building a reservoir model that incorporates all the characteristics of the reservoir that are pertinent to its ability to store hydrocarbons and also to produce them. ….
This present work describes the development of algorithms to obtain the functional relationships between predictor seismic attributes and target lithological properties.
Building a reservoir model that incorporates characteristics of the reservoir corresponds with generating a model of the subsurface formation including physical parameters and physical properties. Here, the predictor seismic attributes correspond with physical parameters and the target lithological properties correspond with physical properties.
Chaki page 33 first paragraph discloses “Every element in the volume is considered as a pixel.” Chaki page 46 discloses “Algorithm 3-2” which includes “sand volume matrix X.”
But Chaki does not explicitly disclose a discrete model; however, in analogous art of geophysical deep learning, Salman column 6 line 67 to column 7 line 2 teaches “to generate a mesh. As an example, a mesh may be a grid. Such constructs (e.g., meshes or grids) may be defined by nodes, cells, intervals, segments, etc.” A mesh and/or grid is a discretized model.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki and Salman. One having ordinary skill in the art would have found motivation to use a discrete grid modeling seismic data into the system of machine learning reservoir characterization for the advantageous purpose of using a data format suitable for simulating behavior of a geologic environment and stored. See Salman column 5 lines 64-66 and column 7 lines 21-32.
Claim 1 further recites “…, calculating, for each spatial location and at each time in the discretized model, a time independent solution to the relationship.” Chaki page 8 section 2.1.2 second paragraph discloses “The product of density and seismic velocity through different types of rock layers represents the seismic impedance.” See also Chaki page 39 section 3.3.2 first paragraph.
Chaki page 35 second paragraph discloses “density and other derived logs.” Deriving density corresponds with a solution of a spatial location and calculated relationship. Chaki does not disclose what relationship or equation is used to derive density from seismic data.
Neither Chaki nor Salman explicitly disclose a time independent solution (i.e. Poisson equation); however, in analogous art of subsurface seismic characterization, Chavarria column 8 lines 1-5 teaches:
The forward modeling of Poisson's equation using the method of the present invention provides the flexibility to generate data in the entire medium including the source regions and thus allows inversion of surface and borehole gravity to recover density distribution in the subsurface.
Performing inversion to recover a density distribution is calculating for respective spatial locations and times, time independent solutions to the Poisson equation relationship.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki, Salman, and Chavarria. One having ordinary skill in the art would have found motivation to use Poisson equations to perform inversion and recover density into the system of machine learning reservoir characterization for the advantageous purpose of deriving density logs. See Chaki page 35 second paragraph. Further motivation to combine is found for the purpose of extracting useful information and accurately determine the density of a subsurface in three dimensions. See Chavarria column 4 lines 19-22.
Claim 1 further recites “…, defining a context of a selected number of grid cells surrounding each spatial location.” Chaki page 28 fig. 3-3 shows “integrated dataset division” after pre-processing. The dataset after respective pre-processing corresponds with defined context (data sets) for the volume including respective cells.
Claim 1 further recites “…, performing dimensionality reduction on each context.” Chaki page 48 discloses:
In case of large number of predictor attributes and smaller amount of training patterns, the dimensionality of the dataset need to be reduced in the pre-processing stage itself. Principal Component Analysis (PCA), forward sequential selection approach can be opted for dimensionality reduction. However, for this work, dimensionality reduction was not required owing to the presence of large training datasets.
Here, Chaki teaches circumstances where PCA should be used for dimensionality reduction. Note, the subsequent teaching that it was not required here is not a teaching away from using PCA for the taught purpose when the identified circumstances suggest using PCA.
Claim 1 further recites “inputting, …, each dimensionality reduced context as a separate earth model to train a machine learning system to determine a relationship between the dimensionality reduced context and the physical property.” Chaki page 28 figure 3.3 shows inputting the integrated dataset as “training set,” “testing set,” and “validation set.” The training and validation resulting in “safe trained network parameters” is inputting the respective datasets to train the machine learning system. Chaki page 30 second paragraph discloses “Finally, a network with a single hidden layer is trained using the Scaled Conjugate Gradient (SCG) Backpropagation Algorithm [98].” See further Chaki page 29 section 3.2.2 “Model Building and Validation.”
Claim 1 further recites “and …, using the trained machine learning system to estimate the physical property at each spatial location and at each time.” Chaki page 48 last paragraph discloses “Other petrophysical properties such as porosity, permeability, shale fraction, etc. can be modelled from seismic attributes using the frameworks proposed in this chapter.” Modeling petrophysical porosity and permeability corresponds with estimating a physical property of at least porosity and permeability.
Claim 2 further recites “2. The method of claim 1 wherein the time independent solution comprises solution to a Poisson equation.” Chaki page 8 section 2.1.2 second paragraph discloses “The product of density and seismic velocity through different types of rock layers represents the seismic impedance.” See also Chaki page 39 section 3.3.2 first paragraph.
Chaki page 35 second paragraph discloses “density and other derived logs.” Deriving density corresponds with a solution of a spatial location and calculated relationship. Chaki does not disclose what relationship or equation is used to derive density from seismic data.
Neither Chaki nor Salman explicitly disclose a Poisson equation; however, in analogous art of subsurface seismic characterization, Chavarria column 8 lines 1-5 teaches:
The forward modeling of Poisson's equation using the method of the present invention provides the flexibility to generate data in the entire medium including the source regions and thus allows inversion of surface and borehole gravity to recover density distribution in the subsurface.
Performing inversion to recover a density distribution is calculating for respective spatial locations and times, time independent solutions to the Poisson equation relationship.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki, Salman, and Chavarria. One having ordinary skill in the art would have found motivation to use Poisson equations to perform inversion and recover density into the system of machine learning reservoir characterization for the advantageous purpose of deriving density logs. See Chaki page 35 second paragraph. Further motivation to combine is found for the purpose of extracting useful information and accurately determine the density of a subsurface in three dimensions. See Chavarria column 4 lines 19-22.
Claim 3 further recites “3. The method of claim 1 wherein the at least one physical property comprises formation fluid pressure.” Chaki page 48 last paragraph discloses “Other petrophysical properties such as porosity, permeability, shale fraction, etc. can be modelled from seismic attributes using the frameworks proposed in this chapter.”
Chaki does not explicitly disclose modelling a formation fluid pressure; however, in analogous art of subsurface seismic characterization, Chavarria column 3 lines 33-36 teach “A number of methods have been used to measure the seismic velocities through underground formations and make an estimate of the formation fluid pressure from the measured velocities.” See also Chavarria claim 2.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki, Salman, and Chavarria. One having ordinary skill in the art would have found motivation to estimate a fluid pressure into the system of machine learning reservoir characterization for the advantageous purpose of controlling a density of drilling mud to avoid “kicks” and blowouts. See Chavarria column 2 lines 50-57.
Claim 4 further recites “4. The method of claim 1 wherein the at least one physical parameter comprises formation porosity and corresponding permeability.” Chaki page 48 last paragraph discloses “Other petrophysical properties such as porosity, permeability, shale fraction, etc. can be modelled from seismic attributes using the frameworks proposed in this chapter.” Modeling petrophysical porosity and permeability corresponds with estimating a porosity and permeability.
Claim 5 further recites “5. The method of claim 1 wherein the at least one physical parameter is obtained using measurements made of subsurface formations.” Chaki page 8 section 2.1.2 first sentence discloses “A spatial database containing seismic attributes and well logs has been acquired from the study area in SEG-Y and Log ASCII Standard (LAS) format respectively.” A database containing well logs is well log measurements.
Claim 6 further recites “6. The method of claim 5 wherein the measurements comprise at least one of well log measurements, surface reflection seismic surveys and measurements made on samples of the subsurface formation.” From the above list of alternatives the Examiner is selecting “well log measurements.”
Chaki page 8 section 2.1.2 first sentence discloses “A spatial database containing seismic attributes and well logs has been acquired from the study area in SEG-Y and Log ASCII Standard (LAS) format respectively.” A database containing well logs is well log measurements.
Claim 7 further recites “7. The method of claim 1 wherein the dimensionality reduction comprises principal component analysis.” Chaki page 48 discloses:
In case of large number of predictor attributes and smaller amount of training patterns, the dimensionality of the dataset need to be reduced in the pre-processing stage itself. Principal Component Analysis (PCA), forward sequential selection approach can be opted for dimensionality reduction. However, for this work, dimensionality reduction was not required owing to the presence of large training datasets.
Here, Chaki teaches circumstances where PCA should be used for dimensionality reduction. Note, the subsequent teaching that it was not required here is not a teaching away from using PCA for the taught purpose when the identified circumstances suggest using PCA.
Claim 8 recites “8. A computer program stored in a non-transitory computer readable medium, the program having logic operable to cause a programmable computer to perform actions.” Chaki does not explicitly disclose a computer; however, in analogous art of geophysical deep learning, Salman column 20 lines 16-18 teaches “computers 554, each computer may include one or more processors (e.g., or processing cores) 556 and memory 558 for storing instructions.”
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki and Salman. One having ordinary skill in the art would have found motivation to use computer implementation into the system of machine learning reservoir characterization for the advantageous purpose of “processing and/or control of data such as, for example, one or more of log data and seismic data.” See Salman column 1 lines 27-29.
Claim 8 further recites “comprising: generating a discretized model of the subsurface formation in space and time, the discretized model comprising at least one physical parameter of the subsurface formation and a relationship between the at least one physical parameter and the physical property.” Chaki abstract discloses:
’Reservoir Characterization (RC)’ can be defined as the act of building a reservoir model that incorporates all the characteristics of the reservoir that are pertinent to its ability to store hydrocarbons and also to produce them. ….
This present work describes the development of algorithms to obtain the functional relationships between predictor seismic attributes and target lithological properties.
Building a reservoir model that incorporates characteristics of the reservoir corresponds with generating a model of the subsurface formation including physical parameters and physical properties. Here, the predictor seismic attributes correspond with physical parameters and the target lithological properties correspond with physical properties.
Chaki page 33 first paragraph discloses “Every element in the volume is considered as a pixel.” Chaki page 46 discloses “Algorithm 3-2” which includes “sand volume matrix X.”
But Chaki does not explicitly disclose a discrete model; however, in analogous art of geophysical deep learning, Salman column 6 line 67 to column 7 line 2 teaches “to generate a mesh. As an example, a mesh may be a grid. Such constructs (e.g., meshes or grids) may be defined by nodes, cells, intervals, segments, etc.” A mesh and/or grid is a discretized model.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki and Salman. One having ordinary skill in the art would have found motivation to use a discrete grid modeling seismic data into the system of machine learning reservoir characterization for the advantageous purpose of using a data format suitable for simulating behavior of a geologic environment and stored. See Salman column 5 lines 64-66 and column 7 lines 21-32.
Claim 8 further recites “calculating, for each spatial location and at each time in the discretized model, a time independent solution to the relationship.” Chaki page 8 section 2.1.2 second paragraph discloses “The product of density and seismic velocity through different types of rock layers represents the seismic impedance.” See also Chaki page 39 section 3.3.2 first paragraph.
Chaki page 35 second paragraph discloses “density and other derived logs.” Deriving density corresponds with a solution of a spatial location and calculated relationship. Chaki does not disclose what relationship or equation is used to derive density from seismic data.
Neither Chaki nor Salman explicitly disclose a time independent solution (i.e. Poisson equation); however, in analogous art of subsurface seismic characterization, Chavarria column 8 lines 1-5 teaches:
The forward modeling of Poisson's equation using the method of the present invention provides the flexibility to generate data in the entire medium including the source regions and thus allows inversion of surface and borehole gravity to recover density distribution in the subsurface.
Performing inversion to recover a density distribution is calculating for respective spatial locations and times, time independent solutions to the Poisson equation relationship.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to combine Chaki, Salman, and Chavarria. One having ordinary skill in the art would have found motivation to use Poisson equations to perform inversion and recover density into the system of machine learning reservoir characterization for the advantageous purpose of deriving density logs. See Chaki page 35 second paragraph. Further motivation to combine is found for the purpose of extracting useful information and accurately determine the density of a subsurface in three dimensions. See Chavarria column 4 lines 19-22.
Claim 8 further recites “defining a context of a selected number of grid cells surrounding each spatial location.” Chaki page 28 fig. 3-3 shows “integrated dataset division” after pre-processing. The dataset after respective pre-processing corresponds with defined context (data sets) for the volume including respective cells.
Claim 8 further recites “performing dimensionality reduction on each context.” Chaki page 48 discloses:
In case of large number of predictor attributes and smaller amount of training patterns, the dimensionality of the dataset need to be reduced in the pre-processing stage itself. Principal Component Analysis (PCA), forward sequential selection approach can be opted for dimensionality reduction. However, for this work, dimensionality reduction was not required owing to the presence of large training datasets.
Here, Chaki teaches circumstances where PCA should be used for dimensionality reduction. Note, the subsequent teaching that it was not required here is not a teaching away from using PCA for the taught purpose when the identified circumstances suggest using PCA.
Claim 8 further recites “inputting each dimensionality reduced context as a separate earth model to train a machine learning system to determine a relationship between the dimensionality reduced context and the physical property.” Chaki page 28 figure 3.3 shows inputting the integrated dataset as “training set,” “testing set,” and “validation set.” The training and validation resulting in “safe trained network parameters” is inputting the respective datasets to train the machine learning system. Chaki page 30 second paragraph discloses “Finally, a network with a single hidden layer is trained using the Scaled Conjugate Gradient (SCG) Backpropagation Algorithm [98].” See further Chaki page 29 section 3.2.2 “Model Building and Validation.”
Claim 8 further recites “and using the trained machine learning system to estimate the physical property at each spatial location and at each time.” Chaki page 48 last paragraph discloses “Other petrophysical properties such as porosity, permeability, shale fraction, etc. can be modelled from seismic attributes using the frameworks proposed in this chapter.” Modeling petrophysical porosity and permeability corresponds with estimating a physical property of at least porosity and permeability.
Dependent claims 9-14 are substantially similar to claims 2-7 above and are rejected for the same reasons.
Conclusion
Prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 2015/0153476 A1 Prange; Michael David et al.
teaches
Constrained History Matching Coupled with Optimization;
History matching a reservoir model using PCA and “well logs, seismic images and geological constraints.” To predict porosity and permeability.
US 5,668,369 A Oraby; Moustafa E.
Lithology-independent well log analysis of formation water saturation
US 10,908,308 B1 Thorne; Julian A.
Building reservoir property models
Park, K. "Seeing Invisible Properties of Subsurface Oil and Gas Reservoir through Extensive Uses of Machine Learning Algorithms" Term Project Report: CS229 Machine Learning Fall 2007 (2007)
Geostatistical modeling.
Determining unknown reservoir properties using machine learning.
Section VI teaches SNESIM using a dissimilarity distance for training.
Laigle, J.M., et al. "Petroleum Systems Through Economic Assessment of the Permian Basin, Texas Aided By a Cognitive System for Geosciences" AAPG Conf. Exh. (Nov. 4-11 2018)
Artificial Intelligence (AI) to evaluate thermal stress, pore pressure, and petroleum generation.
Erofeev, A., et al. "Prediction of Porosity and Permeability Alteration Based on Machine Learning Algorithms" Transport in Porous Media, vol. 128, pp. 677-700 (March 2019)
Porosity and Permeability prediction using machine learning.
Comparison with laboratory measurements and different algorithms.
Tang, M., et al. "A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems" arXiv:1908.05823v1 (August 2019)
Posterior reservoir models using randomized maximum likelihood with a permeability field parameterized with CNN-PCA.
Honorio, J. "Integration of PCA with a Novel Machine Learning Method for Reparameterization and Assisted History Matching Geologically Complex Reservoirs" Society of Petroleum Engineers, SPE-175038-MS (2015)
Using a pluri-PCA approach to reduce the dimensions of grid-based static model.
Tuning coefficients with history matching.
A ML technique called “Piecewise Reconstruction from a Dictionary” (PRaD), which is based on the Markov Random Field method, is introduced to minimize the feature distance between the reconstructed model and the training models.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jay B Hann whose telephone number is (571)272-3330. The examiner can normally be reached M-F 10am-7pm EDT.
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, Kamini Shah can be reached at (571)272-2279. 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.
/Jay Hann/Primary Examiner, Art Unit 2189 11 September 2025