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 .
This action is in response to the amendment and remarks filed September 8th, 2026. In the amendment, claims 1, 8, and 15 were amended, no claims were cancelled or added. As such, claims 1-20 are pending.
Response to Arguments
Applicant’s arguments filed September 8th, 2026, with respect to the rejections are not persuasive for the following reasons:
35 U.S.C 101:
Applicant argues that claim 1 integrates the exception into a practical application by improving how reservoir properties are characterized using a generative machine learning model with improved accuracy and consistency (Pages 5-6 of Remarks). The Examiner respectfully disagrees. As analyzed under Step 2A Prong 2, the providing of data, the memory and processor, and the use of the model applies the abstract idea at a high level of generality. Improved accuracy and consistency is a result of the mathematical concept itself and is not an improvement to any technology. Paragraphs 26 and 46 describe only generic benefits of applying a model rather than a technological improvement.
Applicant argues that the claims improve computer functionality under Enfish and Ex parte Desjardins (Pages 6-8 of Remarks). The Examiner respectfully disagrees. Enfish requires a specific improvement to the way a computer operates that is defined by the claim, whereas claim 1 recites abstract ideas on a generic processor, memory, and model. The alleged benefit is a result of the abstract idea rather than an improved computer functionality. Ex parte Desjardins is distinguishable because eligibility there rested on an improvement to the functioning of the machine learning model itself, such as reduced storage, reduced complexity, and mitigation of catastrophic forgetting that was reflected in the claim and identified in the specification. Here, neither the claim nor the specification identifies any such model functioning improvement.
35 U.S.C 103:
Applicant argues that neither Roy nor Denli, alone or in combination, discloses “wherein the petrophysical interpretation comprises physical and chemical properties,” as recited in amended claims 1, 8, and 15 (Pages 9-10 of Remarks). The Examiner respectfully disagrees. As set forth in the updated rejection, Roy teaches this limitation because Roy's GTM interpretation characterizes porosity (a physical property) and the carbonate and calcareous mineral makeup of the rock (a chemical property). Therefore, the argument is not persuasive.
Applicant argues that Roy is primarily directed to seismic facies estimation of rock type, porosity, and lithology, whereas the claimed approach jointly represents physical and chemical information from multiple sources and infers new interpretations beyond direct classification (Page 10 of Remarks). The Examiner respectfully disagrees. The claims do not require multiple measurement sources, joint representation of fluid and rock chemistry, or inference beyond direct classification, so these contentions are not commensurate with the claim scope.
Applicant argues that Laloy and Kingma are silent regarding the amended limitation and that dependent claims 2-4, 6-7, 9-11, 13-14, and 16-20 are allowable for depending from allowable independent claims (Pages 11-12 of Remarks). The Examiner respectfully disagrees. The independent claims remain rejected under Roy in view of Denli. Therefore, the rejection is maintained.
Specification
The disclosure is objected to because of the following informalities:
Paragraph 16: “FIG. 11 illustrated an example of a process” should read “FIG. 11 illustrates an example of a process”.
Paragraph 31: “and/or any other signals/wavs” should read “and/or any other signals/waves”.
Paragraphs 50-56: the enumeration recites “(1)…(2)…(3)…(4)…(5)…(7)…(8)” and omits “(6)”. The list should be renumbered sequentially.
Paragraph 80: “a flow-based generative model can used to convert the input data” should read “a flow-based generative model can be used to convert the input data”.
Paragraph 86: “The GAN includes may two models, a generator and a discriminator” should read “The GAN may include two models, a generator and a discriminator”.
Paragraph 93: “each cluster in the set of clusters may be associated with a specific rock tyре,” should read “each cluster in the set of clusters may be associated with a specific rock type.” The sentence is also incomplete as it ends with a comma.
Paragraph 111: “Atatic RAM (SRAM)” should read “Static RAM (SRAM)”.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an
abstract idea without significantly more.
Claim 1
Step 1: The claim recites an apparatus comprising at least one processor; therefore, it is directed to the statutory category of machine.
Step2A Prong 1: The claim recites, inter alia:
cluster the set of latent space data to generate a set of clusters: This limitation encompasses a mathematical concept because it involves applying a clustering algorithm (e.g., k-means, hierarchical, Gaussian mixture) to group numerical vectors based on a mathematical distance/similarity measure. See Paragraph 74 of the instant specification which states, “Example clustering algorithms that may be applied to the latent space data may include… K-means clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), hierarchical clustering, gaussian mixture model (GMM) clustering…”.
generate… a set of latent space data corresponding to the set of formation measurement data: This limitation recites a mental process because it involves the evaluation/judgement/opinion to create a latent space data corresponding to measurement data, which can be performed by pen and paper and human judgement.
and determine a petrophysical interpretation based on the set of clusters, wherein the petrophysical interpretation comprises physical and chemical properties: This limitation recites a mental process because it involves the evaluation/judgement/opinion to characterize a petrophysical formation from groupings of data, which can be performed by pen and paper and human judgement.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
[a]n apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor configured to: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
provide a set of formation measurement data to a generative machine learning model: Mere data gathering recited at a high level of generality, and thus is an insignificant extra-solution activity (MPEP 2106.05(g)).
via the generative machine learning model: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
An apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor configured to: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
provide a set of formation measurement data to a generative machine learning model: The additional element of “providing” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of data forwarding steps amounts to no more than mere data gathering. This element amounts to transmitting data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
via the generative machine learning model: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
The elements in combination as an ordered whole still do not amount to significantly more than the judicial exception (i.e., the abstract ideas of mathematical concepts and mental processes for clustering the latent space data and determining a petrophysical interpretation based on the resulting clusters.). The claim merely describes a process of applying known machine learning and data analysis techniques (running a generative machine learning model on formation measurement inputs, generating a latent representation of the inputs, and clustering that representation to derive an interpretations). Additionally, the claim merely performs standard data processing steps of providing measurement data to the model and outputting a petrophysical interpretation of subsurface properties. The recitation of an apparatus comprising at least one memory and at least one processor merely indicates a technological environment in which the abstract ideas are applied, without improving the functioning of a computer or the machine learning model itself.
Therefore, the claim as a whole remains focused on the abstract idea and fails Step 2B of the eligibility analysis.
Claim 2
Step 1: A machine, as above.
Step2A Prong 1: This claim does not recite any abstract ideas but depends on claim 1 which recites an abstract idea.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
the generative machine learning model is a variational autoencoder (VAE): Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
the generative machine learning model is a variational autoencoder (VAE): Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
Even when considered in combination, this additional element represents mere instructions to apply an exception and therefore does not provide an inventive concept. The claim is ineligible.
Claim 3
Step 1: A machine, as above.
Step2A Prong 1: This claim does not recite any abstract ideas but depends on claim 1 which recites an abstract idea.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
the generative machine learning model is a flow-based generative model (FBGM): Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
the generative machine learning model is a flow-based generative model (FBGM): Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
Even when considered in combination, this additional element represents mere instructions to apply an exception and therefore does not provide an inventive concept. The claim is ineligible.
Claim 4
Step 1: A machine, as above.
Step2A Prong 1: This claim does not recite any abstract ideas but depends on claim 1 which recites an abstract idea.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
the generative machine learning model is a generative adversarial network (GAN): Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
the generative machine learning model is a generative adversarial network (GAN): Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
Even when considered in combination, this additional element represents mere instructions to apply an exception and therefore does not provide an inventive concept. The claim is ineligible.
Claim 5
Step 1: A machine, as above.
Step2A Prong 1: This claim does not recite any abstract ideas but depends on claim 1 which recites an abstract idea.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
the set of formation measurement data comprises at least one of well logs, core samples, seismic data, production rates, fluid flow, pressure data, geological information, or a combination thereof: The limitation merely describes the type of data being processed and thus amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
the set of formation measurement data comprises at least one of well logs, core samples, seismic data, production rates, fluid flow, pressure data, geological information, or a combination thereof: The limitation merely describes the type of data being processed and thus amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself which cannot provide inventive concept (MPEP 2106.05(h)).
Even when considered in combination, this additional element represents mere instructions to apply an exception and therefore does not provide an inventive concept. The claim is ineligible.
Claim 6
Step 1: A machine, as above.
Step2A Prong 1: This claim does not recite any abstract ideas but depends on claim 1 which recites an abstract idea.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
the petrophysical interpretation comprises at least one of rock types, porosity, permeability, saturation, lithology, formation pressure, fluid types, or a combination thereof: The limitation merely describes the type of data being processed and thus amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
the petrophysical interpretation comprises at least one of rock types, porosity, permeability, saturation, lithology, formation pressure, fluid types, or a combination thereof: The limitation merely describes the type of data being processed and thus amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself which cannot provide inventive concept (MPEP 2106.05(h)).
Even when considered in combination, this additional element represents mere instructions to apply
an exception and therefore does not provide an inventive concept. The claim is ineligible.
Claim 7
Step 1: A machine, as above.
Step2A Prong 1: Claim 7 is directed to a machine as depending from claim 2 which depends on claim 1, thus the analysis for patent eligibilities of claim 7 and of base claim 1 are incorporated herein.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
the VAE comprises an encoder network, a sampled latent vector, and a decoder network: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
the VAE comprises an encoder network, a sampled latent vector, and a decoder network: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
Even when considered in combination, this additional element represents mere instructions to apply an exception and therefore does not provide an inventive concept. The claim is ineligible.
Claim 8
Step 1: The claim recites a method; therefore, it is directed to the statutory category of a process.
Step2A Prong 1: The claim recites, inter alia:
clustering the set of latent space data to generate a set of clusters: This limitation encompasses a mathematical concept because it involves applying a clustering algorithm (e.g., k-means, hierarchical, Gaussian mixture) to group numerical vectors based on a mathematical distance/similarity measure. See Paragraph 74 of the instant specification which states, “Example clustering algorithms that may be applied to the latent space data may include… K-means clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), hierarchical clustering, gaussian mixture model (GMM) clustering…”.
generating… a set of latent space data corresponding to the set of formation measurement data: This limitation recites a mental process because it involves the evaluation/judgement/opinion to create a latent space data corresponding to measurement data, which can be performed by pen and paper and human judgement.
and determining a petrophysical interpretation based on the set of clusters, wherein the petrophysical interpretation comprises physical and chemical properties: This limitation recites a mental process because it involves the evaluation/judgement/opinion to characterize a petrophysical formation from groupings of data, which can be performed by pen and paper and human judgement.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
providing a set of formation measurement data to a generative machine learning model: Mere data gathering recited at a high level of generality, and thus is an insignificant extra-solution activity (MPEP 2106.05(g)).
via the generative machine learning model: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
providing a set of formation measurement data to a generative machine learning model: The additional element of “providing” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of data forwarding steps amounts to no more than mere data gathering. This element amounts to transmitting data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
via the generative machine learning model: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
Even when considered in combination, these additional elements represent mere instructions to apply
an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 9 recites similar limitations to claim 2. Therefore, claim 9 is rejected using the same rationale as claim 2.
Claim 10 recites similar limitations to claim 3. Therefore, claim 10 is rejected using the same rationale as claim 3.
Claim 11 recites similar limitations to claim 4. Therefore, claim 11 is rejected using the same rationale as claim 4.
Claim 12 recites similar limitations to claim 5. Therefore, claim 12 is rejected using the same rationale as claim 5.
Claim 13 recites similar limitations to claim 6. Therefore, claim 13 is rejected using the same rationale as claim 6.
Claim 14 recites similar limitations to claim 7. Therefore, claim 14 is rejected using the same rationale as claim 7.
Claim 15
Step 1: The claim recites a non-transitory computer medium; therefore, it is directed to the statutory
category of article of manufacture.
Step2A Prong 1: The claim recites, inter alia:
cluster the set of latent space data to generate a set of clusters: This limitation encompasses a mathematical concept because it involves applying a clustering algorithm (e.g., k-means, hierarchical, Gaussian mixture) to group numerical vectors based on a mathematical distance/similarity measure. See Paragraph 74 of the instant specification which states, “Example clustering algorithms that may be applied to the latent space data may include… K-means clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), hierarchical clustering, gaussian mixture model (GMM) clustering…”.
generate… a set of latent space data corresponding to the set of formation measurement data: This limitation recites a mental process because it involves the evaluation/judgement/opinion to create a latent space data corresponding to measurement data, which can be performed by pen and paper and human judgement.
and determine a petrophysical interpretation based on the set of clusters, wherein the petrophysical interpretation comprises physical and chemical properties: This limitation recites a mental process because it involves the evaluation/judgement/opinion to characterize a petrophysical formation from groupings of data, which can be performed by pen and paper and human judgement.
Step2A Prong 2: This judicial exception is not integrated into a practical application because the
additional elements are as follows:
A non-transitory computer-readable storage medium comprising at least one instruction for causing a computer or processor to: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
provide a set of formation measurement data to a generative machine learning model: Mere data gathering recited at a high level of generality, and thus is an insignificant extra-solution activity (MPEP 2106.05(g)).
via the generative machine learning model: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception because the additional elements are as follows:
A non-transitory computer-readable storage medium comprising at least one instruction for causing a computer or processor to: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
provide a set of formation measurement data to a generative machine learning model: The additional element of “providing” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of data forwarding steps amounts to no more than mere data gathering. This element amounts to transmitting data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
generate… a set of latent space data corresponding to the set of formation measurement data: Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)). This falls under Well-Understood, Routine, Conventional activity -see MPEP 2106.05(d)(II)(vi).
via the generative machine learning model: Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea and cannot provide inventive concept (MPEP 2106.05(f)).
Even when considered in combination, these additional elements represent mere instructions to apply
an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 16 recites similar limitations to claim 2. Therefore, claim 16 is rejected using the same rationale as claim 2.
Claim 17 recites similar limitations to claim 3. Therefore, claim 17 is rejected using the same rationale as claim 3.
Claim 18 recites similar limitations to claim 4. Therefore, claim 18 is rejected using the same rationale as claim 4.
Claim 19 recites similar limitations to claim 5. Therefore, claim 19 is rejected using the same rationale as claim 5.
Claim 20 recites similar limitations to claim 6. Therefore, claim 20 is rejected using the same rationale as claim 6.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 4-6, 8, 11-13, 15, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Roy (“Generative topographic mapping for seismic facies estimation of a carbonate wash, Veracruz Basin, southern Mexico”, 2014) in view of Denli (US 20200183047 A1).
Regarding claim 1,
Roy teaches provide a set of formation measurement data to a generative machine learning model (Page 1 Introduction of Roy, “the generative topographic mapping (GTM) algorithm as an alternative to SOM. GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data…”, Page 6 Col. 2 Under GTM workflow for multi-attribute seismic facies classification, “The inputs to our unsupervised GTM algorithm are different seismic inversion volumes (P-impedance, lambda-rho [λρ], mu-rho [μρ], and VP∕VS), which help in understanding the highly heterogeneous conglomerate reservoir of the Veracruz Basin.”
Roy teaches feeding seismic inversion volumes (the formation measurement data) into the GTM algorithm. GTM is a generative probabilistic model that learns the data distribution.)
generate, via the generative machine learning model, a set of latent space data corresponding to the set of formation measurement data (Page 1 Introduction, “GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data… After iterative parameter estimation, the model fits the data, and we relate the points in the D-dimensional data space to grid points or nodes in the lower L-dimensional latent space.”
Roy explains that GTM maps high-dimensional seismic data into a lower-dimensional latent space defined by latent variables or nodes. This mapping produces latent representations corresponding to the input data.)
cluster the set of latent space data to generate a set of clusters (Page 2 Methodology, “These mean posterior probability projections of the data vectors onto the 2D latent space form clusters.”, Page 5 Figure 7 Caption, “Seven clusters are visible on the latent space corresponding to the high-density points. These clusters are delineated by polygons with different colors”
Roy teaches that projections of the data points in the latent space naturally form clusters based on posterior probabilities. These clusters are explicitly visualized and grouped in the latent space.);
and determine a petrophysical interpretation based on the set of clusters, wherein the petrophysical interpretation comprises physical and chemical properties (Page 6 Figure 8 Caption, “Generating the seismic facies volume (geobodies) from GTM clustering within reservoir units… Seven different polygons with different colors around clusters signify rock types for reservoir units”, Page 6 GTM workflow Section, “The impedance volumes better reflect a heterogeneous reservoir based on the variation of the porosity and the rock type. They also help to determine the relationship between the desired rock property such as lithology, porosity, or clay volume.”, Page 14 Conclusion, “This capability allows us to develop and apply a supervised GTM workflow that generates a suite of seismic “similarity” volumes with the probabilistic estimates of the facies types being similar to the well-vectors used to train the GTM model.”, Page 6 GTM workflow for multiattribute seismic facies classification Col. 1, “The facies varies from breccias to conglomerates interbedded with poorly sorted calcareous sandstones… The conglomerates and sandstone are rich in carbonate grains. These carbonate conglomerates are diagenetically altered providing secondary porosity, which is much more prevalent than the primary porosity.”, Page 7 Figure 9 Caption, “…the pink-purple-color facies correspond to the high-clay- content facies.”
Roy determines a petrophysical interpretation by mapping the GTM clusters to rock types and seismic facies of the reservoir units. That interpretation characterizes a physical property (porosity) and a chemical property (carbonate/calcareous (CaCO_3) mineral makeup) of the rock. The petrophysical interpretation therefore comprises both physical and chemical properties, consistent with Paragraph 42 of the instant specification, which defines a petrophysical interpretation as “analyzing physical and chemical properties of rocks and the fluids they contain...”).
Roy does not appear to teach an apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor configured to…
Denli, in the same field of endeavor, teaches [a]n apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor configured to… (Paragraph 2 of Denli, “Specifically, exemplary implementations relate to methods and apparatus for generating geological models with machine learning.”, Paragraph 104, “The computer system 1300 may also include computer components such as non-transitory, computer-readable media. Examples of computer-readable media include a random-access memory (RAM).”, Paragraph 106, “The architecture of computer system 1300 may be varied as desired. For example, any suitable processor-based device may be used, including without limitation personal computers, laptop computers, computer workstations, and multi-processor servers.”, Paragraph 106, “The architecture of computer system 1300 may be varied as desired. For example, any suitable processor-based device may be used, including without limitation personal computers, laptop computers, computer workstations, and multi-processor servers.”
Denli taches a computer system that includes processor-based devices and computer-readable memory such as RAM.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy’s teaching of generative topographic mapping for seismic facies classification with Denli’s machine learning-based reservoir modeling system in order improve the efficiency and automation of subsurface characterization (Paragraphs 2 and 104 of Denli).
Regarding claim 4,
Roy does not appear to teach the generative machine learning model is a generative adversarial network (GAN).
Denli, in the same field of endeavor, teaches the generative machine learning model is a generative adversarial network (GAN) (Paragraph 49 of Denli, “Generative Adversarial Network (GAN) is an artificial network system including generator (or interpreter) and discriminator network used for training the generative network model.”, Paragraph 63, “…a generative adversarial network (GAN) may be used as the machine learning methodology. In one implementation of GAN, two neural networks, including a generative network (which generates candidate reservoir models) and a discriminative network (which evaluates or classifies the candidate reservoir models), contest with each other.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy’s teaching of generative topographic mapping for seismic facies classification with Denli’s teaching of a generative adversarial network (GAN) in order to enhance the generation and evaluation of candidate reservoir models through adversarial training between generator and discriminator networks (Paragraph 55 of Denli).
Regarding claim 5,
Roy teaches the set of formation measurement data comprises at least one of well logs, core samples, seismic data, production rates, fluid flow, pressure data, geological information, or a combination thereof (Page 6 GTM workflow Section, “With the above four volumes (VP∕VS, λρ, and μρ) our input data dimension becomes 4D. That is, every voxel in 3D physical space is associated with four-attribute or 4D vectors, which we call data vectors… The inputs to our unsupervised GTM algorithm are different seismic inversion volumes (P-impedance, lambda-rho [λρ], mu-rho [μρ], and VP∕VS), which help in understanding the highly heterogeneous conglomerate reservoir.”
Roy teaches at least one of the formation measurement data, and that is seismic data.).
Regarding claim 6,
Roy teaches the petrophysical interpretation comprises at least one of rock types, porosity, permeability, saturation, lithology, formation pressure, fluid types, or a combination thereof (Page 6 GTM workflow Section, “The impedance volumes better reflect a heterogeneous reservoir based on the variation of the porosity and the rock type. They also help to determine the relationship between the desired rock property such as lithology, porosity, or clay volume.”, Page 6 Figure 8 Caption, “Seven different polygons with different colors around clusters signify rock types for reservoir units…”
Roy teaches at least one of rock types, and that is porosity and lithology.).
Regarding claim 8,
Roy teaches providing a set of formation measurement data to a generative machine learning model (Page 1 Introduction of Roy, “the generative topographic mapping (GTM) algorithm as an alternative to SOM. GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data…”, Page 6 Col. 2 Under GTM workflow for multi-attribute seismic facies classification, “The inputs to our unsupervised GTM algorithm are different seismic inversion volumes (P-impedance, lambda-rho [λρ], mu-rho [μρ], and VP∕VS), which help in understanding the highly heterogeneous conglomerate reservoir of the Veracruz Basin.”, Page 2 Methodology, “GTM is a nonlinear dimensional reduction technique that provides a probabilistic representation of the data vectors in a corresponding lower dimensional latent space…”
Roy teaches feeding seismic inversion volumes (the formation measurement data) into the GTM algorithm, which corresponds to the generative machine learning model.);
generating, via the generative machine learning model, a set of latent space data corresponding to the set of formation measurement data (Page 1 Introduction, “GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data… After iterative parameter estimation, the model fits the data, and we relate the points in the D-dimensional data space to grid points or nodes in the lower L-dimensional latent space.”
Roy teaches that GTM maps the higher dimensional input data vectors onto nodes in a lower-dimensional latent space, generating latent variables that correspond to the input data);
clustering the set of latent space data to generate a set of clusters (Page 2 Methodology, “These mean posterior probability projections of the data vectors onto the 2D latent space form clusters.”, Page 5 Figure 7 Caption, “Seven clusters are visible on the latent space corresponding to the high-density points. These clusters are delineated by polygons with different colors”
Roy teaches that the projections of the data vectors onto the latent space form clusters.);
and determining a petrophysical interpretation based on the set of clusters, wherein the petrophysical interpretation comprises physical and chemical properties (Page 6 Figure 8 Caption, “Generating the seismic facies volume (geobodies) from GTM clustering within reservoir units… Seven different polygons with different colors around clusters signify rock types for reservoir units”, Page 6 GTM workflow Section, “The impedance volumes better reflect a heterogeneous reservoir based on the variation of the porosity and the rock type. They also help to determine the relationship between the desired rock property such as lithology, porosity, or clay volume.”, Page 14 Conclusion, “This capability allows us to develop and apply a supervised GTM workflow that generates a suite of seismic “similarity” volumes with the probabilistic estimates of the facies types being similar to the well-vectors used to train the GTM model.”, Page 6 GTM workflow for multiattribute seismic facies classification Col. 1, “The facies varies from breccias to conglomerates interbedded with poorly sorted calcareous sandstones… The conglomerates and sandstone are rich in carbonate grains. These carbonate conglomerates are diagenetically altered providing secondary porosity, which is much more prevalent than the primary porosity.”, Page 7 Figure 9 Caption, “…the pink-purple-color facies correspond to the high-clay- content facies.”
Roy determines a petrophysical interpretation by mapping the GTM clusters to rock types and seismic facies of the reservoir units. That interpretation characterizes a physical property (porosity) and a chemical property (carbonate/calcareous (CaCO₃) mineral makeup) of the rock. The petrophysical interpretation therefore comprises both physical and chemical properties, consistent with Paragraph 42 of the instant specification, which defines a petrophysical interpretation as “analyzing physical and chemical properties of rocks and the fluids they contain...”).
Roy appears to not teach [a] computer-implemented method comprising…
Denli, in the same field of endeavor, teaches [a] computer-implemented method comprising (Paragraph 109 of Denli, “the disclosed method are performed using a computer so that the methodology is computer implemented.”):
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy’s teaching of generative topographic mapping for seismic facies classification with Denli’s machine learning-based reservoir modeling system in order improve the efficiency and automation of subsurface characterization (Paragraphs 2 and 104 of Denli).
Claim 11 recites similar limitations to claim 4. Therefore, claim 11 is rejected using the same rationale as claim 4.
Claim 12 recites similar limitations to claim 5. Therefore, claim 12 is rejected using the same rationale as claim 5.
Claim 13 recites similar limitations to claim 6. Therefore, claim 13 is rejected using the same rationale as claim 6.
Regarding claim 15,
Roy teaches provide a set of formation measurement data to a generative machine learning model (Page 1 Introduction of Roy, “the generative topographic mapping (GTM) algorithm as an alternative to SOM. GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data…”, Page 6 Col. 2 Under GTM workflow for multi-attribute seismic facies classification, “The inputs to our unsupervised GTM algorithm are different seismic inversion volumes (P-impedance, lambda-rho [λρ], mu-rho [μρ], and VP∕VS), which help in understanding the highly heterogeneous conglomerate reservoir of the Veracruz Basin.”
Roy teaches feeding seismic inversion volumes (the formation measurement data) into the GTM algorithm, which corresponds to the generative machine learning model.);
generate, via the generative machine learning model, a set of latent space data corresponding to the set of formation measurement data (Page 1 Introduction, “GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data… After iterative parameter estimation, the model fits the data, and we relate the points in the D-dimensional data space to grid points or nodes in the lower L-dimensional latent space.”
Roy teaches that GTM maps the higher dimensional input data vectors onto nodes in a lower-dimensional latent space, generating latent variables that correspond to the input data);
cluster the set of latent space data to generate a set of clusters (Page 2 Methodology, “These mean posterior probability projections of the data vectors onto the 2D latent space form clusters.”, Page 5 Figure 7 Caption, “Seven clusters are visible on the latent space corresponding to the high-density points. These clusters are delineated by polygons with different colors”
Roy teaches that the projections of the data vectors onto the latent space form clusters.);
and determine a petrophysical interpretation based on the set of clusters, wherein the petrophysical interpretation comprises physical and chemical properties (Page 6 Figure 8 Caption, “Generating the seismic facies volume (geobodies) from GTM clustering within reservoir units… Seven different polygons with different colors around clusters signify rock types for reservoir units”, Page 6 GTM workflow Section, “The impedance volumes better reflect a heterogeneous reservoir based on the variation of the porosity and the rock type. They also help to determine the relationship between the desired rock property such as lithology, porosity, or clay volume.”, Page 14 Conclusion, “This capability allows us to develop and apply a supervised GTM workflow that generates a suite of seismic “similarity” volumes with the probabilistic estimates of the facies types being similar to the well-vectors used to train the GTM model.”, Page 6 GTM workflow for multiattribute seismic facies classification Col. 1, “The facies varies from breccias to conglomerates interbedded with poorly sorted calcareous sandstones… The conglomerates and sandstone are rich in carbonate grains. These carbonate conglomerates are diagenetically altered providing secondary porosity, which is much more prevalent than the primary porosity.”, Page 7 Figure 9 Caption, “…the pink-purple-color facies correspond to the high-clay- content facies.”
Roy determines a petrophysical interpretation by mapping the GTM clusters to rock types and seismic facies of the reservoir units. That interpretation characterizes a physical property (porosity) and a chemical property (carbonate/calcareous (CaCO₃) mineral makeup) of the rock. The petrophysical interpretation therefore comprises both physical and chemical properties, consistent with Paragraph 42 of the instant specification, which defines a petrophysical interpretation as “analyzing physical and chemical properties of rocks and the fluids they contain...”).
Roy does not appear to teach [a] non-transitory computer-readable storage medium comprising at least one instruction for causing a computer or processor to…
Denli, in the same field of endeavor, teaches [a] non-transitory computer-readable storage medium comprising at least one instruction for causing a computer or processor to (Paragraph 2 of Denli, “Specifically, exemplary implementations relate to methods and apparatus for generating geological models with machine learning.”, Paragraph 104, “The computer system 1300 may also include computer components such as non-transitory, computer-readable media. Examples of computer-readable media include a random-access memory (RAM).”, Paragraph 106, “The architecture of computer system 1300 may be varied as desired. For example, any suitable processor-based device may be used, including without limitation personal computers, laptop computers, computer workstations, and multi-processor servers.”
Denli teaches an apparatus in the form of a computer system (e.g., computer system 1300) comprising a processor-based device and computer-readable memory such as RAM.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy’s teaching of generative topographic mapping for seismic facies classification with Denli’s machine learning-based reservoir modeling system in order improve the efficiency and automation of subsurface characterization (Paragraphs 2 and 104 of Denli).
Claim 18 recites similar limitations to claim 4. Therefore, claim 18 is rejected using the same rationale as claim 4.
Claim 19 recites similar limitations to claim 5. Therefore, claim 19 is rejected using the same rationale as claim 5.
Claim 20 recites similar limitations to claim 6. Therefore, claim 20 is rejected using the same rationale as claim 6.
Claims 2, 7, 9, 14, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Roy (“Generative topographic mapping for seismic facies estimation of a carbonate wash, Veracruz Basin, southern Mexico”, 2014) in view of Denli (US 20200183047 A1) in further view of Laloy (“Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network”, 2017).
Regarding claim 2,
Roy teaches the generative machine learning model (Page 1 Introduction of Roy, “the generative topographic mapping (GTM) algorithm as an alternative to SOM. GTM finds a model based on a probability density function (PDF) that describes the distribution of the D-dimensional data in terms of smaller number of latent variables, or cluster nodes that approximate the vast majority of the probability mass of the data…”)
Roy in view of Denli appears to not teach the… machine learning model is a variational autoencoder (VAE).
However, in the same field of endeavor, analogous art Laloy discloses the… machine learning model is a variational autoencoder (VAE) (Page 2 Introduction, “In this work, we use for the first time a deep neural network (DNN, see, e.g., Goodfellow et al., 2016, for an overview) to build a parametric low-dimensional representation of complex geologic models. More specifically, we train the generator of a deep variational autoencoder (VAE, Kingma and Welling, 2014) such that it generates TI-consistent geologic model realizations when fed with a low-dimensional standard Gaussian noise vector. A key characteristic of our VAE is that it is largely made up of convolutional layers…”
Laloy teaches using a variational autoencoder (VAE) to parameterize geological data.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy in view of Denli’s teachings with Laloy’s teaching of a VAE comprising an encoder network, a sampled latent vector, and a decoder network in order to enable parametrized low-dimensional encoding and decoding of complex geologic data (Page 3 Section 2 of Laloy).
Regarding claim 7,
Roy in view of Denli does not teach the VAE comprises an encoder network, a sampled latent vector, and a decoder network.
Laloy, in the same field of endeavor, teaches the VAE comprises an encoder network, a sampled latent vector, and a decoder network (Page 4 Figure 2 Caption, “Fig. 2. Illustration of a variational deep autoencoder (VAE).”, Page 3 Section 2.1.2, “The part of the network that connects the input to the code is called the “encoder”, while the one that connects the code to the output is referred to as the “decoder” … The first element of the decoder is a randomly sampled vector of “latent” standard normal variables, z, l of the same size, d, as μ and σ.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy in view of Denli’s teachings with Laloy’s teaching of a VAE comprising an encoder network, a sampled latent vector, and a decoder network in order to enable parametrized low-dimensional encoding and decoding of complex geologic data (Page 3 Section 2 of Laloy).
Claim 9 recites similar limitations to claim 2. Therefore, claim 9 is rejected using the same rationale as claim 2.
Claim 14 recites similar limitations to claim 7. Therefore, claim 14 is rejected using the same rationale as claim 7.
Claim 16 recites similar limitations to claim 2. Therefore, claim 16 is rejected using the same rationale as claim 2.
Claims 3, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Roy (“Generative topographic mapping for seismic facies estimation of a carbonate wash, Veracruz Basin, southern Mexico”, 2014) in view of Denli (US 20200183047 A1) in further view of Kingma (“Glow: Generative Flow with Invertible 1×1 Convolutions”, 2018).
Regarding claim 3,
Roy in view of Denli does not appear to teach the generative machine learning model is a flow-based generative model (FBGM).
Kingma, teaches the generative machine learning model is a flow-based generative model (FBGM) (Page 2 Introduction, “Flow-based generative models, first described in NICE (Dinh et al., 2014) and extended in RealNVP (Dinh et al., 2016) … In this paper we propose a new a generative flow coined Glow, with various new elements as described in Section 3.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine Roy in view of Denli’s teachings with Kingma’s teaching of a flow-based generative model (FBGM) in order to provide an alternative generative modeling framework enabling invertible transformations between latent space representations and formation measurement data to learn meaningful features of the input data (Introduction of Kingma).
Claim 10 recites similar limitations to claim 3. Therefore, claim 10 is rejected using the same rationale as claim 3.
Claim 17 recites similar limitations to claim 3. Therefore, claim 17 is rejected using the same rationale as claim 3.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MAJD MAHER HADDAD whose telephone number is (571)272-2265. The examiner can normally be reached Mon-Friday 8-5 pm.
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, Kamran Afshar, can be reached at (571) 272-7796. 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.
/M.M.H./Examiner, Art Unit 2125
/KAMRAN AFSHAR/Supervisory Patent Examiner, Art Unit 2125
Prosecution Insights