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 . 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 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.
DETAILED ACTION
The following NON-FINAL Office Action is in response to application 18/428,404 filed on 01/31/2024. This communication is the first action on the merits.
Status of Claims
Claims 1-20 are currently pending and have been rejected as follows.
IDS
The information disclosure statements filed on 09/04/2024, 11/06/2025, 11/25/2025, and 06/22/2026 comply with the provisions of 37 CFR 1.97, 1.98 and MPEP § 609 and are considered.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description: 512 of Paragraphs 0042, 0044, 0046, 0047, and 0048. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The following is a quotation of 37 CFR 1.71(a):
The specification must include a written description of the invention or discovery and of the manner and process of making and using the same, and is required to be in such full, clear, concise, and exact terms as to enable any person skilled in the art or science to which the invention or discovery appertains, or with which it is most nearly connected, to make and use the same.
The specification is objected to because the phrase “in examples” is used repeatedly throughout the specification without clearly identifying which examples are being referenced. See paragraphs [0009], [0012]- [0014], [0016]- [0017], [0019], [0021]- [0024], [0029], [0031]- [0033], and [0036]- [0038]. The terminology renders the disclosure unclear and informal because no specific “examples” are defined or enumerated in the specification.
Appropriate corrective action would be to amend the specification to clarify the intended meaning, for example by replacing “in examples” with terminology such as “in some embodiments,” “for example,” or by specifically identifying the referenced examples.
The disclosure is objected to because of the following informalities:
In paragraph [0010], line 7, “accurate more efficient” should read “accurate and more efficient”
In paragraph [0015], line 5, “spectrally decomposition” should read “spectral decomposition”
In paragraph [0017], line 8, “The” should be deleted
In paragraph [0020], line 2, “The envelope attribute similar to” should read “Similar to”
In paragraph [0023], line 6, “a respective cells” should read “a respective cell”
In paragraph [0029], line 4, “well-resolution” should read “high-resolution”
In paragraph [0038], line 3, “high-resolution 3D bulk density” should read “a high-resolution 3D bulk density”
Appropriate correction is required.
Claim Objections
Claim 1 is objected to because of the following informalities:
Line 13, “and bulk density volume” should read “and a bulk density volume”
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 5 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. Claim 5 recites the limitation “based on a predetermined series of rules”. Paragraph [0013] merely states that the rules involve the current value, the manipulation being applied, and other cell locations, but it does not disclose what the rules are, how they are selected, and what manipulation it is referring to. Thus, the claim(s) contains subject matter which was not described in the specification in sufficient detail that would reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. See MPEP 2161.01-I.
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.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
With respect to Claims (1-5, 8-11, 15, and 17-18), the term "high” resolution are relative terms which renders the claims indefinite. The term “high” resolution is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. Therefore, it is unclear what resolution would be considered as falling within ranges of the claimed resolution.
Claims 6-7,12-14, 16, and 19-20 are rejected as for being dependent on the above rejected parent claims.
Additionally, Claim 15 recites the limitation "the one or more memory models" in line 5. There is insufficient antecedent basis for this limitation in the claim. The Examiner suggests that “the one or more memory models” be amended to read “the one or more memory modules”.
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 a judicial exception and do not include additional elements that amount to significantly more than the judicial exception. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Specifically, representative Claim 1 recites:
A computer-implemented method that enables vugular property modeling using geologically high-resolution machine learning, comprising:
obtaining, using at least one hardware processor, multi-disciplinary data associated with a reservoir;
determining, using the at least one hardware processor, seismic attributes from the multi-disciplinary data;
transforming, using the at least one hardware processor, the seismic attributes into three dimensional (3D) geocellular properties associated with the reservoir;
estimating, using the at least one hardware processor, a high-resolution 3D acoustic impedance volume and bulk density volume using a first trained machine learning model, wherein the first trained machine learning model obtains the 3D geocellular properties as input and outputs high-resolution 3D acoustic impedance and bulk density volumes; and
predicting, using the at least one hardware processor, 3D vugular geobodies using the estimated high-resolution 3D acoustic impedance and bulk density volumes using a second trained machine learning model, wherein the second trained machine learning model obtains the high-resolution 3D acoustic impedance and bulk density volumes and outputs predicted 3D vugular geobodies.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements.”
Similar limitations comprise the abstract idea of claims 8 and 15.
Under Step 1 of the analysis, claim 1, a method, belongs to a statutory category. Likewise, claim 8, an apparatus , and claim 15, a system, both belong to statutory categories.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
In the instant case, claims 1, 8, and 15 are found to recite at least one judicial exception (i.e. abstract idea), that being a Mental Process and/or a Mathematical Concept. This can be seen in the claim limitations of “determining” seismic attributes from the multi-disciplinary data, “transforming” the seismic attributes into three dimensional (3D) geocellular properties associated with the reservoir, “estimating” a high-resolution 3D acoustic impedance volume and bulk density volume using a first trained machine learning model, and “predicting” 3D vugular geobodies using the estimated high-resolution 3D acoustic impedance and bulk density volumes using a second trained machine learning model. They fall well within the category of mental processes because these limitations are merely data observations, evaluations, and/or judgements capable of being performed mentally and/or with the aid of pen and paper. Additionally, the limitation of “determining” seismic attributes recites math when read in in light of [0015]-[0022] which describes that multiple different mathematical calculations are used to determine the seismic attributes.
Similar limitations comprise the abstract ideas of claims 8 and 15 which recite the same mathematical calculations, relationships and data evaluations and judgements using generic high level computer elements, e.g. non-transitory, computer readable, storage medium, and memory modules and hardware processors.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
In addition to the abstract ideas recited in claim 1, the claimed method recites the additional elements of “obtaining multi-disciplinary data associated with a reservoir”. However, “obtaining multi-disciplinary data associated with a reservoir” is recited at a high level of generality without describing what the multi-disciplinary data associated with a reservoir is and how it is “obtained”. It is merely data gathering and output steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies). See MPEP 2106.05(g).
The generic data gathering, processing, and output steps, are recited at such a high level of generality (e.g. using at least one hardware processor) that it represents no more than mere instructions to apply the judicial exceptions on a computer. It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer. Noting MPEP 2106.04(d)(I): “It is notable that mere physicality or tangibility of an additional element or elements is not a relevant consideration in Step 2A Prong Two. As the Supreme Court explained in Alice Corp., mere physical or tangible implementation of an exception does not guarantee eligibility. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 224, 110 USPQ2d 1976, 1983-84 (2014) ("The fact that a computer ‘necessarily exist[s] in the physical, rather than purely conceptual, realm,’ is beside the point")”.
In addition to the abstract ideas recited in claim 1, the claimed method further recites the additional element(s) of using generic AI/ML technology, i.e. “machine learning model”, to perform estimations or predictions. The claims do not recite any details regarding how the AI/ML algorithm or model functions or is trained. Instead, the claims are found to utilize the AI/ML algorithm as a tool that provides nothing more than mere instructions to implement the abstract idea on a general purpose computer. See MPEP 2106.05(f). Additionally, the use of the “machine learning model” merely indicates a field of use or technological environment in which the judicial exception is performed. See MPEP 2106.05(h). Therefore, the use of the “machine learning model” to perform steps that are otherwise abstract does not integrate the abstract idea into a practical application. See the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence; and Example 47, ineligible claim 2.
In addition to the abstract ideas recited, claim 8 recites the additional elements of " An apparatus comprising a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising: " however these element(s) are found to be generic computer components recited a high-level of generality such that they amount to no more than mere instructions to apply the judicial exception on a general purpose computer. See MPEP 2106.05(f). It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer.
In addition to the abstract ideas recited, claim 15 recites the additional elements of "A system, comprising: one or more memory modules; one or more hardware processors communicably coupled to the one or more memory modules, the one or more hardware processors configured to execute instructions stored on the one or more memory models to perform operations comprising:" however these element(s) are found to be generic computer components recited a high-level of generality such that they amount to no more than mere instructions to apply the judicial exception on a general purpose computer. See MPEP 2106.05(f). It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer.
Thus, under Step 2A, prong 2 of the analysis, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception. No specific practical application is associated with the claimed method, apparatus, and system. For instance, nothing is done with the result of predicting 3D vugular geobodies.
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer that attempts to apply the abstract idea in a technological environment and/or the additional elements merely serve as a general link to a particular field of use. Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II).
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claims 1, 8, and 15 amount to significantly more than the abstract idea.
With regards to the dependent claims, claims 2-7, 9-14 and 16-20, merely further expand upon the algorithm/abstract idea and do not set forth further additional elements that integrate the recited abstract idea into a practical application or amount to significantly more. Therefore, these claims are found ineligible for the reasons described for parent claims 1, 8 and 15.
Examiner Note - Claim Interpretation
For the purposes of clarity of the record, the Examiner notes the following broadest reasonable interpretations of certain claim terms:
In the present application, the terms “vugular property modeling” (preamble), “3D vugular geobodies” (Claim 1(e)), and “3D distribution of a vugular pore system” ([0009]) are used in related contexts. Based on their usage, the examiner interprets these expressions as referring to the same underlying concept and considers them interchangeable.
In this context, “geologically high resolution” is construed as an attribute of the geological data provided to the ML model for output generation, rather than a limitation on the machine learning model employed, i.e., any machine learning model can be used.
The term “3D geocellular properties”, in light of the specification, is interpreted as basically the original or altered seismic attributes evaluated at every cell of a 3D grid.
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.
Claims 1-3, 6-10, 13-17, 20 are rejected under 35 U.S.C 103 as being unpatentable over ZEIZA (Zeiza, Adam Danur, et al. "Reservoir characterization and 3D architecture of multi-scale vugular pore systems in carbonate reservoirs." SPE Reservoir Characterisation and Simulation Conference and Exhibition. SPE, 2023. (IDS filed on 09/04/2024, Cite No. 20)) in view of Di (US2023/0026857 A1).
Regarding claim 1, ZEIZA teaches on the following limitations of the claim:
a computer-implemented method that enables vugular property modeling (Abstract, lines 1-2: “This paper outlines a novel approach to an integrated 1D to 3D characterization and geomodelling of Vugular pore systems (VPS) in carbonate reservoirs”, and Figure 5), comprising:
obtaining multi-disciplinary data associated with a reservoir (Abstract lines 4-6: “…by utilizing multi-disciplinary datasets…”, and Figure 5, top);
determining seismic attributes from the multi-disciplinary data (Figure 5, middle: “Seismic attribute (acoustic impedance) extraction”);
transforming the seismic attributes into three dimensional (3D) geocellular properties associated with the reservoir (Figure 5, bottom: “… using data analytics, experimental variograms, seismic-based geobodies/probability trends”).
ZEIZA fails to teach the following limitations of claim 1. Di, however, does teach the following:
estimating, using the at least one hardware processor, a high-resolution 3D acoustic impedance volume and bulk density volume using a first trained machine learning model, wherein the first trained machine learning model obtains the 3D geocellular properties as input and outputs high-resolution 3D acoustic impedance and bulk density volumes ([0004]: “… a method that includes extracting, using a first machine learning model, one or more seismic features from seismic data.”; [0054]: “Estimating subsurface rock properties from seismic data is a task in subsurface mapping and interpretation. For example, subsurface property ( e.g., acoustic impedance)…”; [0055]: “ … to integrate with well logs, which represent directly measurements of at least some of the subsurface rock properties, e.g., including density and velocity. Such an integration may first construct a mapping function between seismic signals and the rock properties measured at the wells, and then consistently applying the mapping function throughout the seismic survey. Machine learning, such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, may be implemented for building the non-linear seismic-to-well mapping.”);
and predicting, using the at least one hardware processor, 3D vugular geobodies using the estimated high-resolution 3D acoustic impedance and bulk density volumes using a second trained machine learning model, wherein the second trained machine learning model obtains the high-resolution 3D acoustic impedance and bulk density volumes and outputs predicted 3D vugular geobodies ([0004]: “… and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain … on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data.”; [0016]: “… employ machine learning for estimating subsurface properties (e.g., acoustic impedance, porosity, density, etc.) over a given seismic survey. For example, the method may estimate or "predict" the subsurface properties by learning from a small number of sparsely distributed wells using one or more machine learning models (e.g., deep neural networks).”; [0056]: “ … may estimate subsurface rock properties using two machine learning models (e.g., two deep neural networks). …, the second model may integrate three-dimensional (3D) seismic data and one-dimensional (ID) well logs by using the regional features already learned in the first machine learning model, which reduces the risk of overfitting and improves the lateral consistency in the subsurface property estimation. Accordingly, embodiments of the disclosure may employ a machine learning workflow for integrating seismic data (e.g., seismic cubes) and well logs to predict subsurface properties, such as those that would normally be captured in a well log, at a location that does not have an existing well.”).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Zeiza’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include estimating 3D acoustic impedance and bulk density volumes using a first trained model and using these estimated values as input to a second trained model for predicting the 3D vugular bodies in view of Di with the motivation to reduce the risk of overfitting and improve the lateral consistency in the subsurface property estimation (see Di [0056]) (see MPEP 2143 G).
Regarding Claim 2, ZEIZA in view of Di teaches the elements of the parent claim(s).
ZEIZA further teaches the following limitations of the claim:
The computer implemented method of claim 1, wherein the multi-disciplinary data comprises well-logs (Abstract: borehole images),
1D discrete vugular flags, basic seismic attributes (Page 6, top paragraph: link the 1D VPS flags with Seismic Data),
and high-resolution 3D property volumes (Page 5, top: … the 1D VPS flags are then tied to seismic attributes, i.e. seismic acoustic impedance, … The 3D seismic acoustic impedance cube is extracted into VPS probability (i.e. lower impedance) geobodies, …). [Examiner notes that specification [0009] states the 3D property volumes include "e.g. acoustic impedance"]
Regarding Claim 3, ZEIZA in view of Di teaches the limitations of the parent claim(s).
Di further teaches the limitation of:
The computer implemented method of claim 1, wherein the first trained machine learning model is trained using resampled seismic attributes, high resolution acoustic impedance logs, and high resolution bulk density well logs (See [0058]-[0061]: A first machine learning model may then be trained to extract seismic features in the seismic data. … The first machine learning model may be trained using supervised, unsupervised, pr quasi-unsupervised learning. … One or more well logs, and either the same or potentially additional seismic data, may then be received as input, as at 406. … For example, the well logs may represent one or more subsurface properties, such as acoustic impedance, porosity, density, etc.).
Before the effective filing date of the claimed invention, it would have been obvious to a PHOSITA to modify the teachings of Zeiza to include training the machine learning model using resampled seismic attributes, acoustic impedance, and bulk density well logs in view of Di with the motivation to apply Di’s machine learning approaches for improved efficiency and accuracy. Specifically, one would use Di’s first trained ML model to extract seismic features and generate seismic attributes such as high-resolution 3D acoustic impedance and bulk density volumes from the seismic data and then apply Di’s second ML model to predict 3D vugular geobodies (See ZEIZA Figure 5 and Di FIG. 4).
Regarding claim 6, ZEIZA in view of Di teaches the limitations of the parent claim(s).
ZEIZA further teaches the limitation of:
The computer implemented method of claim 1, wherein the seismic attributes comprise at least one of acoustic impedance, quadrature amplitude, Root Mean Square (RMS) amplitude, variance, frequency, envelope and spectrally decomposed attributes (FIG. 5, middle: Seismic attribute (acoustic impedance) extraction,…).
Regarding claim 7, ZEIZA in view of Di teaches the limitations of the parent claim(s).
Di further teaches the limitation of:
The computer implemented method of claim 1, wherein the seismic attributes are transformed into the 3D geocellular properties associated with the reservoir using at least one trained machine learning model (Abstract: “ A method for seismic processing includes extracting, …, one or more seismic features from seismic data representing a subsurface domain, …, and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain …”)
Since both ZEIZA and Di are both analogous art as they relate to subsurface property estimation; therefore, before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Zeiza’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include transforming the seismic attributes into the 3D geocellular properties associated with the reservoir using at least one trained machine learning model in view of Di with the motivation to reduce the risk of overfitting and improve the lateral consistency in the subsurface property estimation (Di [0056]) (see MPEP 2143 G).
Regarding claim 8, ZEIZA teaches on the following limitations of the claim:
obtaining multi-disciplinary data associated with a reservoir (Abstract lines 4-6: “…by utilizing multi-disciplinary datasets…”, and Figure 5, top);
determining seismic attributes from the multi-disciplinary data (Figure 5, middle: “Seismic attribute (acoustic impedance) extraction”);
transforming the seismic attributes into three dimensional (3D) geocellular
properties associated with the reservoir (Figure 5, bottom: “… using … seismic-based geobodies/probability trends”);
ZEIZA fails to teach the following limitations of claim 8. Di, however, does teach the following:
An apparatus comprising a non-transitory, computer readable, storage
medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising (Claim 9: A non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a processing system, cause the processing system to perform operations, the operations comprising:)
estimating a high-resolution 3D acoustic impedance volume and bulk density
volume using a first trained machine learning model, wherein the first trained machine learning model obtains the 3D geocellular properties as input and outputs high-resolution 3D acoustic impedance and bulk density volumes ([0004]: “… a method that includes extracting, using a first machine learning model, one or more seismic features from seismic data.”; [0054]: “Estimating subsurface rock properties from seismic data is a task in subsurface mapping and interpretation. For example, subsurface property ( e.g., acoustic impedance)…”; [0055]: “ … to integrate with well logs, which represent directly measurements of at least some of the subsurface rock properties, e.g., including density and velocity. Such an integration may first construct a mapping function between seismic signals and the rock properties measured at the wells, and then consistently applying the mapping function throughout the seismic survey. Machine learning, such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, may be implemented for building the non-linear seismic-to-well mapping.”);
and predicting 3D vugular geobodies using the estimated high-resolution 3D
acoustic impedance and bulk density volumes using a second trained machine learning model, wherein the second trained machine learning model obtains the high-resolution 3D acoustic impedance and bulk density volumes and outputs predicted 3D vugular geobodies ([0004]: “… and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain … on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data.”; [0016]: “… employ machine learning for estimating subsurface properties (e.g., acoustic impedance, porosity, density, etc.) over a given seismic survey. For example, the method may estimate or "predict" the subsurface properties by learning from a small number of sparsely distributed wells using one or more machine learning models (e.g., deep neural networks).”; [0056]: “ … may estimate subsurface rock properties using two machine learning models (e.g., two deep neural networks). …, the second model may integrate three-dimensional (3D) seismic data and one-dimensional (ID) well logs by using the regional features already learned in the first machine learning model, which reduces the risk of overfitting and improves the lateral consistency in the subsurface property estimation. Accordingly, embodiments of the disclosure may employ a machine learning workflow for integrating seismic data (e.g., seismic cubes) and well logs to predict subsurface properties, such as those that would normally be captured in a well log, at a location that does not have an existing well.”).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Zeiza’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include estimating a high-resolution 3D acoustic impedance and bulk density volumes using a first trained model and using these estimated values as input to a second trained model for predicting the 3D vugular bodies in view of Di with the motivation to reduces the risk of overfitting and improves the lateral consistency in the subsurface property estimation (see Di [0056]) (see MPEP 2143 G).
Additionally, before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have recognized that applying the known technique of utilizing an apparatus comprising a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor to perform the machine learning based high-resolution 3D acoustic impedance volume and bulk density volume estimation and 3D vugular geobodies prediction of Zeiza in view of Di would have yielded predictable results and resulted in an improved system that would allow the automation of techniques described above.
Regarding claim 9, ZEIZA in view of Di teaches the limitations of the parent claim(s).
ZEIZA further teaches the following limitations of the claim:
• The apparatus of claim 8, wherein the multi-disciplinary data comprises well-logs (Abstract: borehole images),
• 1D discrete vugular flags, basic seismic attributes (Page 6, top paragraph: link the 1D VPS flags with Seismic Data),
• and high-resolution 3D property volumes (Page 5, top: … the 1D VPS flags are then tied to seismic attributes, i.e. seismic acoustic impedance, … The 3D seismic acoustic impedance cube is extracted into VPS probability (i.e. lower impedance) geobodies, …). [Examiner notes that specification [0009] states the 3D property volumes include "e.g. acoustic impedance"]
Regarding Claim 10, ZEIZA in view of Di teaches the limitations of the parent claim(s).
Di further teaches the limitation of:
The apparatus of claim 8, wherein the first trained machine learning model is trained using resampled seismic attributes, high resolution acoustic impedance logs, and high resolution bulk density well logs (See [0058]-[0061]: A first machine learning model may then be trained to extract seismic features in the seismic data. … The first machine learning model may be trained using supervised, unsupervised, pr quasi-unsupervised learning. … One or more well logs, and either the same or potentially additional seismic data, may then be received as input, as at 406. … For example, the well logs may represent one or more subsurface properties, such as acoustic impedance, porosity, density, etc.).
Before the effective filing date of the claimed invention, it would have been obvious to a PHOSITA to modify the teachings of Zeiza to include training the machine learning model using resampled seismic attributes, acoustic impedance, and bulk density well logs in view of Di with the motivation to apply Di’s machine learning approaches for improved efficiency and accuracy. Specifically, one would use Di’s first trained ML model to extract seismic features and generate seismic attributes such as high-resolution 3D acoustic impedance and bulk density volumes from the seismic data and then apply Di’s second ML model to predict 3D vugular geobodies (See ZEIZA Figure 5 and Di FIG. 4).
Regarding claim 13, ZEIZA in view of Di teaches the limitations of the parent claim(s).
ZEIZA further teaches the limitation of:
The apparatus of claim 8, wherein the seismic attributes comprise at least one of acoustic impedance, quadrature amplitude, Root Mean Square (RMS) amplitude, variance, frequency, envelope and spectrally decomposed attributes (FIG. 5, middle: Seismic attribute (acoustic impedance) extraction,…).
Regarding claim 14, ZEIZA in view of Di teaches the limitations of the parent claim(s).
Di further teaches the limitation of:
The apparatus of claim 8, wherein the seismic attributes are transformed into the 3D geocellular properties associated with the reservoir using at least one trained machine learning model (Abstract: “ A method for seismic processing includes extracting, …, one or more seismic features from seismic data representing a subsurface domain, …, and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain …”)
Since both ZEIZA and Di are both analogous art as they relate to subsurface property estimation; therefore, before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Zeiza’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include transforming the seismic attributes into the 3D geocellular properties associated with the reservoir using at least one trained machine learning model in view of Di with the motivation to reduce the risk of overfitting and improve the lateral consistency in the subsurface property estimation (Di [0056]) (see MPEP 2143 G).
Regarding claim 15, ZEIZA teaches on the following limitations of the claim:
obtaining multi-disciplinary data associated with a reservoir (Abstract lines 4-6: …by utilizing multi-disciplinary datasets…, and/or Figure 5, top);
determining seismic attributes from the multi-disciplinary data (Figure 5, middle: Seismic attribute (acoustic impedance) extraction);
transforming the seismic attributes into three dimensional (3D) geocellular
properties associated with the reservoir (Figure 5, bottom: … using … seismic-based geobodies/probability trends);
ZEIZA fails to teach the following limitations of claim 15. Di, however, does teach the following:
A system, comprising: one or more memory modules; one or more hardware processors configured to execute instructions stored on the more or more memory models to perform operations comprising: (Claim 17: A computing system, comprising: one or more processors; and a memory system including one or more non-transitory computer-readable media storing instructions that,
when executed by at least one of the one or more processors, causes the computing system to perform operations)
estimating a high-resolution 3D acoustic impedance volume and bulk density
volume using a first trained machine learning model, wherein the first trained machine learning model obtains the 3D geocellular properties as input and outputs high-resolution 3D acoustic impedance and bulk density volumes ([0004]: “… a method that includes extracting, using a first machine learning model, one or more seismic features from seismic data.”; [0054]: “Estimating subsurface rock properties from seismic data is a task in subsurface mapping and interpretation. For example, subsurface property ( e.g., acoustic impedance)…”; [0055]: “ … to integrate with well logs, which represent directly measurements of at least some of the subsurface rock properties, e.g., including density and velocity. Such an integration may first construct a mapping function between seismic signals and the rock properties measured at the wells, and then consistently applying the mapping function throughout the seismic survey. Machine learning, such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, may be implemented for building the non-linear seismic-to-well mapping.”);
and predicting 3D vugular geobodies using the estimated high-resolution 3D
acoustic impedance and bulk density volumes using a second trained machine learning model, wherein the second trained machine learning model obtains the high-resolution 3D acoustic impedance and bulk density volumes and outputs predicted 3D vugular geobodies ([0004]: … and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain … on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Zeiza’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include estimating 3D acoustic impedance and bulk density volumes using a first trained model and using these estimated values as input to a second trained model for predicting the 3D vugular bodies in view of Di with the motivation to reduce the risk of overfitting and improves the lateral consistency in the subsurface property estimation (see Di [0056]) (see MPEP 2143 G).
Additionally, before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have recognized that applying the known technique of utilizing “a system, comprising: one or more memory modules; one or more hardware processors configured to execute instructions stored on the more or more memory models” to perform the machine learning based high-resolution 3D acoustic impedance volume and bulk density volume estimation and 3D vugular geobodies prediction of Zeiza in view of Di would have yielded predictable results and resulted in an improved system that would allow the automation of techniques described above.
Regarding Claim 16, ZEIZA in view of Di teaches the elements of the parent claim(s).
ZEIZA further teaches the following limitations of the claim:
The system claim 15, wherein the multi-disciplinary data comprises well-logs (Abstract: borehole images),
1D discrete vugular flags, basic seismic attributes (Page 6, top paragraph: link the 1D VPS flags with Seismic Data),
and high-resolution 3D property volumes (Page 5, top: … the 1D VPS flags are then tied to seismic attributes, i.e. seismic acoustic impedance, … The 3D seismic acoustic impedance cube is extracted into VPS probability (i.e. lower impedance) geobodies, …). [Examiner notes that specification [0009] states the 3D property volumes include "e.g. acoustic impedance"]
Regarding Claim 17, ZEIZA in view of Di teaches the limitations of the parent claim(s).
Di further teaches the limitation of:
The system claim 15, wherein the first trained machine learning model is trained using resampled seismic attributes, high resolution acoustic impedance logs, and high resolution bulk density well logs (See [0058]-[0061]: A first machine learning model may then be trained to extract seismic features in the seismic data. … The first machine learning model may be trained using supervised, unsupervised, pr quasi-unsupervised learning. … One or more well logs, and either the same or potentially additional seismic data, may then be received as input, as at 406. … For example, the well logs may represent one or more subsurface properties, such as acoustic impedance, porosity, density, etc.).
Before the effective filing date of the claimed invention, it would have been obvious to a PHOSITA to modify the teachings of Zeiza to include training the machine learning model using resampled seismic attributes, acoustic impedance, and bulk density well logs in view of Di with the motivation to apply Di’s machine learning approaches for improved efficiency and accuracy. Specifically, one would use Di’s first trained ML model to extract seismic features and generate seismic attributes such as high-resolution 3D acoustic impedance and bulk density volumes from the seismic data and then apply Di’s second ML model to predict 3D vugular geobodies (See ZEIZA Figure 5 and Di FIG. 4).
Regarding claim 20, ZEIZA, in view of Di teaches the limitations of the parent claim(s).
ZEIZA further teaches the limitation of:
The system of claim 15, wherein the seismic attributes comprise at least one of acoustic impedance, quadrature amplitude, Root Mean Square (RMS) amplitude, variance, frequency, envelope and spectrally decomposed attributes (FIG. 5, middle: Seismic attribute (acoustic impedance) extraction,).
Claims 4, 11, and 18 are rejected under 35 U.S.C 103 as being unpatentable over ZEIZA (Zeiza, Adam Danur, et al. "Reservoir characterization and 3D architecture of multi-scale vugular pore systems in carbonate reservoirs." SPE Reservoir Characterisation and Simulation Conference and Exhibition. SPE, 2023.) in view of Di (US2023/0026857 A1) and further in view of Hurley (Hurley et al., "Quantification of Vuggy Porosity in a Dolomite Reservoir from Borehole Images and Core, Dagger Draw Field, New Mexico," Presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, September 1998 (IDS filed on 09/04/2024, Cite No. 8)).
Regarding Claim 4, ZEIZA in view of Di teaches the limitations of the parent claim(s).
Di further teaches the following limitations of the claim:
The computer implemented method of claim 1, wherein the second trained machine learning model is trained using high resolution acoustic impedance logs, and high resolution bulk density well logs ([0060]-[0061]: The second machine learning model may thus be configured to map the (e.g., 3D) seismic data and extracted (e.g., 2D) seismic features to the (e.g., ID) well logs. [0059]: For example, the well logs may represent one or more subsurface properties, such as acoustic impedance, porosity, density, etc.)
It would have been obvious to combine the teachings of Di with Zeiza for the same rationale as claim 1.
Zeiza, in view of Di fails to clearly teach the following limitations of claim 4. Hurley, however, does explicitly teach the following:
wherein the second trained machine learning model is trained using continuous vugular flag logs (Page 4, Discussion: Once vug quantification has been done, it is possible to use neural-network approaches to predict vuggy porosity from other conventional logs).
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Zeiza’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include Hurley’s teaching on using 1D VPS flags (vugular flag logs) to train the second machine-learning model to predict 3D vugular geobodies.
A PHOSITA would have been motivated to make this modification because modeling 3D vugular geobodies is a known objective in subsurface characterization, and Hurley teaches that 1D VPS flags (vugular flag logs) provide suitable training data for neural-network prediction of vuggy porosity. Integrating Hurley's vug-log suggestion into Di's two-stage machine-learning approach, jointly with ZEIZA’s VPS characteristic workflow, merely applies a known machine-learning technique to an established predictive framework to improve its capability for predicting 3D vugular geobodies, yielding the predictable result of generating such predictions.
Claims 11 and 18 recite similar subject matter as claim 4 and are rejected under the same rationale.
Claims 5, 12, and 19 are rejected under 35 U.S.C 103 as being unpatentable over ZEIZA (Zeiza, Adam Danur, et al. "Reservoir characterization and 3D architecture of multi-scale vugular pore systems in carbonate reservoirs." SPE Reservoir Characterisation and Simulation Conference and Exhibition. SPE, 2023.) in view of Di (US2023/0026857 A1) and further in view of IMHOF (US20120090834A1).
Regarding claim 5, the combination of ZEIZA and Di teach the limitations of the parent claim(s). The combination of ZEIZA and Di fails to clearly teach, IMHOF, however teaches the following limitations of the claim:
The computer implemented method of claim 1, wherein transforming the seismic attributes into three dimensional (3D) geocellular properties associated with the reservoir comprises generating 3D gridded data by evaluating respective seismic attributes associated with each cell and modifying or retaining the respective seismic attributes based on a predetermined series of rules ( [0003]: “A seismic attribute is a measurable property of seismic data used to highlight or identify geological or geophysical features” and [0023]-[2026] : “In one embodiment, the invention is a method for transforming a seismic Survey data Volume into a seismic attribute data Volume more sensitive to Subsurface geophysical features indicative of hydrocarbon potential, comprising:”. “(a) selecting a 2D or 3D data analysis window size”; “(b) for each of multiple positions of the analysis window in the seismic data Volume, transforming the data within the window to a spectrum in a wavenumber domain; and” “(c) defining an attribute of the seismic databased on one or more spectral properties (“spectral attribute”), and computing the spectral attribute for each window, and assigning that attribute value to a spatial location representative of the window, thereby creating a multidimensional spectral attribute data volume.”).
Since ZEIZA and IMHOF are both analogous art as they relate to seismic data analysis; therefore, before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified ZEIZA’s method for vugular feature detection and 3D modeling, as discussed above, to clearly include “transforming the seismic attributes into three dimensional (3D) geocellular properties associated with the reservoir comprises generating 3D gridded data by evaluating respective seismic attributes associated with each cell and modifying or retaining the respective seismic attributes based on a predetermined series of rules” in view of IMHOF with the motivation to “transforming a seismic Survey data Volume into a seismic attribute data Volume more sensitive to Subsurface geophysical features indicative of hydrocarbon potential” ([0023]) (see MPEP 2143 G).
Claims 12 and 19 recite similar subject matter as claim 5 and are rejected under the same rationale.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Vallabhanneni (U.S PG-Pub. No. 2022/0075915 A1) teaches using machine learning to build 3D models of underground oil and gas reservoirs. It combines seismic data with well log data such as drilling, production, and core information. The system first trains a model to turn the combined data into “integrated enhanced logs,” which are then assembled into a static 3D reservoir model. The application also trains a second machine learning model using the updated 3D model plus dynamic modeling data. That second model is used to generate a dynamic reservoir 3Dmodel that tracks reservoir behavior over time.
Meek (U.S Patent No. 10,802,171 B2) teaches a way to turn surface seismic data and well logs into sharper underground images. It starts by tying seismic records to well-log measurements, so the data lines up in time and depth. It then uses a first round of model-based pre-stack inversion to build rock-property volumes such as acoustic impedance, shear impedance, density, and wave velocities. A second round refines those volumes with supervised neural network processing using additional wells.
Sinaga (Sinaga TM, Rosid MS, Haidar MW. Porosity prediction using neural network based on seismic inversion and seismic attributes. InE3S Web of Conferences 2019 (Vol. 125, p. 15006). EDP Sciences.) teaches
porosity prediction by using neural network on seismic attributes such as
amplitude envelope, average frequency, amplitude weighted phase, integrated absolute amplitude, acoustic impedance, and dominant frequency.
Zhao (Zhao L, Zou C, Chen Y, Shen W, Wang Y, Chen H, Geng J. Fluid and lithofacies prediction based on integration of well-log data and seismic inversion: A machine-learning approach. Geophysics. 2021 Jul 1;86(4):M151-65.) discloses an extreme gradient boosting (XGB) based workflow to predict the fluid and lithofacies distribution by integrating well-log and seismic data.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HUA MEI H CHEN whose telephone number is (571)270-0493. The examiner can normally be reached Monday-Friday 8am-5pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby Turner can be reached at 5712726334. 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.
/HUA MEI HARRY CHEN/ Examiner, Art Unit 2857
/SHELBY A TURNER/ Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights