DETAILED ACTION
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 .
Claims 1-20 have been presented for examination based on the amendment filed on
04/03/2023.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph.
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(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL by: Aaditya Satija, “RESERVOIR FORECASTING BASED ON STATISTICAL FUNCTIONAL ANALYSIS OF DATA AND PREDICTION VARIABLES” (2014) in further view of WO2010033710A2 by Dean & Schmidt.
This action is made Non-Final.
---- This page is left blank after this line ----
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.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention.
Wands Factor Evaluation
1. Breadth of the Claims
The claims are exceptionally broad. By reciting "a first transformation" and its "inverse" without further qualification, the claims encompass every conceivable mathematical transformation capable of decorrelating data. Under the standard set forth in Amgen Inc. v. Sanofi, "the more one claims, the more one must enable." The scope here reaches far beyond the specific mathematical frameworks disclosed. The Breadth of the Claims strongly weighs against enablement.
2. Nature of the Invention
The invention involves complex statistical data modeling for "unconventional subsurface reservoirs." Paragraph [0002] admits that the local variability of petrophysical properties makes determining completion designs "challenging because there can be a large number of combinations." This highlights the high complexity of the underlying subject matter. The nature of the invention weighs against enablement.
3. State of the Prior Art
While data imputation and Principal Component Analysis (PCA) are known in the art, the specific application of generating imputed production trends through the inverse transformation of stochastic random numbers in a reservoir engineering context is not described as a routine or well-settled practice. State of the Prior Art is Neutral to Weighs against enablement.
4. Level of Ordinary Skill in the Art (POSITA)
A POSITA in this field would likely be a petroleum engineer with advanced proficiency in data science or reservoir simulation. While this individual possesses a high level of skill, they still require sufficient technical guidance to apply generic mathematical concepts to specific geological gaps. Level of Ordinary Skill in the Art (POSITA) Supports enablement.
5. Level of Predictability in the Art
The field is inherently unpredictable due to the "local variability of petrophysical properties" and the non-linear nature of well production. Paragraph explicitly notes that "single well-completion design may not effectively stimulate the unconventional reservoir rocks across the field." Therefore, the effect of applying an arbitrary "transformation" to stochastic data is mathematically and geologically unpredictable. The Level of Predictability in the Art Strongly weighs against enablement.
6. Amount of Direction or Guidance Provided
The specification provides guidance only for a very narrow species of transformations: "principal component transform" and "sphering transform." There is no guidance provided for identifying, selecting, or implementing any other type of transformation that would satisfy the functional requirements of the claims while maintaining the "multivariate relation" necessary for accurate prediction. The Amount of Direction or Guidance Provided Weighs against enablement.
7. Existence of Working Examples
The application provides figures (Figures . 2A–3B) and subset data analysis demonstrating the invention's success using PCA and sphering. However, there are zero working examples using any other type of transformation. A single species (PCA) is insufficient to support a generic claim in an unpredictable art. Existence of Working Examples Weighs against enablement.
8. Quantity of Experimentation Necessary
To practice the full scope of the claims (i.e., to use a transformation other than PCA), a POSITA would have to engage in a significant trial-and-error process to discover which mathematical operations would successfully preserve multivariate production relationships when applied to Gaussian random numbers. This constitutes a requirement for undue experimentation. Quantity of Experimentation Necessary Weighs against enablement.
Enablement Supported: NO
The specification fails to provide an enabling disclosure commensurate with the scope of the claims. While the inventor may have been in possession of a specific system using Principal Component Analysis, the claims seek to monopolize the entire genus of "transformations" for well production data imputation. The lack of guidance for alternative transformations in an inherently unpredictable geological field necessitates undue experimentation for a POSITA to practice the full breadth of the invention.,
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 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. The term "inverse transformation" is challenged for ambiguity regarding its mathematical precision and functional scope. The term "includes" as an open-ended transition within a specific functional limitation, creates uncertainty as to what additional, potentially unrelated mathematical operations may be part of the "second transformation". In the context of multivariate data transformations (like PCA or sphering disclosed in the specification), an "inverse" can have multiple meanings. It could refer to a strict mathematical inverse matrix (A-1), a pseudoinverse (A+) used for non-square data sets, or a specific sequence of inverse operations (e.g., inverse sphering followed by inverse PCA). The claim recites that the second transformation "includes an inverse transformation". Under the broadest reasonable interpretation (BRI), this limitation does not define the second transformation itself, but merely requires that an inverse be present somewhere within it. This leaves a POSITA unable to determine the boundaries of the second transformation. For instance, if the second transformation "includes" an inverse but also includes five other unrelated transformations that alter the stochastic nature of the random numbers, it is unclear if such a process still falls within the claim scope. While the specification describes specific species of transformations (such as the "principal component transform" and "sphering transform”) and their corresponding "inverse" steps, Claim 1 uses the generic genus "first transformation". Without a more definite structural or functional constraint on what constitutes an "inverse" for any possible first transformation, the metes and bounds of the "second transformation" remain speculative.
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.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim(s) recite(s) mathematical concepts including transformations, decorrelation, and correlation used to generate a predictive model. These are mathematical relationships and calculations which are categorized as abstract ideas. The claim also recites mental processes of obtaining data and predicting trends, which are concepts that can be performed in the human mind. This judicial exception is not integrated into a practical application because the additional limitations of obtaining well data and predicting trends merely link the abstract idea to a particular technological environment (well completion) and characterize the results of the calculation. The claim does not reflect a technical improvement to a specific industrial process or computer functionality; rather, it describes a mathematical method for imputing data to increase model accuracy. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the step of obtaining data is insignificant extra-solution activity (data gathering). The remaining steps are performed by a generic computer using its ordinary capacity to store and process data, which is well-understood, routine, and conventional activity in the art. The ordered combination of these mathematical steps does not result in a technological solution to a technical problem.
Claims [ 1 ]:
Step 1: the claims are drawn to a method and system respectively, falling under one of the four statutory categories of invention.
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. The limitations are bolded for abstract idea/judicial exception identification.
Claim 1
Mapping Under Step 2A Prong 1
A computer-implemented method, comprising:
obtaining first data associated with a plurality of wells, wherein the first data comprises input data and well production data, and wherein the input data comprises subsurface condition data and well completion data;
generating a predictive model between the well production data and the input data;
decorrelating the input data into second data by applying a first transformation to the input data to generate the second data;
generating a plurality of random numbers using the second data;
correlating the plurality of random numbers by applying a second transformation to the plurality of random numbers to generate imputed data of the input data, wherein the second transformation comprises an inverse transformation of the first transformation;
applying the predictive model to the imputed data of the input data to generate imputed data of the well production data;
and predicting well production trend of the plurality of wells using the imputed data of the well production data.
See Step 2A Prong 2
See Step 2A Prong 2
Mathematical Concepts: The claims recite "generating a predictive model." [See FIG. 5 (502) Prediction Model. Is shown a function) This is a mathematical relationships and calculations used to manipulate data. (as in 2106.04(a)(2) Abstract Idea Groupings)
Mathematical Concepts: The claims recite "decorrelating1 the input data2 into second data by applying a first transformation3 to the input data to generate the second data" This is a mathematical relationships and calculations used to manipulate data. (as in 2106.04(a)(2) Abstract Idea Groupings)
Mathematical Concepts: The claims recite " generating a plurality of random numbers4.." This is a mathematical relationships and calculations used to manipulate data. (as in 2106.04(a)(2) Abstract Idea Groupings)
Mathematical Concepts: The claims recite "correlating5 the plurality of random numbers by applying a second transformation6 to the plurality of random numbers to generate imputed data of the input data, wherein the second transformation comprises an inverse transformation of the first transformation". This is a mathematical relationships and calculations used to manipulate data. (as in 2106.04(a)(2) Abstract Idea Groupings)
See Step 2A Prong 2
See Step 2A Prong 2
Step 2A, Prong 2: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d). As per (1) the additional elements are identified as bolded parts of the limitations in column 1 of the table below, and as per (2) the evaluation is shown in the mapping section of the table.
In accordance with this step, the judicial exception is not integrated into a practical application.
Claim 1
Mapping Under Step 2A Prong 2
A computer-implemented method, comprising:
obtaining first data associated with a plurality of wells, wherein the first data comprises input data and well production data, and wherein the input data comprises subsurface condition data and well completion data;
generating a predictive model between the well production data and the input data;
decorrelating the input data into second data by applying a first transformation to the input data to generate the second data;
generating a plurality of random numbers using the second data;
correlating the plurality of random numbers by applying a second transformation to the plurality of random numbers to generate imputed data of the input data, wherein the second transformation comprises an inverse transformation of the first transformation;
applying the predictive model to the imputed data of the input data to generate imputed data of the well production data;
and predicting well production trend of the plurality of wells using the imputed data of the well production data.
Generic Tool: The claim invokes a "computer" merely as a tool to perform the mathematical transformations more efficiently than a human. (2106.05(f)) (See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit))
Additional Elements: The additional elements beyond the mathematical transformations include obtaining data from wells and predicting a "well production trend". (mere data gathering) (MPEP § 2106.05(g))
Field of Use: Limiting the mathematical model to the field of well production is a "field of use" limitation, which does not integrate the exception into a practical application.
See Step 2A Prong 1
See Step 2A Prong 1
See Step 2A Prong 1
See Step 2A Prong 1
Additional Elements: The additional elements beyond the mathematical transformations include obtaining data from wells and predicting a "well production trend".
Improvement to Technology/Technical Field: While the specification indicates this technique helps determine "well completion designs" for "unconventional subsurface reservoirs," the claim itself focuses on the statistical accuracy of the prediction through data imputation. An improvement in the mathematical accuracy of a model is generally viewed as an improvement to the abstract idea itself, not a technical improvement to a technological process or computer functionality.
Field of Use: Limiting the mathematical model to the field of well production is a "field of use" limitation, which does not integrate the exception into a practical application. (2106.04(d)(1)) (See MPEP § 2106.05(f))( See, e.g., Rapid Litigation Management v. CellzDirect, Inc., 827 F.3d 1042, 119 USPQ2d 1370 (Fed. Cir. 2016)) ( See Internet Patents Corporation v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1418 (Fed. Cir. 2015))
Additional Elements: The additional elements beyond the mathematical transformations include obtaining data from wells and predicting a "well production trend". (mere data gathering) (MPEP § 2106.05(g))
Field of Use: Limiting the mathematical model to the field of well production is a "field of use" limitation, which does not integrate the exception into a practical application.
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05. This step determines whether the additional elements amount to "significantly more" than the exception by providing an unconventional technological solution. (see MPEP § 2106.05(g) and see MPEP § 2106.05(h))
"Obtaining first data" is characterized as "mere data gathering," which is considered insignificant extra-solution activity. Executing the transformations and predictive model on a "computer" requires only well-understood, routine, and conventional computer functions (storing/retrieving data, performing calculations).
Conclusion: The additional elements do not amount to significantly more.
Claim 2 recites, “The computer-implemented method of claim 1 (See claim 1), wherein the subsurface condition data comprises at least one of total organic carbon (TOC), reservoir pressure, porosity, volume of clay, or Young's modulus, and wherein the subsurface condition data is from each of the plurality of wells.” (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 3 recites, “The computer-implemented method of claim 1 (See claim 1), wherein the well completion data comprises at least one of lateral well length, total proppant amount, total frack water volume, or number of fracture clusters, and wherein the well completion data is from each of the plurality of wells.” (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 4 recites, “The computer-implemented method of claim 1 (see claim 1), wherein generating the predictive model between the well production data and the input data comprises generating the predictive model using a linear regression model between the well production data and the input data.) (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 5 recites, “The computer-implemented method of claim 1 (See claim 1), wherein decorrelating the input data into the second data by applying the first transformation to the input data to generate the second data comprises: applying a third transformation to the input data to transform the first data into fourth data, wherein the third transformation comprises principal component transform; and applying a fourth transformation to the fourth data to transform the fourth data into the second data, wherein the fourth transformation comprises sphering transform.” (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 6 recites, “The computer-implemented method of claim 5 (See claim 5), wherein correlating the plurality of random numbers by applying the second transformation to the plurality of random numbers to generate the imputed data of the input data comprises: applying a fifth transformation to the plurality of random numbers to transform the plurality of random numbers into fifth data, wherein the fifth transformation comprises an inverse transformation of the fourth transformation; and applying a sixth transformation to the fifth data to transform the fifth data into the imputed data of the input data, wherein the sixth transformation comprises an inverse transformation of the third transformation.” (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 7 recites, “The computer-implemented method of claim 1 (See Claim 1), wherein generating the plurality of random numbers using the second data comprises generating a plurality of Gaussian random numbers using the second data.” (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 8 recites, “The computer-implemented method of claim 1, wherein predicting the well production trend of the plurality of wells using the imputed data of the well production data comprises predicting, based on a subset of the input data, the well production trend of the plurality of wells using the imputed data of the well production data.” (Mental Processes)(see MPEP § 2106.04(a)(2), subsection III) (Mathematical Concepts) (as in 2106.04(a)(2) Abstract Idea Groupings)
Claim 9Step 1: Article of Manufacture
Step 2A Prong 1: similar to claim 1
Step 2A Prong 2: similar to claim 1
Step 2B: similar to claim 1
Claim 10Step 1: Article of Manufacture
Step 2A Prong 1: similar to claim 2
Step 2A Prong 2: similar to claim 2
Step 2B: similar to claim 2
Claim 11Step 1: Article of Manufacture
Step 2A Prong 1: similar to claim 3
Step 2A Prong 2: similar to claim 3
Step 2B: similar to claim 3
Claim 12Step 1: Article of Manufacture
Step 2A Prong 1: similar to claim 4
Step 2A Prong 2: similar to claim 4
Step 2B: similar to claim 4
Claim 13Step 1: Article of Manufacture
Step 2A Prong 1: similar to claim 5
Step 2A Prong 2: similar to claim 5
Step 2B: similar to claim 5
Claim 14Step 1: Article of Manufacture
Step 2A Prong 1: similar to claim 6
Step 2A Prong 2: similar to claim 6
Step 2B: similar to claim 6
Claim 15Step 1: Machine
Step 2A Prong 1: similar to claim 1
Step 2A Prong 2: similar to claim 1
Step 2B: similar to claim 1
Claim 16Step 1: Machine
Step 2A Prong 1: similar to claim 2
Step 2A Prong 2: similar to claim 2
Step 2B: similar to claim 2
Claim 17Step 1: Machine
Step 2A Prong 1: similar to claim 3
Step 2A Prong 2: similar to claim 3
Step 2B: similar to claim 3
Claim 18Step 1: Machine
Step 2A Prong 1: similar to claim 4
Step 2A Prong 2: similar to claim 4
Step 2B: similar to claim 4
Claim 19Step 1: Machine
Step 2A Prong 1: similar to claim 5
Step 2A Prong 2: similar to claim 5
Step 2B: similar to claim 5
Claim 20Step 1: Machine
Step 2A Prong 1: similar to claim 6
Step 2A Prong 2: similar to claim 6
Step 2B: similar to 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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL by: Aaditya Satija, “RESERVOIR FORECASTING BASED ON STATISTICAL FUNCTIONAL ANALYSIS OF DATA AND PREDICTION VARIABLES” (2014) in further view of WO2010033710A2 by Dean & Schmidt.
Regarding Claim 1
Satija teaches A computer-implemented method, comprising: obtaining first data associated with a plurality of wells, wherein the first data comprises input data and well production data, and wherein the input data comprises subsurface condition data and well completion data; (P.51-52 §3.2 ¶1: “In
this problem, the data variable 𝑫 consists of time series observations of contaminant
concentration at the three observation wells over the past 3.5 days…In a causal forecasting approach, the data-prediction relationship would be parameterized using a model variable 𝑴 that contains the subsurface parameters of the aquifer.” The examiner interprets where input data and well production data is shown in Satija obtaining production history (D) and model properties (M).) generating a predictive model between the well production data and the input data; (P.49 §3.1 ¶1: “Forecasts obtained as uncertainty quantification on some future response such as future oil and water production of existing wells, four-dimensional saturation changes in the field, or production rates of planned wells are often used for decision making in the petroleum industry. A typical example of a forecast is the prediction of reservoir production performance based on historical production data and geological information in presence of the historical production data. The causal relationship between the data and the prediction is parameterized using a three-dimensional gridded subsurface model constrained to well and seismic data. These forecasts are often evaluated as forward responses of the subsurface models obtained solutions of dynamic data inversion.”)
decorrelating the input data into second data by applying a first transformation to the input data to generate the second data; (P.71 Figure 3.3:
PNG
media_image1.png
1208
886
media_image1.png
Greyscale
Figure 3.3 teaches PCA and CFCA to transform correlated variables into uncorrelated components.)
generating a plurality of random numbers using the second data; (P.59 §3.3 ¶1: “This posterior distribution is sampled to obtain 𝐾 low dimensional samples of 𝒉*that are back transformed to an ensemble of {𝒉1, 𝒉2⋯ 𝒉k} that together empirically represent the forecast uncertainty in physical dimensions.” The examiner interprets where random numbers is shown in sampling a joint/posterior distribution in the transformed space.) correlating the plurality of random numbers by applying a second transformation to the plurality of random numbers to generate imputed data of the input data, wherein the second transformation comprises an inverse transformation of the first transformation; (P.71 Figure 3.3: The examiner interprets where inverse transformation/imputed data as shown in Figure 3.3 disclosing a bijective back-transformation.) applying the predictive model to the imputed data of the input data to generate imputed data of the well production data; (P.71 Figure 3.3, P.67 §3.4 ¶2: “Since sampling a Gaussian posterior distribution and back transforming those samples are computationally inexpensive linear operations, as many samples can be generated as needed to effectively quantify an estimate on the forecast-uncertainty.” The examiner interprets where apply models to imputed data is shown in applying models to transformed/back-transformed samples to generate forecasts.) and predicting well production trend of the plurality of wells using the imputed data of the well production data. (P.67 §3.5 ¶1: “Since many forecasting problems with subsurface uncertainty tend to involve highly multivariate earth models with computationally expensive forward models, using PFA as a diagnostic technique or a quick-estimate may be useful since it avoids any
iterative workflow.” The examiner interprets where predicting trend is shown in quantifying forecast uncertainty and predicting production performance over time.)
While Satija focuses on using this cycle to generate forecasts, Satija fails to teaches computer-implemented modeling systems that require populating physical properties for reservoir realizations to address the problem of sparse or incomplete data. Dean & Schmidt teaches computer-implemented modeling systems that require populating physical properties for reservoir realizations to address the problem of sparse or incomplete data. Dean & Schmidt teaches A computer-implemented method, comprising: obtaining first data associated with a plurality of wells, wherein the first data comprises input data and well production data, and wherein the input data comprises subsurface condition data and well completion data; (P.2 Line: 31 “With respect to coupling, a variable in the fully-expanded Jacobian that can be used to couple fluid flow in the reservoir to the geomechanical model can be: effective stress, porosity and one or more displacements associated with the geomechanical model.” The examiner interprets where obtaining data is shown in obtaining porosity and stresses.) correlating the plurality of random numbers by applying a second transformation to the plurality of random numbers to generate imputed data of the input data, wherein the second transformation comprises an inverse transformation of the first transformation; (P.29 Line: 15 “Such a computer system can also store and manipulate the data indicative of physical properties associated with a geomechanical reservoir system, the fully-expanded Jacobian for the full system of equations for the models included in the computation, the solution to the fully-expanded Jacobian, the generated fracturing predictions, or measurements that can be used by a computer system implemented with the analytical methods described herein” The examiner interprets where the inverse transformation/imputed data is shown in manipulating physical properties for realizations to fill gaps in sparse data.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date to apply Satija's known, efficient bijective mapping cycle to the input variables (subsurface/completion) of the system taught by Dean & Schmidt to fill information gaps (data imputation) in sparse datasets. Satija himself identifies 'data-gaps' as a central challenge in earth science forecasting and positions his methodology as a 'toolkit' for such problems. The motivation to do so would be to reconstruct missing or sparse observational data in a way that preserves the physical and statistical relationships between variables, enabling more accurate and reliable forecasting and analysis. The result of this combination; applying the predictive model to the synthetic imputed inputs to predict production trends, is the predictable result of applying Satija’s established forecasting framework to a more complete, synthetic dataset generated through his own transformation methodology.
Regarding Claim 2
Satija in combination with Dean & Schmidt teach The computer-implemented method of claim 1 (See Claim 1). Satija teaches wherein the subsurface condition data comprises at least one of total organic carbon (TOC), reservoir pressure, porosity, volume of clay, or Young's modulus, (P.50 §3.1 ¶2: “This spatial prior distribution may include elements of structural uncertainty (layering and faults), lithofacies and petrophysical properties (porosity, hydraulic conductivity) from geological and geophysical data
sources.” and wherein the subsurface condition data is from each of the plurality of wells (P.51-52 §3.2 ¶1: “In this problem, the data variable 𝑫 consists of time series observations of contaminant concentration at the three observation wells over the past 3.5 days…In a causal forecasting approach, the data-prediction relationship would be parameterized using a model variable 𝑴 that contains the subsurface parameters of the aquifer.” )
Satija fails to teach a geomechanical modeling system configured for receiving and storing data for physical properties such as porosity and stresses. Dean & Schmidt teaches a geomechanical modeling system configured for receiving and storing data for physical properties such as porosity and stresses. Dean & Schmidt teaches volume of clay, or Young's modulus, (P.6 Line: 8 “For example, a fully-expanded Jacobian can act to couple fluid flow in the reservoir to the geomechanical model by one or more of the following variables: effective stress, a porosity and one or more displacements associated with the geomechanical model.”)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention that the selection of these common reservoir parameters as the target variables for Satija’s imputation cycle is a routine selection of result-effective variables well known in the art of reservoir engineering. The motivation to do so would be that selecting common reservoir parameters as target variables in the imputation cycle is critical for ensuring accurate, physically meaningful, and consistent imputed datasets. Integrating sensitivity analysis, feature ranking, and domain-specific constraints with advanced machine learning and deep learning techniques enables high-fidelity reservoir modeling, particularly under conditions of sparse or incomplete data. The results; predicting production trends using synthetic imputed data for these specific parameters, are the predictable result of applying Satija’s forecasting framework to the standard physical properties required for reservoir modeling as taught by Dean & Schmidt.
Regarding Claim 3
Satija in combination with Dean & Schmidt teach The computer-implemented method of claim 1 (See Claim 1). Satija teaches (P.51-52 §3.2 ¶1: “In this problem, the data variable 𝑫 consists of time series observations of contaminant concentration at the three observation wells over the past 3.5 days…In a causal forecasting approach, the data-prediction relationship would be parameterized using a model variable 𝑴 that contains the subsurface parameters of the aquifer.”
The examiner interprets where the well completion data is from each of the plurality of wells is expressed as obtaining historical production data (D) and model variables (M) from multiple wells in a field to perform reservoir-wide forecasting.)
Satija fails to teach wherein the well completion data comprises at least one of lateral well length, total proppant amount, total frack water volume, or number of fracture clusters. Dean & Schmidt teaches wherein the well completion data comprises at least one of lateral well length, total proppant amount, total frack water volume, or number of fracture clusters.
(Fig. 5:
PNG
media_image2.png
1214
990
media_image2.png
Greyscale
The examiner interprets where the completion data is expressed as receiving physical properties and parameters to populate a "fracture model" (e.g., width, profile).)
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to combine Dean & Schmidt with Satija. The selection of lateral well length, proppant amount, and fracture cluster counts as the variables for imputation is a routine selection of result-effective engineering variables well known in the art of well completion. Furthermore, Satija discloses obtaining this data from an ensemble of multiple wells in a field to establish causal relationships, The result; predicting production trends using synthetic imputed completion data for these specific parameters, is the predictable result of applying Satija’s forecasting framework to the standard completion properties required for reservoir modeling as taught by Dean & Schmidt. Satija explicitly recognizes that earth science measurements are susceptible to "data-gaps" and that obtaining reliable data is "technologically difficult". Dean & Schmidt teaches a system that relies on receiving physical properties to populate a geomechanical model for "completion strategies" A person of ordinary skill in the art (PHOSITA) would have been motivated to use Satija's more efficient, bijective mapping cycle to fill those gaps (imputation) in the completion data (lateral length, proppant, etc.) required by the system of Dean & Schmidt to ensure a complete dataset for modeling.
Regarding Claim 4
Satija in combination with Dean & Schmidt teach The computer-implemented method of claim 1 (See Claim 1). Satija teaches wherein generating the predictive model between the well production data and the input data comprises generating the predictive model using a linear regression model between the well production data and the input data. (P.5-6 §1.3.1 ¶12: “However, in the causal approach, the data variable and the prediction variable are viewed as physical “responses” of the subsurface. This establishes a causal relationship between the data and the prediction based on a shared underlying subsurface. A model variable 𝑴 is defined to capture relevant properties of the subsurface. For example, in a reservoir engineering problem, the model variable could contain the permeability field on a three dimensional grid of a certain resolution. Forward models based on physical processes are used to estimate the causal physical relationships between (1) the data and the model as 𝒅 = 𝒈(𝒎) and (2) the prediction and the model as 𝒉 = 𝒓(𝒎)” The examiner interprets where linear regression is expressed in using linear parametric regression to establish causal physical relationships between data and models.)
Therefore, It would have been obvious to a POSITA before the effective filing date of the invention to utilize the linear regression model taught by Satija within the reservoir modeling framework of Dean. The motivation to do so would be the design incentive to improve the scalability and speed of forecasting results in the petroleum industry, as explicitly stated by Satija. The use of linear regression is a well-known statistical technique that, when applied to known reservoir data, yields the predictable result of a production trend prediction without the high computational cost of iterative flow simulators.
Regarding Claim 5
Satija in combination with Dean & Schmidt teach the computer-implemented method of claim 1 (See Claim 1). Satija teaches wherein decorrelating the input data into the second data by applying the first transformation to the input data to generate the second data comprises: applying a third transformation to the input data to transform the first data into fourth data, wherein the third transformation comprises principal component transform; (P.23 §2.2.1.2 ¶1 : “This [PCA] is a classical multivariate analysis procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components”) and applying a fourth transformation to the fourth data to transform the fourth data into the second data, wherein the fourth transformation comprises sphering transform. (P.71 See Figure 3.3, P.67 §3.4 ¶2: “Since sampling a Gaussian posterior distribution and back transforming those samples are computationally inexpensive linear operations, as many samples can be generated as needed to effectively quantify an estimate on the forecast-uncertainty.” The examiner interprets where sphering is shown as the routine act of standardizing these PCA components to unit variance.)
Regarding Claim 6
Satija in combination with Dean & Schmidt teach the computer-implemented method of claim 5 (See Claim 5). Satija teaches wherein correlating the plurality of random numbers by applying the second transformation to the plurality of random numbers to generate the imputed data of the input data comprises: applying a fifth transformation to the plurality of random numbers to transform the plurality of random numbers into fifth data, wherein the fifth transformation comprises an inverse transformation of the fourth transformation; (See Figure 3.3, P.23 §2.2.1.2 ¶1 : “This [PCA] is a classical multivariate analysis procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components” The examiner interprets the inverse sphering as shown in the idea that if the data was standardized (sphered), the bijective return requires an inverse of that standardization.) and applying a sixth transformation to the fifth data to transform the fifth data into the imputed data of the input data, wherein the sixth transformation comprises an inverse transformation of the third transformation. (See Figure 3.3: The examiner interprets where inverse PCA is shown in Figure 3.3 as the sampled scores are mapped back to the physical space via an 'Inverse Functional Transformation.’)
Regarding Claim 7
Satija in combination with Dean & Schmidt teach the computer-implemented method of claim 1 (See Claim 1). Satija teaches wherein generating the plurality of random numbers using the second data comprises generating a plurality of Gaussian random numbers using the second data (P.71 See Figure 3.3, P.67 §3.4 ¶2: “Since sampling a Gaussian posterior distribution and back transforming those samples are computationally inexpensive linear operations, as many samples can be generated as needed to effectively quantify an estimate on the forecast-uncertainty.”)
Regarding Claim 8
Satija in combination with Dean & Schmidt teach the computer-implemented method of claim 1 (See Claim 1). Satija teaches wherein predicting the well production trend of the plurality of wells using the imputed data of the well production data comprises predicting, based on a subset of the input data, the well production trend of the plurality of wells using the imputed data of the well production data. (P.56 §3.2.2 ¶2: “To address this problem of high dimensionality, (Scheidt et al., 2014) use non-linear
principal component analysis or NLPCA (Kramer, 1991) to reduce the dimensions of the samples 𝒅 and 𝒉 to a scalar value.” The examiner interprets where based on a subset of the input is shown in using PCA/CFCA to "reduce the dimension" of reservoir data into a subset of significant components.
Satija fails to teach a system specifically configured to evaluate 'completion strategies'. Dean & Schmidt teaches wherein predicting the well production trend of the plurality of wells using the imputed data of the well production data comprises predicting, based on a subset of the input data, the well production trend of the plurality of wells using the imputed data of the well production data. (P.51:
PNG
media_image3.png
1048
1054
media_image3.png
Greyscale
The examiner interprets where based on subset of data is shown in evaluating specific "completion strategies" which requires isolating subsets of engineering parameters.)
It would have been obvious to a POSITA before the effective filing date of the invention to utilize the variable subset selection technique taught by Satija within the reservoir modeling framework of Dean. The motivation to do so would be the clear design incentive to improve the speed and efficiency of forecasting by focusing computational effort on the aspects of the problem that are most relevant to the desired forecast, as explicitly stated by Satija. The use of sensitivity analysis to identify a subset of result-effective variables is a routine statistical procedure that, when applied to known reservoir data, yields the predictable result of an efficient, fit-for-purpose production trend prediction.
Regarding Claim 9Article of Manufacture versions of Claim 1. Similar rejection, see Claim 1.
Regarding Claim 10Article of Manufacture versions of Claim 2. Similar rejection, see Claim 2.
Regarding Claim 11Article of Manufacture versions of Claim 3. Similar rejection, see Claim 3.
Regarding Claim 12Article of Manufacture versions of Claim 4. Similar rejection, see Claim 4.
Regarding Claim 13Article of Manufacture versions of Claim 5. Similar rejection, see Claim 5.
Regarding Claim 14Article of Manufacture versions of Claim 5. Similar rejection, see Claim 6.
Regarding Claim 15Machine versions of Claim 1. Similar rejection, see Claim 1.
Regarding Claim 16Machine versions of Claim 2. Similar rejection, see Claim 2.
Regarding Claim 17Machine versions of Claim 3. Similar rejection, see Claim 3.
Regarding Claim 18Machine versions of Claim 4. Similar rejection, see Claim 4.
Regarding Claim 19Machine versions of Claim 5. Similar rejection, see Claim 5.
Regarding Claim 20Machine versions of Claim 6. Similar rejection, see Claim 6.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AARIC RAYJEE MARKS whose telephone number is (571)467-6372. The examiner can normally be reached Monday-Friday 8am-5pm.
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, Ryan Pitaro can be reached at (571) 272-4071. 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.
/AARIC R MARKS/Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
1 Spec [0003]: “..The input data is decorrelated into second data by application of a first transformation to the input data to generate the second data.” Also see FIG. 5 (504)
2 Spec [0029]: “FIG. 3A illustrates an example of preserving the multivariate relation of the original input multivariate data using the imputed data.”
3 Spec [0026]: “ An example of the first transformation can include two transforms.“
4 Spec [0027]: “The generated random numbers can be Gaussian random numbers in some cases.”
5 Spec: [0018]: “In some implementations, data imputing can be a statistical technique for estimating the missing data using the correlation within the original multivariate data.”
6 Spec [0003]: “.. where the second transformation includes an inverse transformation of the first transformation. “
Prosecution Insights