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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 10/6/2025 has been entered.
Response to Amendment
Applicant' s amendment and response filed 10/6/2025 has been entered and made record. This application contains 23 pending claims.
Claims 1-2, 10, 17, 28, 32, 34-35, 37, and 39-41 have been amended.
Claims 14 and 38 have been cancelled.
Claims 43-47 have been added.
Response to Arguments
Applicant’s arguments filed 10/6/2025 regarding claims rejections under 35 U.S.C. 101 in claim 1-2, 10, 14, 17, 20-21, 23-24, 27-28, and 31-42 have been fully considered but they are not persuasive.
The applicant argues on page 9-11 of the remark filed on 10/6/2025 that “…
Applicant respectfully contends that the claims as amended comply with 35 USC§101. … In this regard, amended claim 1 manifests an integration into a practical application, both in a metaphorical sense and in an actual sense. Metaphorically, the structured representation is integrated into the seismic data by the integrated presentation of both in a single output. Practically, the single output, on a pixel level, integrates the two disparate parts of the seismic image and the structured representation. Separate from this, Applicant respectfully contends that the limitations are akin to Core wireless Licensing S.A.R.L. v. LG Electronics, Inc. in which, acknowledging prior art interface difficulties(necessitating the viewer to drill down to consume the information), found the claimed summary interface patent eligible. As such, Applicant respectfully contends that the claims are presented comply with 35 USC §101.”
The Examiner respectfully disagrees applicant’s argument. Practical application can be demonstrated by limitations that are sufficient to integrate the judicial exception into a practical application. The additional element of “wherein the relationships comprise: (i) spatial relationships including positional descriptors; and (ii) one or both of geological or petrological relationships” is not sufficient to integrate the abstract idea into a practical application because it only adds an insignificant extra-solution activity to the judicial exception. The additional element “accessing subsurface data for a subsurface region, wherein the subsurface data comprises one or more seismic images” represents necessary data gathering and does not integrate the limitation into a practical application. As recited in MPEP section 2106.05(g), necessary data gathering (i.e. accessing data) is considered extra solution activity in light of Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015). Therefore, the current claims do not recite additional elements that are indicative of integration of an abstract idea into a practical application.
Hence, the Examiner submits that the rejections of claim 1-2, 10, 14, 17, 20-21, 23-24, 27-28, and 31-42 are proper.
Applicant' s arguments filed 12/6/2025 regarding claims rejections under 35 U.S.C. 103 in claims 1-2, 10, 14, 17, 20-21, 23-24, 27-28, and 31-42 have been fully considered and are persuasive. Newly discovered prior arts, Salman US 20200278465, and Bi US 20160124113, will be used in combination with prior arts cited in the previous office action to reject some features of the amended claim limitations.
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 1-2, 10, 17, 23-24, 27-28, 31-35, 37, and 39-47 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
As to claim 1, the claim recites “A method comprising:
accessing subsurface data for a subsurface region, wherein the subsurface data comprises one or more seismic images;
automatically extracting a structured representation from the subsurface data by:
identifying geologic and fluid objects in the subsurface data, wherein each object corresponds to a node of the structured representation; and
identifying relationships among the identified geologic and fluid objects, wherein each relationship corresponds to an edge of the structured representation, wherein the relationships comprise: (i) spatial relationships including positional descriptors; and (ii) one or both of geological or petrological relationships;
automatically analyzing the structured representation; and
automatically generating, using the analysis of the structured representation, one or more images for output on a display, the one or more images comprising the one or more seismic images with respective nodes anchored at respective pixel locations for the respective objects and the relationships superimposed thereon so that the one or more images are on the subsurface data and being generated to highlight at least one aspect of the structured representation representing the identified geologic and the fluid objects and the relationships among the identified geologic and the fluid objects.”
Under the Step 1 of the eligibility analysis, we determine whether the claim is directed to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (process for claim 1).
Under the Step 2A, Prong One, we consider whether the claim recites a judicial exception (abstract idea). In the above claim, the bold type portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim that covers mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations).
In claim 1, the steps identified in bold type are mathematical concepts, therefore, they are considered to be abstract idea.
Next, under the Step 2A, Prong Two, we consider whether the claim that recites a judicial exception is integrated into a practical application.
In this step, we evaluate whether the claim recites additional element that integrate the exception into a practical application of that exception.
The claim comprises the following additional element:
accessing subsurface data for a subsurface region, wherein the subsurface data comprises one or more seismic images; wherein the relationships comprise: (i) spatial relationships including positional descriptors; and (ii) one or both of geological or petrological relationships.
The additional element “accessing subsurface data for a subsurface region, wherein the subsurface data comprises one or more seismic images” represents necessary data gathering and does not integrate the limitation into a practical application. The additional element “wherein the relationships comprise: (i) spatial relationships including positional descriptors; and (ii) one or both of geological or petrological relationships” is not sufficient to integrate the abstract idea into a practical application because it only adds an insignificant extra-solution activity to the judicial exception.
In conclusion, the above additional element, considered individually and in combination with the other claims elements does not reflect an improvement to other technology or technical field, does not reflect improvements to the functioning of the computer itself, does not recite a particular machine, does not effect a transformation or reduction of a particular article to a different state or thing, and, therefore, does not integrate the judicial exception into a practical application. Therefore, the claim is directed to a judicial exception and require further analysis under the Step 2B.
The above claim, does not include additional element that is sufficient to amount to significantly more than the judicial exception because it is generically recited and is well-understood/conventional in a relevant art as evidenced by the prior art of record (Step 2B analysis).
For example, accessing subsurface data for a subsurface region, wherein the subsurface data comprises one or more seismic images is considered necessary data gathering. As recited in MPEP section 2106.05(g), necessary data gathering (i.e. accessing data) is considered extra solution activity in light of Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015).
For example, the relationships comprise: (i) spatial relationships including positional descriptors; and (ii) one or both of geological or petrological relationships is disclosed by “Salman 20200278465”, [0002], [0043], [0052], [0086], FIG. 1; and “Bi US 20160124113”, [0010], [0073], [0078], [0080].
With regards to the dependent claims, claims 2, 10, 17, 23-24, 27-28, 31-35, 37, and 39-47 provide additional features/steps which are considered part of an expanded abstract idea of the independent claim 1, and do not integrate the abstract ideas into a practical application.
The dependent claims are, therefore, also not eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 and 43 are rejected under 35 U.S.C. 103 as being unpatentable over Cheng et al. (US 20130338987, hereinafter Cheng), in view of Salman et al. (US 20200278465, hereinafter Salman), and further in view of Liu et al. (US 20190064378, hereinafter Liu).
As to claim 1, Cheng teaches accessing subsurface data for a subsurface region, wherein the subsurface data comprises one or more seismic images; (FIG. 5, #500; FIG. 9, Step 902; [0056]); and
automatically extracting a structured representation from the subsurface data ([0004] discloses physical regions that can be subjected to 3D analysis include the earth's subsurface (i.e., 3D model visualization represents seismic image - emphasis added by Examiner); [0024] discloses automatically identifying potential compartments of a reservoir based on the reservoirs geological structure, and obtaining structural data corresponding to a geological structure of a reservoir) by:
identifying geologic and fluid objects in the subsurface data, wherein each object corresponds to a node of the structured representation ([0076] discloses each node is an abstraction of a level set contact on a given reservoir, and each edge that connects nodes can also contain attributes such as gas/oil/water pressure gradients within each reservoir regions (i.e., each node and each edge correspond to geologic and fluid objects such as oil and gas). As shown in FIG. 5, the topological net can be represented as a graph with critical points 506 (i.e., nodes); [0081] discloses by analyzing the topological relation of the critical points (i.e., nodes) on the topological net, the compartments, fluid (i.e., oil and gas of the geologic and fluid objects) contacts and their spill/break-over relations can be tracked);
identifying relationships among the identified geologic and fluid objects, wherein each relationship corresponds to an edge of the structured representation ([0076] discloses a topological net is a data representation for relationships of reservoir compartments where each node is an abstraction of a level set contact on a given reservoir. An edge connecting nodes indicates a smooth transition between two level sets, and each edge can also contain attributes such as gas/oil/water pressure gradients within each reservoir regions. As shown in FIG. 5, the topological net can be represented as a graph with critical points 506 (i.e., nodes) and edges 508);
automatically analyzing the structured representation ([0024] discloses automatically identifying potential compartments of a reservoir based on the reservoirs geological structure); and
one or more seismic images with the relationships superimposed thereon so that the one or more images are on the subsurface data ([0096] discloses the geometry of the reservoir compartments can also be re-constructed from the topological net 802, based on the depth information associated with the critical points 804 and the corresponding depth level sets of the reservoir geometry, and the topological net 802 may also be superimposed over a display of the geological model used to generate the topological net 802).
Cheng does not explicitly teach wherein each relationship corresponds to an edge of the structured representation, wherein the relationships comprise: (i) spatial relationships including positional descriptors; and (ii) one or both of geological or petrological relationships; and one or more seismic images with respective nodes anchored at respective pixel locations for the respective objects.
Salman teaches wherein each relationship corresponds to an edge of the structured representation, wherein the relationships comprise: (i) spatial relationships including positional descriptors ([0043] discloses seismic image data identify one or more faults in a geologic region., and identification of a fault can include determining one or more parameters or parameter values that characterize the fault, and consider fault location, position (i.e., location and position of fault indicates spatial relationships - emphasis added by Examiner), dimension(s), type of fault, etc.; [0086] discloses information may specifies one or more location coordinates (i.e., location coordinates indicate positional descriptors of spatial relationships - emphasis added by Examiner) of a feature in a geologic environment); and (ii) one or both of geological or petrological relationships ([0002] discloses analysis of data identify and locate various subsurface structures (e.g., horizons, faults, geobodies, etc.) in a geologic environment., and various types of structures may be indicative of hydrocarbon traps or flow channels, as may be associated (i.e., various subsurface structures such as horizons, faults, geobodies indicate geological relationships - emphasis added by Examiner) with one or more reservoirs (e.g., fluid reservoirs); [0052] discloses FIG. 1 also shows the geologic environment 150 as optionally including equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159 (i.e., a substantially horizontal portion of a well that intersects with one or more fractures indicate geological relationships - emphasis added by Examiner)); and
one or more seismic images with respective nodes anchored at respective pixel locations for the respective objects ([0113] and [0116] disclose nodes or neurons may include layers and/or other features. Information can include coordinates of the point, which may be a pixel or a voxel of a seismic image dataset, which can include associated seismic information (e.g. , coordinates, amplitude, time, etc.). A series of selections can be associated with a particular structural feature of a subsurface region).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Salman into Cheng for the purpose of identifying and locating various subsurface structures such as horizons, faults, geobodies in a geologic environment in order to improve characterization of a subsurface region for purposes of resource extraction. This combination would improve in making a drilling operation of a subsurface region more accurate as to a borehole's trajectory where the bore hole is to have a trajectory that penetrates a reservoir.
Cheng does not explicitly teach automatically generating, using the analysis of the structured representation, one or more images for output on a display, the one or more images being based on the subsurface data and being generated to highlight at least one aspect of the structured representation representing the identified geologic and the fluid objects and the relationships among the identified geologic and the fluid objects.
Liu teaches automatically generating, using the analysis of the structured representation, one or more images for output on a display, the one or more images are on the subsurface data and being generated to highlight at least one aspect of the structured representation representing the identified geologic and the fluid objects and the relationships among the identified geologic and the fluid objects ([0007] and [0051] disclose extracting a feature probability volume by processing the geophysical data (see FIG. 2A), with one or more fully convolutional neural networks, which are trained to relate the geophysical data to at least one subsurface feature. The seismic image is then generated from this “faulted ” volume using wave propagation models or convolution models (see FIG. 3); and automatically interpret a subsurface feature within geophysical data; [0042] discloses fully convolutional neural networks is trained with image to image or volume to volume, and automatically detects and interprets subsurface features that can be highlighted using a contiguous region of pixels/voles in a seismic volume which are a subsurface feature, such as faults, channels, environments of deposition (i.e., geologic and the fluid objects - emphasis added by Examiner). The present technological advancement can work with stacked or migrated seismic data with or without additional attributes such as semblance, and the output of the method can be a feature probability volume that can then be further post-processed to extract objects that integrate into a subsurface interpretation workflow semblance; [0076]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Liu into Cheng in view of Salman for the purpose of analyzing of seismic or other geophysical subsurface imaging data using convolutional neural networks. This combination would improve in automatically detecting and interpreting subsurface features that can be highlighted using a contiguous region of pixels/voxels in a seismic volume.
As to claim 43, the combination of Cheng, Salman, and Liu teaches the claimed limitations as discussed in claim 1.
The combination of Cheng and Liu does not explicitly teach wherein the relationships comprise: (i) spatial relationships; and (ii) both of geological and petrological relationships.
Salman teaches wherein the relationships comprise: (i) spatial relationships ([0043] discloses seismic image data identify one or more faults in a geologic region., and identification of a fault can include determining one or more parameters or parameter values that characterize the fault, and consider fault location, position (i.e., location and position of fault indicates spatial relationships - emphasis added by Examiner), dimension(s), type of fault, etc.; [0086] discloses information may specifies one or more location coordinates (i.e., location coordinates indicate positional descriptors of spatial relationships - emphasis added by Examiner) of a feature in a geologic environment); and (ii) both of geological ([0002] discloses analysis of data identify and locate various subsurface structures (e.g., horizons, faults, geobodies, etc.) in a geologic environment., and various types of structures may be indicative of hydrocarbon traps or flow channels, as may be associated (i.e., various subsurface structures such as horizons, faults, geobodies indicate geological relationships - emphasis added by Examiner) with one or more reservoirs (e.g., fluid reservoirs); [0052]), and petrological relationships ([0027] discloses “The presence of a fault may be detectable by observing characteristics of rocks such as changes in lithology (i.e., changes in lithology or rocks characteristics indicates petrological relationships - emphasis added by Examiner) from one fault block to the next, breaks and offsets between strata or seismic events, and changes in formation pressure in wells that penetrate both sides of a fault.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Salman into Cheng in view of Liu for the purpose of identifying and locating various subsurface structures such as horizons, faults, geobodies in a geologic environment in order to improve characterization of a subsurface region for purposes of resource extraction. This combination would improve in making a drilling operation of a subsurface region more accurate as to a borehole's trajectory where the bore hole is to have a trajectory that penetrates a reservoir.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Cheng, Salman, and Liu, in view of Imhof et al. (US 20130064040, hereinafter Imhof).
As to claim 2, the combination of Cheng, Salman, and Liu teaches the claimed limitations as discussed in claim 1.
Cheng teaches wherein the structured representation is based on any of: graphs, embeddings, or a combination of graphs and embeddings ([0076] and [0078] disclose FIG. 5 is a diagram of a reservoir structure and a corresponding topological net, and a topological net is a data representation for relationships of reservoir compartments, similar in structure to a Reeb Graph. The topological net is represented as a graph with critical points 506 and poly segments 508 that connect the critical points 506, and each critical point in the topological net represents a minimum, maximum, or saddle point on the reservoir geometry. The relative spatial arrangement of the critical points can be displayed in the topological net);
wherein identifying geologic and fluid objects utilizes a domain expert's annotations or a geoscientific simulation ([0026] discloses “identifying critical points of the topological net by passing a plane of constant depth through the reservoir structure to obtain depth level contours and identifying locations where the depth level contours intersect. Furthermore, the structural data may comprise geological surfaces, seismic data, geological models, reservoir models, or some combination thereof.”);
wherein the geologic and fluid objects comprise any of: a geologic trap, a fault, a reservoir, a source rock, a geologic seal, and direct hydrocarbon indicators ([0080] discloses a potential compartment is a geological trap that is able to contain fluid such as gas, oil, and/or water, and various compartments can be readily identified based on the topological net 504 in FIG. 5. The locations of the geological traps depend on the density and pressure of the fluids, and since a base saddle critical point would allow the trapped oil/water break over from one trap to another trap, potential compartments can be identified by the reservoir regions separated by the base saddle location; [0084]);
wherein the relationships among the identified geologic and fluid objects comprise any of: geological relationships, geophysical relationships, and petrological relationships ([0024] discloses generating a topological net based on the structural data, and the topological net comprising critical points and poly segments connecting the critical points. The method includes identifying potential compartments of the reservoir structure based on the reservoirs geological structure, and also based on the topological net. The method also includes identifying spill or break-over relationships among the potential compartments based on the topological net; [0067]); further comprising:
determining object attributes from the subsurface data ([0104] discloses the topological net can be used to develop a compartment matrix that shows which compartments share a fluid column in original pressure communication, and since the topological net includes depth data and linkages to the compartment geometry, one can also mark the gas/oil/water contact movements and/or their pressures gradients (i.e., object attributes from the subsurface data) on the poly segments of the topological net to assist the production scale connectivity analysis); and
determining edge attributes from the subsurface data ([0076] discloses an edge connects nodes where each node is an abstraction of a level set contact on a given reservoir, and each edge contains attributes such as gas/oil/water pressure gradients within each reservoir regions),
wherein at least one edge attribute is related to a potential hydrocarbon migration path ([0076] and [0081] disclose an edge connects nodes where each node is an abstraction of a level set contact on a given reservoir. By analyzing the topological relation of the critical points on the topological net, the compartments, fluid contacts and their spill/break-over relations can be tracked, and the fluid contact movements (i.e., a potential hydrocarbon migration path) would be reflected in the level sets contours on the reservoir geometry).
The combination of Cheng and Liu does not explicitly teach wherein the at least one edge attribute comprises quantities measured along the potential hydrocarbon migration path.
Imhof teaches wherein the at least one edge attribute comprises quantities measured along the potential hydrocarbon migration path ([0164] discloses nodes of acyclic graphs represent random variables in the Bayesian sense which may be observable quantities, and edges represent conditional dependencies. Given the local geometry, the reservoir/seal system is assigned a trap score, and the trap is preferably filled with hydrocarbons, and thus, the trap score is then combined with scores for presence of a source and indications of at least potential for migration pathways that lead from the source to the trap).
It would have been obvious to one of ordinary skill in the art before the
effective filing date of the claimed invention to incorporate Imhof into Cheng in view of Salman and Liu for the purpose of detecting and ranking potential hydrocarbon opportunities using seismic data. This combination would improve in automatically analyzing seismic data for the presence of elements of the hydrocarbon system, and ranks these prospect regions with regard to their hydrocarbon accumulation potential so that hydrocarbon accumulations can be timely discovered.
Claims 10, 17, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Cheng, Salman, Liu, and Imhof, in view of Yarus et al. (US 20160170087, hereinafter Yarus).
As to claim 10, the combination Cheng, Salman, Liu, and Imhof teaches the claimed limitations as discussed in claim 2.
Cheng teaches automatically determining global attributes of the structured representation, automatically connecting the geologic and fluid objects to other related knowledge bases ([0024]; [0076] discloses FIG. 5 shows a whole reservoir structure (i.e., a global attribute – emphasis added by Examiner) which includes edges that contain attributes such as gas/oil/water pressure gradients within each reservoir regions, and critical point in the topological net represents a minimum, maximum, or saddle point on the reservoir geometry; [0105] discloses the geological model or earth model represents a three-dimensional representation of one or more potential reservoirs, and the model can be generated from various geological data and engineering data using computational, analytical, and interpretive methods such as seismic pattern recognition and expert analysis of the geological structure, rock properties, core samples (i.e., connecting the geologic and fluid objects to other related knowledge bases – emphasis added by Examiner), and the like);
automatically inferring information from the structured representation of the subsurface data ([0101]; [0102] discloses “Reconciling these interpretations enables one to determine an actual reservoir structure that best fits the geological data and production data. The actual reservoir structure can then be used to guide future production (i.e., inferring information from the structured representation of the subsurface data – emphasis added by Examiner)), for example, placement of new well bores, and the like.”); and
wherein automatically inferring information comprises at least one of the following: making an analog recommendation for hydrocarbon management; predicting a confidence of hydrocarbon presence in the subsurface region ([0102] discloses “Reconciling these interpretations enables one to determine an actual reservoir structure that best fits the geological data and production data. The actual reservoir structure can then be used to guide future production, for example, placement of new well bores, and the like.”; [0109]); geological reasoning; and prospect rating and ranking.
The combination of Cheng, Liu, and Imhof does not explicitly teach receiving the geological question from a user; and answering a geological question with a question answering system.
Yarus teaches receiving the geological question from a user ([0018] and [0030] disclose the CART-based proxy computations is performed by the management system, servers, or other network devices, and the user may submit information and parameters. The CART based determinations made by the logic answers any number of questions about the earth formation; i.e., the CART receives questions which would include from a user – emphasis added by Examiner); and
answering a geological question with a question answering system ([0009] and [0030] disclose the computer executable instructions for classification and regression tree (CART) (i.e., question answering system – emphasis added by Examiner) based determinations made by the logic answer any number of questions about the earth formation).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Yarus into Cheng in view of Salman, Liu and Imhof for the purpose of providing less extensive data, user and computing time, and utilizing less computational resources to arrive at accurate results for estimating natural resource reserves and production. Yarus does not explicitly teach automatically answering a geological question, however, Cheng teaches that potential compartments of a reservoir based on the reservoirs geological structure can be automatically identified (see Cheng, Abstract), and Liu teaches that a subsurface feature within geophysical data can be automatically detected and interpreted (see Liu, Abstract, [0042]). Thus, the combination of Cheng, Liu, Imhof, and Yarus would be able to automatically answers a geological question, and would improve in accurately predicting production estimation of natural resource reserves, production capabilities, and improving production schemes to extract wellbore fluids or gases from the formation.
As to claim 17, the combination of Cheng, Salman, Liu, Imhof, and Yarus teaches the claimed limitations as discussed in claim 10.
Cheng teaches wherein the structured representation is based on any of: graphs and embeddings ([0076] and [0078] disclose FIG. 5 is a diagram of a reservoir structure and a corresponding topological net, and a topological net is a data representation for relationships of reservoir compartments, similar in structure to a Reeb Graph. The topological net is represented as a graph with critical points 506 and poly segments 508 that connect the critical points 506, and each critical point in the topological net represents a minimum, maximum, or saddle point on the reservoir geometry. The relative spatial arrangement of the critical points can be displayed in the topological net),
The combination of Cheng, Imhof, and Yarus does not explicitly teach wherein extracting the structured representation utilizes a structured representation model; and wherein the structured representation model comprises a neural network.
Liu teaches wherein extracting the structured representation utilizes a structured representation model ([0007] discloses a method to automatically interpret a subsurface feature within geophysical data, and the method includes extracting a feature probability volume by processing the geophysical data with one or more fully convolutional neural networks (i.e., utilizes a structured representation model – emphasis added by Examiner), which are trained to relate the geophysical data to at least one subsurface feature); and
wherein the structured representation model comprises a neural network ([0007] discloses a method to automatically interpret a subsurface feature within geophysical data, and the method includes extracting a feature probability volume by processing the geophysical data with one or more fully convolutional neural networks (i.e., the structured representation model – emphasis added by Examiner), which are trained to relate the geophysical data to at least one subsurface feature).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Liu into Cheng in view of Salman, Imhof and Yarus for the purpose of analyzing of seismic or other geophysical subsurface imaging data using convolutional neural networks. This combination would improve in automatically detecting and interpreting subsurface features that can be highlighted using a contiguous region of pixels/voxels in a seismic volume.
As to claim 23, the combination of Cheng, Salman, Liu, Imhof, and Yarus teaches the claimed limitations as discussed in claim 17.
The combination of Cheng, Imhof, and Yarus does not explicitly teach wherein the neural network is a graph convolutional neural network.
Liu teaches wherein the neural network is a graph convolutional neural network
([0007] and [0015] disclose a method to automatically interpret a subsurface feature within geophysical data, and the method includes extracting a feature probability volume by processing the geophysical data with one or more fully convolutional neural networks which are trained to relate the geophysical data to at least one subsurface feature; FIGs. 3 and 9 show graphs of convolution neural networks or models).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Liu into Cheng in view of Salman, Imhof, and Yarus for the purpose of analyzing of seismic or other geophysical subsurface imaging data using convolutional neural networks. This combination would improve in automatically detecting and interpreting subsurface features that can be highlighted using a contiguous region of pixels/voxels in a seismic volume.
Claims 24, and 27-28 are rejected under 35 U.S.C. 103 as being unpatentable over Cheng, Salman, Liu, Imhof, and Yarus, in view of Roy et al. (US 20200088897, hereinafter Roy), and further in view of Bas et al. (US 20140278115, hereinafter Bas).
As to claim 24, the combination of Cheng, Salman, Liu, Imhof, and Yarus teaches the claimed limitations as discussed in claim 23.
The combination of Cheng, Imhof, and Yarus does not explicitly teach automatically sequentially identifying the geologic and fluid objects and the relationships utilizing a neural network decoding sequential creation of the geologic and fluid objects.
Liu teaches automatically sequentially identifying the geologic and fluid objects and the relationships utilizing a neural network decoding sequential creation of the geologic and fluid objects ([0007] discloses a method to automatically interpret a subsurface feature within geophysical data, and the method includes extracting a feature probability volume by processing the geophysical data with one or more fully convolutional neural networks which are trained to relate the geophysical data to
at least one subsurface feature (i.e., utilizing a neural network decoding sequential creation of the geologic and fluid objects)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Liu into Cheng in view of Salman, Imhof and Yarus for the purpose of analyzing of seismic or other geophysical subsurface imaging data using convolutional neural networks. This combination would improve in automatically detecting and interpreting subsurface features that can be highlighted using a contiguous region of pixels/voxels in a seismic volume.
The combination of Cheng, Liu, Imhof, and Yarus does not explicitly teach a recurrent neural network decoding sequential creation of the geologic and fluid objects.
Roy teaches utilizing a recurrent neural network decoding sequential creation of the geologic and fluid objects ([0013] discloses deep learning computational models like Convoluted Neural Networks (CNN) and/or a Recurrent Neural Networks (RNN) can implement deep structures; and a properly trained deep learning model can receive seismic attributes of a well and then infer/predict the reservoir properties of the well based on the received seismic attributes (i.e., decoding sequential creation of the geologic and fluid objects – emphasis added by Examiner)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Roy into Cheng in view of Salman, Liu, Imhof, and Yarus for the purpose of analyzing relationship between seismic attributes and reservoir properties using machine learning. This combination would improve in generating more effective and accurate predictions of the well's reservoir properties, and generating a representation of the reservoir properties of the relevant subsurface region.
The combination of Cheng, Imhof, Yarus, Liu, and Roy does not explicitly teach automatically modeling the objects based on spatial relationships.
Bas teaches automatically modeling the objects based on spatial relationships ([0079] discloses “According to a graphical model, the distributions can be factored to model the contextual relationships.”; [0109]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Bas into Cheng in view of Salman, Liu, Imhof, Yarus, and Roy for the purpose of analyzing seismic and other data in order to identify features of interest of subsurface formations. This combination would provide a system that imitates the decision making of a human expert using geophysical concepts and expert knowledge, and jointly utilizes machine inference and expert feedback to simultaneously analyze multiple seismic attributes.
As to claim 27, the combination of Cheng, Salman, Liu, Imhof, Yarus, Roy, and Bas teaches the claimed limitations as discussed in claim 24.
Cheng teaches wherein the subsurface data comprises one or more of the following: seismic images; electromagnetic images; well measurements; analog data; knowledge bases; related geological and petrological information; and related field performance data ([0102] discloses The geological data and production data can include, rock types, fluid properties, pressure profiles such as shown in FIG. 4, actual flow rates, and the like. Reconciling these interpretations enables one to determine an actual reservoir structure that best fits (i.e., well measurements – emphasis added by Examiner) the geological data and production data; [0103] discloses All of the potential compartments 1002 pertaining to a reservoir may be included in the connectivity diagram, including system exit points, leak points, and spill points for gas, oil, and water (i.e., related geological and petrological information – emphasis added by Examiner); FIGs. 4 and 5 show seismic images).
As to claim 28, the combination of Cheng, Salman, Liu, Imhof, Yarus, Roy, and Bas teaches the claimed limitations as discussed in claim 27.
Cheng teaches wherein the subsurface data additionally includes auxiliary information pertaining the subsurface region ([0104] discloses based on the data provided by the topological net, graph analysis algorithms such as shortest path and maximum flow algorithms could be used to derive additional information about reservoir connectivity (i.e., additional auxiliary information pertaining the subsurface region – emphasis added by Examiner), such as the location of weak links among connected compartments or the locations to inject water in order to increase the production);
wherein the auxiliary information comprises text documents ([0104] discloses “the three-dimensional shared earth model can be used to annotate (i.e., annotating involves writing in text document form – emphasis added by Examiner) the topological net together with the three-dimensional representation of the reservoir geometry for interactive visualization and processing of the RCA/DCA models.”); and
wherein related field performance data comprises one or more of oil-in-place, gas-oil-ratio, production rates, and a recovery factor ([0102] discloses The geological data and production data can include, rock types, fluid properties, pressure profiles such as shown in FIG. 4, actual flow rates, and the like. Reconciling these interpretations enables one to determine an actual reservoir structure that best fits the geological data and production data; and the actual reservoir structure can then be used to guide future production (i.e., future production would include oil-in-place – emphasis added by Examiner), for example, placement of new well bores).
Claim 31 is rejected under 35 U.S.C. 103 as being unpatentable over Cheng, Salman, and Liu, in view of Yarus.
As to claim 31, the combination of Cheng, Salman, and Liu teaches the claimed limitations as discussed in claim 1.
Cheng teaches wherein the subsurface data comprises seismic data; wherein the seismic data is used to generate a mapping image of a subsurface region ([0026] discloses obtaining depth level sets of the structural data from a real value function that maps to depths ranging from minimum depth to maximum depth of
the structural data, and the structural data may comprise geological surfaces, seismic
data, geological models, reservoir models, or some combination thereof);
wherein automatically generating the one or more images comprises automatically placing one or more overlays, using the structured representation, on the mapping image of the subsurface region ([0029] discloses generate the poly segment by obtaining depth level sets of the structural data from a real value function that maps to depths ranging from minimum depth to maximum depth of the structural data, and the system includes a visualization engine configured to provide a visual display of a reservoir and overlay the topological net over the visual display of the reservoir; [0091] discloses the critical points used to construct the topological net 712 are used to automatically identify the potential reservoir compartments, and the depth area bounded by the critical points 714 and 718 is identified as a potential reservoir compartment 720, which is shown in FIG. 7E as a slant-pattern shaded area, and the depth area bounded by the critical points 712 and 718 is identified as a potential reservoir compartment 722, which is shown in FIG. 7E as a vertical-pattern shaded area).
The combination of Cheng and Liu does not explicitly teach receiving at least one question related to one or more aspects of the subsurface region; and wherein automatically generating the one or more images comprises automatically placing one or more overlays, using the structured representation, on the mapping image of the subsurface region in order to answer the at least one question related to one or more aspects of the subsurface region.
Yarus teaches receiving at least one question related to one or more aspects of the subsurface region ([0022] discloses “The CART based proxy analysis may be utilized to answer questions regarding porosity, reservoir composition oil saturation, gas saturation, water saturation, and so forth.”); and
automatically placing one or more overlays on the mapping image of the subsurface region in order to answer the at least one question related to one or more aspects of the subsurface region ([0017] discloses one or more sensors or logging tools such as probes, drill string measurement devices, nuclear magnetic resonance imagers (i.e., nuclear magnetic resonance imagers would generate images - emphasis added by Examiner), etc. may be integrated with or connected to the mobile computing system 124 to perform logging, data retrieval, data storage, processing, and information display; [0030] discloses the CART based determinations made by the logic may answer any number of questions, such as is the porosity above 8% for an earth formation or a designated portion of the earth formation, is the water saturation above 50%, is there a shale barrier).
It would have been obvious to one of ordinary skill in the art before the
effective filing date of the claimed invention to incorporate Yarus into Cheng in view of Salman and Liu for the purpose of providing less extensive data, user and computing time, and utilizing less computational resources to arrive at accurate results for estimating natural resource reserves and production. This combination would improve in accurately predicting production estimation of natural resource reserves, production capabilities, and improving production schemes to extract wellbore fluids or gases from the formation.
Claims 32-33 are rejected under 35 U.S.C. 103 as being unpatentable over Cheng, Salman, Liu, and Yarus, in view of Goel et al. (US 20100332442, hereinafter Goel).
As to claim 32, the combination of Cheng, Salman, Liu, and Yarus teaches the claimed limitations as discussed in claim 31.
Cheng teaches wherein the structured representation comprises a graph; wherein the graph includes a plurality of the nodes corresponding to the identified geologic and the fluid objects ([0076] and [0078] disclose FIG. 5 is a diagram (i.e., graph – emphasis added by examiner) of a reservoir structure and a corresponding topological net, and a topological net is a data representation for relationships of reservoir compartments, similar in structure to a Reeb Graph. The topological net is represented as a graph with critical points 506 and poly segments 508 that connect the critical points 506, and each critical point in the topological net represents a minimum, maximum, or saddle point on the reservoir geometry (i.e., the graph includes a plurality of the nodes corresponding to the identified geologic and the fluid objects– emphasis added by examiner). The relative spatial arrangement of the critical points can be displayed in the topological net);
wherein the graph includes the edges that connect the plurality of the nodes and indicate the relationship between respective nodes (FIG. 5; FIG. 7D and 7E); and
wherein the one or more overlays are automatically placed on the mapping image of the subsurface region to indicate both of at least one of the plurality of nodes and at least one of the edges (FIG. 5; FIGs. 7D and 7E show the mapping image of the subsurface region indicates both of at least one of the plurality of nodes and at least one of the edges; [0029] discloses generate the poly segment by obtaining depth level sets of the structural data from a real value function that maps to depths ranging from minimum depth to maximum depth of the structural data, and the system includes a visualization engine configured to provide a visual display of a reservoir and overlay the topological net over the visual display of the reservoir).
The combination of Cheng, Salman, Liu, and Yarus does not explicitly teach
wherein the graph is based on a probability distribution.
Goel teaches a graph, wherein the graph is based on a probability distribution (FIGs. 1, 2, and 3, [0011]).
It would have been obvious to one of ordinary skill in the art before the
effective filing date of the claimed invention to incorporate Goel into Cheng in view of Salman, Liu, and Yarus for the purpose of taking uncertainty into consideration in reservoir development planning of oil and gas production, in order to solve uncertainty in data which is represented by probability distribution functions. This combination would provide optimization in reservoir behavi