CTNF 18/412,203 CTNF 78412 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 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, 5-13, 16, 17 and 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (abstract idea) without significantly more. Under Step 1 of the 2019 Revised Patent Subject Matter Eligibility Guidance, the claims are directed to a process (claim 1, a method) or a machine (claim 16, a system) which are statutory categories. However, evaluating claim 1 , under Step 2A , Prong One , the claim is directed to the judicial exception of an abstract idea using the grouping of a mathematical relationship/mental process. The limitations include: generating, using the seismic processing system and statistical sampling, a plurality of pilot waveforms based on the plurality of time-space waveforms; forming, using the seismic processing system, a training seismic dataset comprising an input training dataset and an output training dataset, wherein the input training dataset is based on the plurality of time-space waveforms and the output training dataset is based on the plurality of pilot waveforms; and training, using the seismic processing system and the training seismic dataset, a machine- learning (ML) model to predict the output training dataset, at least in part, from the input training dataset. These limitations recite mathematical calculations, statistical analysis, data evaluation, and mathematical model training operations that can be practically performed in the human mind or using generic computer implementation, including organizing information, selecting representative data, generating datasets, and mathematically training a predictive model. The claim merely uses a genetic seismic processing system as a tool to automate the abstract mathematical operations and does not improve computer functionality, seismic acquisition technology, or another technology field. The examiner notes that the element “a machine- learning (ML) model to predict the output training dataset” is considered performing mathematical calculation which falls within the “mathematical concept” grouping of abstract ideas (see Example 47, in the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence). Next , Step 2A , Prong Two evaluates whether additional elements of the claim “integrate the abstract idea into a practical application” in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the exception. The claim does not recite additional elements that integrate the judicial exception into a practical application. The claim recites additional elements “a seismic processing system”, “a seismic acquisition system”, “seismic data”, “time-space waveforms”, and “a subsurface region of interest”. These additional elements merely represent generic computer components and field-of-use limitations that apply the abstract idea in the environment of seismic data processing. The claim does not recite any specific improvement to seismic acquisition technology, seismic imaging technology, computer functionality, or machine operation. The claim does not recite improving signal-to-noise ratio, improving seismic image quality, reducing seismic artifacts, or any other technological improvement. Instead, the claim merely uses generic computer systems as tools to receive data, perform statistical sampling, organize datasets, and train a machine-learning model. The claimed “pilot waveforms” are merely manipulated data and do not impose any meaningful limitation on the abstract idea. Further, the claim does not recite a particular machine integral to the claim, as the “seismic processing system” and “seismic acquisition system” are recited at a high level of generality and perform only generic data acquisition and processing functions. The claim also does not effect a transformation of an article into a different state or things as the claimed operations merely manipulate and analyze data. This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform the abstract ideas. As set forth in the 2019 Eligibility Guidance, 84 Fed. Reg. at 55 “merely include[ing] instructions to implement an abstract idea on a computer” is an example of when an abstract idea has not been integrated into a practical application Therefore, the claims are directed to an abstract idea. At Step 2B , consideration is given to additional elements that may make the abstract idea significantly more. Under Step 2B , there are no additional elements that make the claim significantly more than the abstract idea. The additional elements of “receiving, by a seismic processing system from a seismic acquisition system, seismic data regarding a subsurface region of interest, wherein the seismic data comprises a plurality of time-space waveforms” is considered insignificant extra-solution activity of collecting data that is not sufficient to integrate the claim into a particular practical application. The act of data gathering is considered insufficient to elevate the claim to a practical application. The limitations have been considered individually and as a whole and do not amount to significantly more than the abstract idea itself. Dependent claims 2 and 5-13 do not add anything which would render the claimed invention a patent eligible application of the abstract idea. The claim merely extends (or narrow) the abstract idea which do not amount for "significant more" because it merely adds details to the algorithm which forms the abstract idea as discussed above. Claim 16 is rejected 35 USC § 101 for the same rationale as in claim 1. Dependent claims 17 and 20 do not add anything which would render the claimed invention a patent eligible application of the abstract idea. The claim merely extends (or narrow) the abstract idea which do not amount for "significant more" because it merely adds details to the algorithm which forms the abstract idea as discussed above. The limitations have been considered individually and as a whole and do not amount to significantly more than the abstract idea itself. Claims 3, 4, 14, 15, 18 and 19 are considered eligible under 35 USC 101. Claims 3, 4, 18 and 19 integrate the mathematical and machine-learning operations into a specific technological workflow involving seismic imaging, drilling-target determination, wellbore trajectory, and physical drilling operations, rather than merely manipulating data. Thes claims apply the processed seismic information to control or guide a real-world industrial process in the field of hydrocarbon exploration and drilling. Claims 14 and 15 recite iterative seismic waveform refinement tied to signal-quality improvement using a signal-to-noise ratio threshold, thereby reciting a technological objective and improvement to seismic signal processing rather than generic data analysis. Claim Rejections - 35 USC § 103 07-20-aia AIA 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, 7, 9-12, 16 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Salman et al. (Pub. No. US 20190383965) (hereinafter Salman) in view of Zhu et al. (NPL: “ Seismic Facies Analysis Using the Multiattribute SOM-K-Means Clustering ”, Hindawi (2022)) (hereinafter Zhu). As per claims 1, 9 and 16 , Salman teaches receiving, by a seismic processing system from a seismic acquisition system, seismic data regarding a subsurface region of interest (see Abstract and ¶¶ [0002], [0034]-[0035]), wherein the seismic data comprises a plurality of time-space waveforms (see ¶ [0068], i.e., “1D seismic trace, which may be a series of amplitude values for a series of time values”); Salman further teaches “training a deep learning framework” using generated seismic data (see ¶ [0067], i.e. “deep learning applied to seismic trace data can operate at the level of the time series (e.g., amplitude with respect to time, etc.)”). Salman additionally teaches generating synthetic and semi-synthetic seismic datasets for ML training, including “generate synthetic data” (see ¶ [0106]), “semi-synthetic training data collections” and “multiply a limited collection of existing training data into one or more sets of semi-synthetic training data collections” (see ¶ [0079]). Salman additionally teaches training a deep learning framework using generated synthetic geophysical data and subsequently applying the trained framework to acquired geophysical data to generate interpretation results (i.e., predict the output) (see ¶¶ [0003] and [0100]). Salman further teaches implementing the trained framework to generate interpretation results from acquired seismic data (see Abstract and ¶¶ [0033]-[0037]). However, Salman does not explicitly teach generating a plurality of pilot waveforms using statistical sampling from the plurality of time-space waveforms, nor does Salman explicitly disclose forming an output training dataset that is based on such statistically selected pilot waveforms. Zhu, however, teaches clustering seismic traces into representative groups and generating representative/centroid traces from clustered seismic attributes using SOM and k-means clustering, including reducing redundancy while preserving representative seismic variability (see pages 2-10, sections 2. Related Work , section 3. SOM-K-Means Clustering for SFA , and section 4. Seismic Facies Analysis Experiments , discussing SOM clustering, k-means clustering, representative facies clusters, centroid generation, and representative seismic attributes). Such representative clustered traces would have suggested pilot waveforms generated from a larger population of seismic waveforms and statistically selected to represent the variability of the seismic dataset. Zhu further teaches using such representative clustered traces as waveform exemplars of the clustered seismic data (see page 3. Section 3. SOM-K-Means Clustering for SFA ). It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to use the representative clustered traces of Zhu as the output training dataset and the original seismic traces seismic traces as the input training dataset when training the deep learning framework of Salman, because supervised machine learning models are conventionally trained to learn a mapping between input examples and representative target outputs and because representative clustering and statistical sampling reduce redundancy while preserving characteristic waveform variability, thereby enabling the trained model to predict representative or conditioned seismic waveforms from acquired seismic waveforms while improving machine learning training efficiency, robustness, and generalization capability for seismic waveform prediction and conditioning. As per claims 7 and 20 , the combination of Salman and Zhu teaches the system as stated above. Salman further teaches generating synthetic and semi-synthetic seismic datasets and multiplying existing seismic training data generated waveform datasets (see ¶¶ [0078]-[0079] and [0106]). However, Salman does not explicitly teach forming bins of waveforms, generating virtual waveforms from combinations of waveforms within each bin, and generating pilot waveforms using statistical sampling from the virtual waveforms. Zhu, however, teaches grouping seismic traces into representative clusters/bins and generating representative /centroid traces from combinations of traces within each cluster (see pages 2-10, sections 2. Related Work , section 3. SOM-K-Means Clustering for SFA , and section 4. Seismic Facies Analysis Experiments , discussing SOM clustering, k-means clustering, representative facies clusters, centroid generation, and representative seismic attributes). It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention generate virtual representative waveforms from clustered seismic bins and statistically sample representative pilot waveforms because representative clustering and centroid generation reduce redundancy while preserving representative waveform diversity, thereby improving ML training robustness and computational efficiency. As per claims 10-12 , the combination of Salman and Zhu teaches the system as stated above. Salman teaches training deep learning frameworks using generated and acquired seismic datasets (see Abstract and ¶¶ [0078]-[0079]). The combination of Salman and Zhu, however, does not explicitly disclose dividing the seismic datasets into separate training, testing, and validation partitions. Partioning datasets into training, testing, and validation subsets is well known in machine learning model development before the effective filling date of the claimed invention. It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to partition the seismic datasets intotraining, testing, and validation datasets because separate datasets are conventionally used to train, test, and validate ML model performance and avoid overfitting, thereby improving predictive reliability and model accuracy. Claims 2-5, 8, 14 and 15, 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Salman in view of Zhu and further in view of Moldoveanu (Pub. No. US 2022/0066061). As per claims 2 and 17 , the combination of Salman and Zhu teaches the system as stated above except for predicting, a plurality of filtered time-space waveforms based, at least in part, on the plurality of time-space waveforms using the trained ML model. Moldoveanu, however, teaches applying a noise mitigation process to seismic traces to reduce noise in the seismic data and generating improved seismic data through wavefield reconstruction (see Abstract and ¶¶[0062]-[0080]). The noise-mitigated traces produced by Moldoveanu constitute filtered seismic waveforms derived from the original seismic waveforms. It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to configure the trained deep learning framework of the combination of Salman and Zhu to predict filtered seismic waveforms as taught by Moldoveanu because noise mitigation and waveform filtering improve the quality of seismic data used for subsequent interpretation and analysis, thereby improving the accuracy and reliability of the interpretation results generated from acquired seismic data. As per claims 3 and 18 , the combination of Salman and Zhu teaches the system as stated above except for forming, by the seismic processing system, a seismic image based, at least in part, on the plurality of filtered time-space waveforms; and determining, by a seismic interpretation system, a drilling target in the subsurface region based on the seismic image. Moldoveanu, however, teaches applying a noise mitigation process to seismic traces, mitigating noise in identified traces, and generating improved seismic data through wavefield reconstruction (see Abstract and ¶¶ [0004] and [0062]-[0080]), thereby teaching filtered time-space waveforms. Moldoveanu further teaches generating stack volumes and seismic images from noise-mitigated and reconstructed seismic data for interpretation of subsurface structures (see ¶ [0004] and discussion of first and second stack volumes following noise mitigation and wavefield reconstruction). However, the combination does not explicitly disclose determining a drilling target based on the seismic image. Salman teaches generating interpretation results for geologic environment from acquired geophysical data using a trained deep learning framework (see Abstract and ¶¶ [0033]-[0037]), where such interpretation results are used to support exploration and operational decisions (see ¶¶ [0027] and [0100]). It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to utilize the seismic image generated from the filtered seismic waveforms of Moldoveanu to identify a drilling target within the subsurface region because seismic images are conventionally interpreted to identify subsurface structures and hydrocarbon-bearing formations suitable for drilling, thereby improving drilling target selection and effectiveness of subsequent exploration and production operations. As per claims 4 and 19 , the combination of Salman and Zhu teaches the system as stated above except for planning, using a wellbore planning system, a planned wellbore trajectory to intersect the drilling target in the subsurface region using the seismic image; and drilling, using a drilling system, a portion of a wellbore guided by the planned wellbore trajectory. Moldoveanu, however, teaches that seismic images and seismic interpretation results may be used in hydrocarbon exploration workflows, including identifying subsurface targets and planning drilling operations. For example, ¶ [0036] discusses utilizing the processed seismic information in exploration and development activities, and ¶ [0038] discusses use of the seismic processing results for drilling-related planning and decision making. It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to use the seismic generated from filtered waveforms and interpreted drilling target to plan a wellbore trajectory and drill a wellbore toward the target because seismic imaging is routinely performed to identify subsurface targets and guide well placement decisions, thereby improving drilling efficiency, target interpretation accuracy, and hydrocarbon recovery. As per claim 5 , the combination of Salman and Zhu teaches the system as stated above except that the plurality of time-space waveforms is ordered based on a seismic parameter. Moldoveanu, however, teaches seismic traces associated with seismic survey parameters including source locations, receiver locations, streamer-array configurations streamer depths, and reflection-point locations (see ¶¶ [0057]-[0061]). However, Moldoveanu does not explicitly disclose ordering the plurality of time-spaced waveforms based on a seismic parameter. It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to organize or order the seismic waveforms according to such seismic parameters because seismic processing workflows routinely sort and arrange seismic traces according to acquisition-related parameters to facilitate subsequent processing, reconstruction, and analysis, thereby improving processing efficiency and consistency of the seismic dataset. As per claim 8 , the combination of Salman and Zhu teaches the system as stated above except for generating a plurality of virtual waveforms comprises applying alignment and amplitude correction to each time-space waveform of each bin. Moldoveanu, however, teaches aligning and scaling seismic measurements for comparison and verification of properties (see ¶ [0048]), wherein scaling constitutes amplitude adjustment or amplitude correction of the seismic measurements. Moldoveanu further teaches applying correction operations to seismic traces, including receiver motion correction and other preprocessing operations prior to subsequent seismic processing (see ¶ [0062]). Accordingly, Moldoveanu teaches alignment and amplitude-related correction of seismic waveforms. However, Moldoveanu does not explicitly disclose applying the alignment and amplitude correction to each waveform of a bin during generation of virtual waveforms. As discussed above, Zhu teaches grouping seismic traces into representative clusters and generating representative traces from grouped seismic data. It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to apply the alignment and amplitude-scaling operations taught by Moldoveanu to the grouped waveforms of Zhu before generating representative virtual waveforms because alignment and amplitude normalization improve waveform consistency and coherence among traces being combined, thereby improving the quality and representativeness of the generated virtual waveforms. 07-21-aia AIA Claim 6 are rejected under 35 U.S.C. 103 as being unpatentable over Salman in view of Zhu and further in view of Moldoveanu and Luo et al. (Pub. No.US 2020/0018149) (hereinafter Luo). As per claim 6 , the combination of Salman, Zhu and Moldoveanu teaches the system as stated above except that the seismic parameter is an azimuth. Luo, however, teaches obtaining directional information using polarization analysis, including “back-azimuth projection” (see ¶ [0146]). Back-azimuth-based seismic parameter used to characterize the directionality of seismic arrivals. It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to use azimuth as seismic parameter because azimuth-based organization preserves directional information contained in seismic measurements, thereby improving subsequent seismic processing and interpretation . 07-21-aia AIA Claim 13 are rejected under 35 U.S.C. 103 as being unpatentable over Salman in view of Zhu and further in view of Bodo et al. (NPL: “Active Learning with Clustering”, JMLR: Workshopand Conference Proceedings 16 (2011) (hereinafter Bodo). As per claim 13 , the combination of Salman, Zhu and Moldoveanu teaches the system as stated above except that statistical sampling comprises diversity criteria heuristics. As discussed above, Zhu teaches selecting representative clustered seismic data that preserve variability across the dataset while reducing redundancy. Bodo, teaches heuristics selection of samples based on information content, clustering, and version-space reduction (see pages 127-128, paragraphs 4-5 and page 132, 1 st paragraph). It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to employ heuristic selection of representative clustered seismic waveforms because representative cluster-based selection improves coverage of waveform population while reducing redundant samples, thereby implementing diversity-oriented statistical sampling and improving training efficiency and model robustness. Allowable Subject Matter 07-43 Claims 14 and 15 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Regarding claim 14 , none of the prior art of record teaches or fairly suggests a method including the steps of: iteratively or recursively, until a stopping condition is reached: generating a plurality of updated pilot waveforms based, at least in part, on the plurality of filtered time-space waveforms; training the ML model using the training seismic dataset, wherein the training seismic dataset comprising an input training dataset and an output training dataset, wherein the input training dataset is based on the plurality of filtered of time-space waveforms and the output training dataset is based on the plurality of updated pilot waveforms; and updating the plurality of filtered time-space waveforms based, at least in part, on the trained ML model, in combination with the rest of the claim limitations as claimed and defined by the applicant. Prior art 07-96 The prior art made record and not relied upon is considered pertinent to applicant’s disclosure: Li et al. [‘436] discloses a process for producing hydrocarbons from a subterranean reservoir selecting a subterranean formation for hydrocarbon production; designing a seismic survey to image the subterranean formation; acquiring raw data using seismic sources and receivers; obtaining raw data (d) from a seismic survey; estimating the stacked image ({tilde over (m)}) with mitigated artifacts; demigrating the data from the stacked image ({tilde over (m)}) to attain a clean reference; building a reference from the demigrated data; solving an unsupervised dictionary learning problem; resolving a dual-domain sparse inversion to leverage sparsity and guide attenuating noise of the raw input data (d); inverting simultaneously the dual-domain sparse inversion to reduce noise; comparing a direct demigration to the learned inversion to obtain denoised data with a proper amplitude versus offset; and constructing a well in said subterranean reservoir to produce hydrocarbons. Kaul et al. [‘983] discloses a method for determining a top of salt (TOS) surface in a seismic volume based on a crossline direction of the seismic volume and an inline direction of the seismic volume. The method also includes determining a binary mask based upon the TOS surface. The method also includes sampling seismic data in the seismic volume to obtain a training seismic slice. The method also includes sampling the binary mask to obtain a mask slice. The method also includes selecting a first coordinate in the training seismic slice to produce a first tile. The method also includes selecting a second coordinate in the mask slice to produce a second tile. The method also includes generating or updating a model of the seismic volume based upon the first tile and the second tile. Wang et al. [‘594] discloses a method for seismic imaging including image enhancement using a trained neural network. The neural network may receive training pairs of low signal-to-noise ratio 3D seismic images and high signal-to-noise ratio 3D seismic images; train a neural network on the training pairs wherein the training uses atrous convolution; receive a seismic image representative of a subsurface volume of interest; apply the neural network to the seismic image to generate a second seismic image; and display the second seismic image on a graphical user interface. The method is executed by a computer system. Contact information Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOHAMED CHARIOUI whose telephone number is (571)272-2213. The examiner can normally be reached Monday through Friday, from 9 am to 6 pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Schechter can be reached on (571) 272-2302. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. 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. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). Mohamed Charioui /MOHAMED CHARIOUI/Primary Examiner, Art Unit 2857 Application/Control Number: 18/412,203 Page 2 Art Unit: 2857 Application/Control Number: 18/412,203 Page 3 Art Unit: 2857 Application/Control Number: 18/412,203 Page 4 Art Unit: 2857 Application/Control Number: 18/412,203 Page 5 Art Unit: 2857 Application/Control Number: 18/412,203 Page 6 Art Unit: 2857 Application/Control Number: 18/412,203 Page 7 Art Unit: 2857 Application/Control Number: 18/412,203 Page 8 Art Unit: 2857 Application/Control Number: 18/412,203 Page 9 Art Unit: 2857 Application/Control Number: 18/412,203 Page 10 Art Unit: 2857 Application/Control Number: 18/412,203 Page 11 Art Unit: 2857 Application/Control Number: 18/412,203 Page 12 Art Unit: 2857 Application/Control Number: 18/412,203 Page 13 Art Unit: 2857 Application/Control Number: 18/412,203 Page 14 Art Unit: 2857 Application/Control Number: 18/412,203 Page 15 Art Unit: 2857 Application/Control Number: 18/412,203 Page 16 Art Unit: 2857 Application/Control Number: 18/412,203 Page 17 Art Unit: 2857 Application/Control Number: 18/412,203 Page 18 Art Unit: 2857
Prosecution Insights