Prosecution Insights
Last updated: November 20, 2026
Application No. 18/679,780

AUTOMATING THE PARAMETRIZATION OF MULTI-STAGE ITERATIVE SOURCE SEPARATION WITH PRIORS USING MACHINE-LEARNING

Non-Final OA §103
Filed
May 31, 2024
Priority
Jun 01, 2023 — IN 202311037870
Examiner
NYAMOGO, JOSEPH A
Art Unit
2858
Tech Center
2800 — Semiconductors & Electrical Systems
Assignee
Schlumberger Technology Corporation
OA Round
1 (Non-Final)
67%
Grant Probability
Favorable
1-2
OA Rounds
8m
Est. Remaining
96%
With Interview

Examiner Intelligence

Grants 67% — above average
67%
Career Allowance Rate
98 granted / 146 resolved
-0.9% vs TC avg
Strong +28% interview lift
Without
With
+28.5%
Interview Lift
resolved cases with interview
Typical timeline
3y 1m
Avg Prosecution
25 currently pending
Career history
180
Total Applications
across all art units

Statute-Specific Performance

§101
1.9%
-38.1% vs TC avg
§103
78.9%
+38.9% vs TC avg
§102
14.9%
-25.1% vs TC avg
§112
4.0%
-36.0% vs TC avg
Black line = Tech Center average estimate • Based on career data from 146 resolved cases

Office Action

§103
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 . Priority Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. INDIA 202311037870, filed on June 1, 2023. Information Disclosure Statement The information disclosure statement (IDS) submitted on June 11, 2025 and December 17, 2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. 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. Claim(s) 1 – 5, 7 – 13, and 15 – 17 are rejected under 35 U.S.C. 103 as being unpatentable over LIU et al. (US 2020/0183035 A1) (herein after Liu) in view of Alwon (US 2019/0302290 A1) (herein after Alwon). Regarding Claim 1, Liu discloses, 1. A method for processing seismic data (Fig. 1, ¶ 26 data received and/or recorded as part of the seismic surveying process), — Liu fails to disclose, — comprising: receiving blended seismic data from at least one seismic source; applying a sparsity promoting transform domain to the received blended seismic data to differentiate a primary signal from interference and background noise; isolating the primary signal from the interference and background noise by selecting a threshold value in the sparsity promoting transform domain using a machine learning model, wherein the primary signal represents unblended seismic data; and removing the interference and background noise from the unblended seismic data to produce modified seismic data. In analogous art, Alwon discloses, — comprising: receiving blended seismic data from at least one seismic source (Fig. 4, ¶ 74 seismic data include blended seismic data); applying a sparsity promoting transform domain (Fig. 5, ¶ 82 convert seismic data of one or more of different domains, such as, for example, the FK or Radon domains) to the received blended seismic data to differentiate a primary signal (Fig. 1, ¶ 30 enhanced signal) from interference and background noise (Fig. 1, ¶ 30 noise may be subject to attenuation); isolating the primary signal from the interference and background noise by selecting a threshold value (Fig. 1, ¶ 35 noise attenuation) in the sparsity promoting transform domain using a machine learning model (Fig. 1, ¶ 35 machine learning techniques), wherein the primary signal represents unblended seismic data (Fig. 1, ¶ 89 enhance seismic data); and removing the interference and background noise from the unblended seismic data to produce modified seismic data (Fig. 7, ¶ 87 enhance signal). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu by combining the method for processing seismic data disclosed by Liu with a method for processing seismic data comprising: receiving blended seismic data from at least one seismic source; applying a sparsity promoting transform domain to the received blended seismic data to differentiate a primary signal from interference and background noise; isolating the primary signal from the interference and background noise by selecting a threshold value in the sparsity promoting transform domain using a machine learning model, wherein the primary signal represents unblended seismic data; and removing the interference and background noise from the unblended seismic data to produce modified seismic data; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 2, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu fails to disclose, 2. The method of claim 1 wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio relative to a predetermined value. Alwon further discloses, 2. The method of claim 1 wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio (Fig. 13, ¶ 149 level of signal to noise (e.g., SNR)) relative to a predetermined value (Fig. 13, ¶ 149 which is greater than that of "noisy" data). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the method for processing seismic data disclosed by Liu in view of Alwon with a method for processing seismic data wherein, the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio relative to a predetermined value; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 3, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu fails to disclose, 3. The method of claim 1 wherein selecting the threshold value is based at least partially upon multiple independent applications of the sparsity promoting transform domain to the received blended seismic data. Alwon further discloses, 3. The method of claim 1 wherein selecting the threshold value is based at least partially upon multiple independent applications (Fig. 6, ¶ 81 learning various filters and passing them through a network with several layers) of the sparsity promoting transform domain to the received blended seismic data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the method for processing seismic data disclosed by Liu in view of Alwon with a method for processing seismic data wherein, selecting the threshold value is based at least partially upon multiple independent applications of the sparsity promoting transform domain to the received blended seismic data; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 4, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu further discloses, 4. The method of claim 1 wherein isolating the primary signal from the interference and background noise by selecting a threshold value (Fig. 1, ¶ 38 optimization process) in the sparsity promoting transform domain using the machine learning model comprises using a machine learning model comprising a convolutional neural network (CNN) (Fig. 1, ¶ 41 Fully Convolutional Neural Networks) in which a classification head (Fig. 1, ¶ 81 task of classification) and a regression head (Fig. 1, Claim 28 using interpolation or extrapolation) share weights (Fig. 1, ¶ 38 e.g. weight of the filters) in initial layers of the CNN. Regarding Claim 5, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu further discloses, 5. The method of claim 1 wherein selecting the threshold value comprises determining whether to pass a section of the seismic data to a thresholding routine (Fig. 1, ¶ 67 a trained ML model may be used to predict (infer)) based on binary cross entropy loss (Fig. 1, ¶ 67 ML model that has been trained with augmented datasets may have an objective function (e.g., binary cross entropy) using the classification head of the machine learning model. Regarding Claim 7, Liu in view of Alwon disclose the limitations of claim 5, which this claim depends on. Liu further discloses, 7. The method of claim 5 further comprising conducing pixelwise noise and signal thresholding estimations (Fig. 1, ¶ 48 proportion of geologic labels of pixels in any given patch must meet a set criterion) based on MSE loss using a segmentation head (Fig. 1, ¶ 81 task of segmentation) of the machine learning model, wherein the segmentation head shares weights (Fig. 1, ¶ 38 e.g. weight of the filters) in initial layers of the CNN. Regarding Claim 8, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu fails to disclose, 8. The method of claim 1 wherein removing the interference and background noise from the unblended seismic data to produce modified seismic data comprises removing the interference and background noise based on the selected threshold value. Alwon further discloses, 8. The method of claim 1 wherein removing the interference and background noise from the unblended seismic data to produce modified seismic data comprises removing the interference and background noise (Fig. 1, ¶ 35 noise attenuated seismic data) based on the selected threshold value (Fig. 1, ¶ 35 noise attenuation). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the method for processing seismic data disclosed by Liu in view of Alwon with a method for processing seismic data wherein, removing the interference and background noise from the unblended seismic data to produce modified seismic data comprises removing the interference and background noise based on the selected threshold value; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 9, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu fails to disclose, 9. The method of claim 1 wherein removing the interference and background noise from the unblended seismic data to produce modified seismic data comprises removing the interference and background noise based on the application of the sparsity promoting transform domain to the received blended seismic data. Alwon further discloses, 9. The method of claim 1 wherein removing the interference and background noise from the unblended seismic data to produce modified seismic data comprises removing the interference and background noise (Fig. 1, ¶ 35 noise attenuation) based on the application of the sparsity promoting transform domain (Fig. 5, ¶ 82 convert seismic data of one or more of different domains, such as, for example, the FK or Radon domains) to the received blended seismic data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the method for processing seismic data disclosed by Liu in view of Alwon with a method for processing seismic data wherein, removing the interference and background noise from the unblended seismic data to produce modified seismic data comprises removing the interference and background noise based on the application of the sparsity promoting transform domain to the received blended seismic data; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 10, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu further discloses, 10. The method of claim 1 further comprising enhancing a sparsity of the blended seismic data in the transform domain by using wavefield propagation information (Fig. 1, ¶ 27 Full Wavefield Inversion (FWI)), wherein the wavefield propagation information contains geological data of the subsurface (Fig. 1, ¶ 27 subsurface physical properties model). Regarding Claim 11, Liu in view of Alwon disclose the limitations of claim 1, which this claim depends on. Liu further discloses, 11. The method of claim 1 further comprising generating an image (Fig. 1, ¶ 44 generating images) of the subsurface based on the modified seismic data. Regarding Claim 12, Liu discloses, 12. A computing system (Fig. 1, ¶ 41 data augmentation systems), comprising: one or more processors (Fig. 7, ¶ 92 central processing unit (CPU) 9902); at least one seismic source (Fig. 1, ¶ 26 data received and/or recorded as part of the seismic surveying process) communicated to the one or more processors; and a memory system (Fig. 7, ¶ 93 additional non-transitory, computer-readable media) including one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising a method for processing seismic data (Fig. 1, ¶ 26 data received and/or recorded as part of the seismic surveying process), — enhancing a sparsity of the blended seismic data in the transform domain by using wavefield propagation information (Fig. 1, ¶ 27 Full Wavefield Inversion (FWI)); — and generating an image (Fig. 1, ¶ 44 generating images) of the subsurface based on the modified seismic data. Liu fails to disclose, — the method comprising: receiving blended seismic data from the at least one seismic source; applying a sparsity promoting transform domain to the received blended seismic data to differentiate a primary signal from interference and background noise; — isolating the primary signal from the interference and background noise by selecting a threshold value in the sparsity promoting transform domain using a machine learning model, wherein the primary signal represents unblended seismic data, wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio relative to a predetermined value; removing the interference and background noise from the unblended seismic data to produce modified seismic data; — In analogous art, Alwon discloses, — the method comprising: receiving blended seismic data from the at least one seismic source (Fig. 4, ¶ 74 seismic data include blended seismic data); applying a sparsity promoting transform domain (Fig. 5, ¶ 82 convert seismic data of one or more of different domains, such as, for example, the FK or Radon domains) to the received blended seismic data to differentiate a primary signal (Fig. 1, ¶ 30 enhanced signal) from interference and background noise (Fig. 1, ¶ 30 noise may be subject to attenuation); — isolating the primary signal from the interference and background noise by selecting a threshold value (Fig. 1, ¶ 35 noise attenuation) in the sparsity promoting transform domain using a machine learning model (Fig. 1, ¶ 35 machine learning techniques), wherein the primary signal represents unblended seismic data (Fig. 1, ¶ 89 enhance seismic data), wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio (Fig. 13, ¶ 149 level of signal to noise (e.g., SNR)) relative to a predetermined value (Fig. 13, ¶ 149 which is greater than that of "noisy" data); removing the interference and background noise from the unblended seismic data to produce modified seismic data (Fig. 7, ¶ 87 enhance signal); — It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu by combining the processing seismic data disclosed by Liu with a system comprising: the method comprising: receiving blended seismic data from the at least one seismic source; applying a sparsity promoting transform domain to the received blended seismic data to differentiate a primary signal from interference and background noise; isolating the primary signal from the interference and background noise by selecting a threshold value in the sparsity promoting transform domain using a machine learning model, wherein the primary signal represents unblended seismic data, wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio relative to a predetermined value; removing the interference and background noise from the unblended seismic data to produce modified seismic data; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 13, Liu in view of Alwon disclose the limitations of claim 12, which this claim depends on. Liu further discloses, — and wherein the machine learning model comprises a convolutional neural network (CNN) in which a classification head (Fig. 1, ¶ 81 task of classification) and a regression head (Fig. 1, Claim 28 using interpolation or extrapolation) share weights (Fig. 1, ¶ 38 e.g. weight of the filters) in initial layers of the CNN. Liu fails to disclose, 13. The computing system of claim 12 wherein selecting the threshold value is based at least partially upon multiple independent applications of the sparsity promoting transform domain to the received blended seismic data, — Alwon further discloses, 13. The computing system of claim 12 wherein selecting the threshold value is based at least partially upon multiple independent applications (Fig. 6, ¶ 81 learning various filters and passing them through a network with several layers) of the sparsity promoting transform domain to the received blended seismic data, — It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the system disclosed by Liu in view of Alwon with a system wherein, selecting the threshold value is based at least partially upon multiple independent applications of the sparsity promoting transform domain to the received blended seismic data; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 15, Liu in view of Alwon disclose the limitations of claim 12, which this claim depends on. Liu fails to disclose, 15. The computing system of claim 12 wherein removing the interference and background noise from the seismic data to produce modified seismic data comprises removing the interference and background noise based on the selected threshold value and the application of the sparsity promoting transform domain to the received blended seismic data. Alwon further discloses, 15. The computing system of claim 12 wherein removing the interference and background noise from the seismic data to produce modified seismic data comprises removing the interference and background noise (Fig. 1, ¶ 35 noise attenuated seismic data) based on the selected threshold value (Fig. 1, ¶ 35 noise attenuation) and the application of the sparsity promoting transform domain (Fig. 5, ¶ 82 convert seismic data of one or more of different domains, such as, for example, the FK or Radon domains) to the received blended seismic data. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the system disclosed by Liu in view of Alwon with a 15. The computing system of claim 12 wherein removing the interference and background noise from the seismic data to produce modified seismic data comprises removing the interference and background noise based on the selected threshold value and the application of the sparsity promoting transform domain to the received blended seismic data; disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Regarding Claim 16, Liu in view of Alwon disclose the limitations of claim 12, which this claim depends on. Liu further discloses, 16. The computing system of claim 12 wherein enhancing the sparsity of the blended seismic data in the transform domain by using wavefield propagation information (Fig. 1, ¶ 27 Full Wavefield Inversion (FWI)) comprises using wavefield propagation information that contains geological data of the subsurface (Fig. 1, ¶ 27 subsurface physical properties model). Regarding Claim 17, Liu in view of Alwon disclose the limitations of claim 12, which this claim depends on. Liu further discloses, 17. The computing system of claim 12 wherein the operations further comprise performing a wellsite action (Fig. 1, ¶ 29 drilling a well and prospecting for, and/or producing, hydrocarbons using the well; and/or, causing a well to be drilled, e.g., to prospect for hydrocarbons)) in response to the modified seismic data. Claim(s) 6, 14, 18 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over LIU et al. (US 2020/0183035 A1) (herein after Liu) in view of Alwon (US 2019/0302290 A1) (herein after Alwon), and further in view of Hegge et al. (US 2023/0140656 A1) (herein after Hegge). Regarding Claim 6, Liu in view of Alwon disclose the limitations of claim 5, which this claim depends on. Liu and Alwon fail to disclose, 6. The method of claim 5 further comprising determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine. In analogous art, Hegge discloses, 6. The method of claim 5 further comprising determining the threshold value based on mean square error (MSE) loss (Fig. 2, ¶ 38 mean squared error function) using the regression head of the learning model in response to determining to pass the section to the thresholding routine. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the method for processing seismic data disclosed by Liu in view of Alwon with a method for processing seismic data further comprising, determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine; disclosed by Hegge for the benefit of processing seismic data use machine learning to improve seismic data processing functionality by using past seismic processing results to determine other processing results [Hegge: ¶ 19 testing different values of process parameters may be a time-consuming operation that requires an iterative and sequential testing process to evaluate different results in order to find an optimum result. Thus, some embodiments use machine learning to improve seismic data processing functionality by using past seismic processing results to determine other processing results based on different parameterizations]. Regarding Claim 14, Liu in view of Alwon disclose the limitations of claim 12, which this claim depends on. Liu further discloses, 14. The computing system of claim 12 wherein selecting the threshold value comprises: determining whether to pass a section of the seismic data to a thresholding routine (Fig. 1, ¶ 67 a trained ML model may be used to predict (infer)) based on binary cross entropy loss (Fig. 1, ¶ 67 ML model that has been trained with augmented datasets may have an objective function (e.g., binary cross entropy) using the classification head of the machine learning model; — and conducing pixelwise noise and signal thresholding estimations (Fig. 1, ¶ 48 proportion of geologic labels of pixels in any given patch must meet a set criterion) based on MSE loss using a segmentation head (Fig. 1, ¶ 81 task of segmentation) of the machine learning model, wherein the segmentation head shares weights (Fig. 1, ¶ 38 e.g. weight of the filters) in initial layers of the CNN. Liu and Alwon fail to disclose, — determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine; — In analogous art, Hegge discloses, — determining the threshold value based on mean square error (MSE) loss (Fig. 2, ¶ 38 mean squared error function) using the regression head of the learning model in response to determining to pass the section to the thresholding routine; — It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the system disclosed by Liu in view of Alwon with a system for, determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine; disclosed by Hegge for the benefit of processing seismic data use machine learning to improve seismic data processing functionality by using past seismic processing results to determine other processing results [Hegge: ¶ 19 testing different values of process parameters may be a time-consuming operation that requires an iterative and sequential testing process to evaluate different results in order to find an optimum result. Thus, some embodiments use machine learning to improve seismic data processing functionality by using past seismic processing results to determine other processing results based on different parameterizations]. Regarding Claim 18, Liu discloses, 18. A non-transitory computer-readable medium (Fig. 7, ¶ 93 additional non-transitory, computer-readable media) storing instructions that, when executed by at least one processor of a computing system (Fig. 7, ¶ 92 central processing unit (CPU) 9902), cause the computing system to perform operations, the operations comprising a method for processing seismic data (Fig. 1, ¶ 26 data received and/or recorded as part of the seismic surveying process), the method comprising: — enhancing a sparsity of the blended seismic data in the transform domain by using wavefield propagation information (Fig. 1, ¶ 27 Full Wavefield Inversion (FWI)); — wherein the machine learning model comprises a convolutional neural network (CNN) in which a classification head (Fig. 1, ¶ 81 task of classification) and a regression head (Fig. 1, Claim 28 using interpolation or extrapolation) share weights (Fig. 1, ¶ 38 e.g. weight of the filters) in initial layers of the CNN, wherein selecting the threshold value comprises: determining whether to pass a section of the seismic data to a thresholding routine (Fig. 1, ¶ 67 a trained ML model may be used to predict (infer)) based on binary cross entropy loss (Fig. 1, ¶ 67 ML model that has been trained with augmented datasets may have an objective function (e.g., binary cross entropy) using the classification head of the machine learning model; — and conducing pixelwise noise and signal thresholding estimations (Fig. 1, ¶ 48 proportion of geologic labels of pixels in any given patch must meet a set criterion) based on MSE loss using a segmentation head (Fig. 1, ¶ 81 task of segmentation) of the machine learning model, wherein the segmentation head shares weights (Fig. 1, ¶ 38 e.g. weight of the filters) in initial layers of the CNN; — generating an image (Fig. 1, ¶ 44 generating images) of the subsurface based on the modified seismic data; displaying the image on a display (Fig. 7, display device 9920); and performing a wellsite action (Fig. 1, ¶ 29 drilling a well and prospecting for, and/or producing, hydrocarbons using the well; and/or, causing a well to be drilled, e.g., to prospect for hydrocarbons)) in response to the modified seismic data, wherein performing the wellsite action comprises generating or transmitting a signal that instructs or causes an action to occur, wherein the action comprises a physical action (Fig. 1, ¶ 29 "hydrocarbon management" or "managing hydrocarbons"), and wherein the physical action comprises selecting where to drill a wellbore in the subsurface formation, drilling the wellbore, varying a trajectory of the wellbore, varying a weight or torque on a drill bit that is drilling the wellbore, varying a rate or concentration of a fluid being pumped into the wellbore, or a combination thereof (Fig. 1, ¶ 29 drilling a well and prospecting for, and/or producing, hydrocarbons using the well; and/or, causing a well to be drilled, e.g., to prospect for hydrocarbons; hydrocarbon exploration; identifying potential hydrocarbon-bearing formations; characterizing hydrocarbon-bearing formations; identifying well locations; determining well injection rates; determining well extraction rates; identifying reservoir connectivity; acquiring, disposing of, and/or abandoning hydrocarbon resources). Liu fails to disclose — receiving blended seismic data from at least one seismic source; applying a sparsity promoting transform domain to the received blended seismic data to differentiate a primary signal from interference and background noise; — isolating the primary signal from the interference and background noise by selecting a threshold value in the sparsity promoting transform domain using a machine learning model, wherein the primary signal represents unblended seismic data, wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio relative to a predetermined value, wherein the threshold value is based at least partially upon multiple independent applications of the sparsity promoting transform domain to the received blended seismic data, — determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine; — removing the interference and background noise from the unblended seismic data based on the selected threshold value and the application of the sparsity promoting transform domain to the received blended seismic data to produce modified seismic data; — In analogous art, Alwon discloses, — receiving blended seismic data from at least one seismic source (Fig. 4, ¶ 74 seismic data include blended seismic data); applying a sparsity promoting transform domain (Fig. 5, ¶ 82 convert seismic data of one or more of different domains, such as, for example, the FK or Radon domains) to the received blended seismic data to differentiate a primary signal (Fig. 1, ¶ 30 enhanced signal) from interference and background noise (Fig. 1, ¶ 30 noise may be subject to attenuation); — isolating the primary signal from the interference and background noise by selecting a threshold value (Fig. 1, ¶ 35 noise attenuation) in the sparsity promoting transform domain using a machine learning model (Fig. 1, ¶ 35 machine learning techniques), wherein the primary signal represents unblended seismic data (Fig. 1, ¶ 89 enhance seismic data), wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio (Fig. 13, ¶ 149 level of signal to noise (e.g., SNR)) relative to a predetermined value (Fig. 13, ¶ 149 which is greater than that of "noisy" data), wherein the threshold value is based at least partially upon multiple independent applications (Fig. 6, ¶ 81 learning various filters and passing them through a network with several layers) of the sparsity promoting transform domain to the received blended seismic data, — removing the interference and background noise (Fig. 1, ¶ 35 noise attenuated seismic data) from the unblended seismic data based on the selected threshold value (Fig. 1, ¶ 35 noise attenuation) and the application of the sparsity promoting transform domain to the received blended seismic data to produce modified seismic data (Fig. 7, ¶ 87 enhance signal); — It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu by combining the non-transitory computer-readable medium for performing the method for processing seismic data disclosed by Liu with a non-transitory computer-readable medium for performing a method for processing seismic data comprising: receiving blended seismic data from at least one seismic source; applying a sparsity promoting transform domain to the received blended seismic data to differentiate a primary signal from interference and background noise; isolating the primary signal from the interference and background noise by selecting a threshold value in the sparsity promoting transform domain using a machine learning model, wherein the primary signal represents unblended seismic data, wherein the machine learning model is trained to determine if a subset of the seismic data represents a high or a low signal to noise ratio relative to a predetermined value, wherein the threshold value is based at least partially upon multiple independent applications of the sparsity promoting transform domain to the received blended seismic data, removing the interference and background noise from the unblended seismic data based on the selected threshold value and the application of the sparsity promoting transform domain to the received blended seismic data to produce modified seismic data; — disclosed by Alwon for the benefit of processing seismic data by simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality or a reduced turnaround time [Alwon: ¶ 72 simultaneous seismic source acquisition and processing technique that may allow for an improvement in quality for a standard turnaround time or a reduced turnaround time]. Liu and Alwon fail to disclose, — determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine; — In analogous art, Hegge discloses, — determining the threshold value based on mean square error (MSE) loss (Fig. 2, ¶ 38 mean squared error function) using the regression head of the learning model in response to determining to pass the section to the thresholding routine; — It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Liu in view of Alwon by combining the non-transitory computer-readable medium for performing the method for processing seismic data disclosed by Liu in view of Alwon with a non-transitory computer-readable medium for performing a method for processing seismic data comprising: determining the threshold value based on mean square error (MSE) loss using the regression head of the learning model in response to determining to pass the section to the thresholding routine; disclosed by Hegge for the benefit of processing seismic data use machine learning to improve seismic data processing functionality by using past seismic processing results to determine other processing results [Hegge: ¶ 19 testing different values of process parameters may be a time-consuming operation that requires an iterative and sequential testing process to evaluate different results in order to find an optimum result. Thus, some embodiments use machine learning to improve seismic data processing functionality by using past seismic processing results to determine other processing results based on different parameterizations]. Regarding Claim 19, Liu in view of Alwon in view of Hegge disclose the limitations of claim 18, which this claim depends on. Liu further discloses, 19. The non-transitory computer-readable medium of claim 18 wherein enhancing the sparsity of the seismic data in the transform domain by using wavefield propagation information (Fig. 1, ¶ 27 Full Wavefield Inversion (FWI)) comprises using wavefield propagation information that contains geological data of the subsurface (Fig. 1, ¶ 27 subsurface physical properties model). Regarding Claim 20, Liu in view of Alwon in view of Hegge disclose the limitations of claim 18, which this claim depends on. Liu further discloses, 20. The non-transitory computer-readable medium of claim 18 wherein performing the wellsite action further comprises adjusting at least one control parameter (Fig. 1, ¶ 29 drilling a well and prospecting for, and/or producing, hydrocarbons using the well; and/or, causing a well to be drilled, e.g., to prospect for hydrocarbons; hydrocarbon exploration; identifying potential hydrocarbon-bearing formations; characterizing hydrocarbon-bearing formations; identifying well locations; determining well injection rates; determining well extraction rates; identifying reservoir connectivity; acquiring, disposing of, and/or abandoning hydrocarbon resources) in a machine based on the image. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Kaul et al. (US 2021/0270983 A1) discloses, a method for processing seismic data (Fig. 1C, ¶ 39 method and apparatus for performing a seismic survey operation). Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH O. NYAMOGO whose telephone number is (469)295-9276. The examiner can normally be reached 9:00 A to 5:00 P CT. 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, EMAN ALFAKAWI can be reached at 571-272-4448. 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. /JOSEPH O. NYAMOGO/ Examiner Art Unit 2858 /FARHANA A HOQUE/Primary Examiner, Art Unit 2858
Read full office action

Prosecution Timeline

May 31, 2024
Application Filed
Oct 20, 2026
Non-Final Rejection mailed — §103
Nov 09, 2026
Examiner Interview Summary
Nov 09, 2026
Applicant Interview (Telephonic)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12800760
METHOD AND APPARATUS FOR DETERMINATION OF DIRECTION OF ARRIVAL ANGLE
3y 1m to grant Granted Nov 17, 2026
Patent 12771130
HEAVY OVERLOAD CHECK METHOD FOR LOAD TRANSFER DECISION OF OPEN-LOOP POWER GRID
3y 8m to grant Granted Oct 20, 2026
Patent 12753563
PARTITION MONITORING METHOD AND MODEL FOR CONCRETE DAM OPERATION KEY PART
2y 8m to grant Granted Oct 06, 2026
Patent 12743488
Automatic Partial Discharge and Noise Signals Separation using Arithmetic Coding in Time Domain and Magnitude Distributions in Frequency Domain
4y 10m to grant Granted Sep 22, 2026
Patent 12704543
WAFER ANALYZING DEVICE AND WAFER ANALYZING SYSTEM
2y 8m to grant Granted Aug 11, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
67%
Grant Probability
96%
With Interview (+28.5%)
3y 1m (~8m remaining)
Median Time to Grant
Low
PTA Risk
Based on 146 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month