DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1 and 5-7 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Willis et al. in Non-Patent Literature “Mitigation of Zigzag Noise on DAS VSP Records Acquired in Vertical Wells” (see 23 MAY 2023 IDS).
Regarding claim 1, Willis et al. teaches:
A method (Abstract) comprising:
receiving wellbore data comprising one or more seismic measurements (see “deploy wireline or coiled tubed based fiber-optic cables for acquiring distributed acoustic sensing (DAS) vertical seismic profile (VSP) data”, Introduction, Fig. 1);
generating a seismic input image based on the one or more seismic measurements (see “Figure 2 represents an example of zigzag noise on a DAS VSP data set”, Introduction, Fig. 1; Fig. 2 b-d);
processing the seismic input image to remove a zigzag noise in the seismic input image, wherein the zigzag noise represents noise in the one or more corresponding seismic measurements (see “A new algorithm…to help mitigate zigzag noise…2”extract the periodicity…3) remove the noise based upon the periodicity”, pg. 2; Fig. 2 e-h; see “denoise the data using the estimated period of the zigzag noise…perform adaptive subtraction…”, pg. 3); and
outputting a denoised seismic image (Fig. 2 e-h; Fig. 3d denoised traces using deconvolution; Fig. 4e denoised traces using estimated wavelet; Fig. 5b).
Regarding claim 5, Willis et al. teaches wherein the zigzag noise comprises a coupling noise caused by an uncoupling between an optic cable and a casing in a wellbore (see “a reverberating noise train…zigzag noise, appears in the distributed acoustic sensing vertical seismic profile records in zones with poor coupling”, Summary; see “deploy wireline or coiled tubing…do not have permanently installed fiber…this flexibility comes with the added liability of the potential for the fiber no to be acoustically well coupled to the wellbore wall…contaminated with zigzag noise..”, Introduction).
Regarding claim 6, Willis et al. teaches wherein the zigzag noise comprises a noise region having varying polarities through the noise region in depth (Figs. 1-4).
Regarding claim 7, Willis et al. teaches wherein the wellbore data comprises vertical seismic profile data that is collected using one or more fiber optic cables (see “Fiber-optic cables deployed by means of wireline or coiled tubing…”, Summary; see “deploy wireline or coiled tubed based fiber-optic cables for acquiring distributed acoustic sensing (DAS) vertical seismic profile (VSP) data”, Introduction, Fig. 1 “).
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) 2-3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Willis et al. in Non-Patent Literature “Mitigation of Zigzag Noise on DAS VSP Records Acquired in Vertical Wells” (see 23 MAY 2023 IDS) as applied to claim 1 above, and further in view of Dupont et al. in Foreign Patent Document.
Regarding claim 2, Willis et al. teaches the limitations as indicated above. Willis et al. differs from the claimed invention in that it is silent regarding providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a deep-learning network.
Dupont et al. teaches “analyze… seismic data…to generate image data for use in training machine learning algorithms” ([0021] machine learning model) wherein the seismic data may be collected via a wireline operation that suspends a wireline tool into a wellbore ([0040]-[0042]). The seismic data is processed in a data processing system ([0065], Fig. 7) comprising providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a deep-learning network (see “ processes…e.g., 2D or 3D seismic image data 456…Model 458 may be, for example, a deep learning model, e.g., a generative model such as a general adversarial network
(GAN) model”, [0065] emphasis added). Dupont et al. establishes that it is known in the art to process seismic image data using machine learning, deep learning networks, general adversarial networks, etc.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 3, Willis et al. teaches the limitations as indicated above. Willis et al. differs from the claimed invention in that it is silent regarding providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a generative adversarial network.
Dupont et al. teaches “analyze… seismic data…to generate image data for use in training machine learning algorithms” ([0021] machine learning model) wherein the seismic data may be collected via a wireline operation that suspends a wireline tool into a wellbore ([0040]-[0042]). The seismic data is processed in a data processing system ([0065], Fig. 7) comprising providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a generative adversarial network (see “ processes…e.g., 2D or 3D seismic image data 456…Model 458 may be, for example, a deep learning model, e.g., a generative model such as a general adversarial network (GAN) model”, [0065] emphasis added). Dupont et al. establishes that it is known in the art to process seismic image data using
machine learning, deep learning networks, general adversarial networks, etc.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Claim(s) 8-10, 12-17 and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Willis et al. in Non-Patent Literature “Mitigation of Zigzag Noise on DAS VSP Records Acquired in Vertical Wells” (see 23 MAY 2023 IDS), and further in view of Dupont et al. in Foreign Patent Document WO 2019200207 A1.
Regarding claim 8, Willis et al. teaches:
A system (Abstract) comprising:
receiving wellbore data comprising one or more seismic measurements (see “deploy wireline or coiled tubed based fiber-optic cables for acquiring distributed acoustic sensing (DAS) vertical seismic profile (VSP) data”, Introduction, Fig. 1);
generating a seismic input image based on the one or more seismic measurements (see “Figure 2 represents an example of zigzag noise on a DAS VSP data set”, Introduction, Fig. 1; Fig. 2 b-d);
processing the seismic input image to remove a zigzag noise in the seismic input image, wherein the zigzag noise represents noise in the one or more corresponding seismic measurements (see “A new algorithm…to help mitigate zigzag noise…2”extract the periodicity…3) remove the noise based upon the periodicity”, pg. 2; Fig. 2 e-h; see “denoise the data using the estimated period of the zigzag noise…perform adaptive subtraction…”, pg. 3); and
outputting a denoised seismic image (Fig. 2 e-h; Fig. 3d denoised traces using deconvolution; Fig. 4e denoised traces using estimated wavelet; Fig. 5b).
Willis et al. differs from the claimed invention in that it is silent regarding one or more processors and a computer-readable medium comprising instructions stored therein, which when executed by the processors, cause the processors to perform operations.
Dupont et al. teaches “analyze… seismic data…to generate image data for use in training machine learning algorithms” ([0021] machine learning model) wherein the seismic data may be collected via a wireline operation that suspends a wireline tool into a wellbore ([0040]-[0042]). The seismic data is processed in a data processing system ([0065], Fig. 7). The data processing system comprises one or more processors and a computer-readable medium comprising instructions stored therein, which when executed by the processors, cause the processors to perform operations (see “…at least one hardware-based processor….a memory…”, [0022], Fig. 1; see “…instructions…program code…”, [0026]). Dupont et al. establishes that it is known in the art to process seismic image data in a system comprising processors, memory and instructions.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 9, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Dupont et al. teaches the seismic data is processed in a data processing system ([0065], Fig. 7) comprising providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a deep-learning network (see “ processes…e.g., 2D or 3D seismic image data 456…Model 458 may be, for example, a deep learning model, e.g., a generative model such as a general adversarial network (GAN) model”, [0065] emphasis added). Dupont et al. establishes that it is known in the art to process seismic image data using machine
learning, deep learning networks, general adversarial networks, etc.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 10, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Dupont et al. teaches the seismic data is processed in a data processing system ([0065], Fig. 7) comprising providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a generative adversarial network (see “ processes…e.g., 2D or 3D seismic image data 456…Model 458 may be, for example, a deep learning model, e.g., a generative model such as a general adversarial network (GAN) model”, [0065] emphasis added). Dupont et al. establishes that it is known in the art to process seismic image data using
machine learning, deep learning networks, general adversarial networks, etc.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 12, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Willis et al. teaches wherein the zigzag noise comprises a coupling noise caused by an uncoupling between an optic cable and a casing in a wellbore (see “a reverberating noise train…zigzag noise, appears in the distributed acoustic sensing vertical seismic profile records in zones with poor coupling”, Summary; see “deploy wireline or coiled tubing…do not have permanently installed fiber…this flexibility comes with the added liability of the potential for the fiber no to be acoustically well coupled to the wellbore wall…contaminated with zigzag noise..”, Introduction).
Regarding claim 13, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Willis et al. teaches wherein the zigzag noise comprises a noise region having varying polarities through the noise region in depth (Figs. 1-4).
Regarding claim 14, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Willis et al. teaches wherein the wellbore data comprises vertical seismic profile data that is collected using one or more fiber optic cables (see “Fiber-optic cables deployed by means of wireline or coiled tubing…”, Summary; see “deploy wireline or coiled tubed based fiber-optic cables for acquiring distributed acoustic sensing (DAS) vertical seismic profile (VSP) data”, Introduction, Fig. 1 “).
Regarding claim 15, Willis et al. teaches:
receiving wellbore data comprising one or more seismic measurements (see “deploy wireline or coiled tubed based fiber-optic cables for acquiring distributed acoustic sensing (DAS) vertical seismic profile (VSP) data”, Introduction, Fig. 1);
generating a seismic input image based on the one or more seismic measurements (see “Figure 2 represents an example of zigzag noise on a DAS VSP data set”, Introduction, Fig. 1; Fig. 2 b-d);
processing the seismic input image to remove a zigzag noise in the seismic input image, wherein the zigzag noise represents noise in the one or more corresponding seismic measurements (see “A new algorithm…to help mitigate zigzag noise…2”extract the periodicity…3) remove the noise based upon the periodicity”, pg. 2; Fig. 2 e-h; see “denoise the data using the estimated period of the zigzag noise…perform adaptive subtraction…”, pg. 3); and
outputting a denoised seismic image (Fig. 2 e-h; Fig. 3d denoised traces using deconvolution; Fig. 4e denoised traces using estimated wavelet; Fig. 5b).
Willis et al. differs from the claimed invention in that it is silent regarding A non-transitory computer-readable storage medium comprising instructions stored therein, which when executed by one or more processors, cause the processors to perform operations.
Dupont et al. teaches “analyze… seismic data…to generate image data for use in training machine learning algorithms” ([0021] machine learning model) wherein the seismic data may be collected via a wireline operation that suspends a wireline tool into a wellbore ([0040]-[0042]). The seismic data is processed in a data processing system ([0065], Fig. 7). The data processing system comprises a non-transitory computer-readable storage medium comprising instructions stored therein, which when executed by one or more processors, cause the processors to perform (see “…at least one hardware-based processor….a memory…”, [0022], Fig. 1; see “…instructions…program code…”, [0026]). Dupont et al. establishes that it is known in the art to process seismic image data in a system comprising processors, memory and instructions.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 16, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Dupont et al. teaches the seismic data is processed in a data processing system ([0065], Fig. 7) comprising providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a deep-learning network (see “ processes…e.g., 2D or 3D seismic image data 456…Model 458 may be, for example, a deep learning model, e.g., a generative model such as a general adversarial network (GAN) model”, [0065] emphasis added). Dupont et al. establishes that it is known in the art to process seismic image data using machine
learning, deep learning networks, general adversarial networks, etc.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 17, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Dupont et al. teaches the seismic data is processed in a data processing system ([0065], Fig. 7) comprising providing the seismic input image to a machine-learning model, wherein the machine- learning model comprises a generative adversarial network (see “ processes…e.g., 2D or 3D seismic image data 456…Model 458 may be, for example, a deep learning model, e.g., a generative model such as a general adversarial network (GAN) model”, [0065] emphasis added). Dupont et al. establishes that it is known in the art to process seismic image data using
machine learning, deep learning networks, general adversarial networks, etc.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known seismic image processing techniques taught in Dupont et al in Willis et al. to improve Willis et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. thereby resulting increase accuracy of the denoised output results.
Regarding claim 19, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Willis et al. teaches wherein the zigzag noise comprises a coupling noise caused by an uncoupling between an optic cable and a casing in a wellbore (see “a reverberating noise train…zigzag noise, appears in the distributed acoustic sensing vertical seismic profile records in zones with poor coupling”, Summary; see “deploy wireline or coiled tubing…do not have permanently installed fiber…this flexibility comes with the added liability of the potential for the fiber no to be acoustically well coupled to the wellbore wall…contaminated with zigzag noise..”, Introduction).
Regarding claim 20, Willis et al. and Dupont et al. teaches the limitations as indicated above. Further, Willis et al. teaches wherein the zigzag noise comprises a noise region having varying polarities through the noise region in depth (Figs. 1-4).
Claim(s) 4, 11 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Willis et al. in Non-Patent Literature “Mitigation of Zigzag Noise on DAS VSP Records Acquired in Vertical Wells” (see 23 MAY 2023 IDS) and Dupont et al. in Foreign Patent Document WO 2019200207 A1 as applied to claims 3, 10 and 17 above, and further in view of Shi et al. in Foreign Patent Document WO 2020033902 A1.
Regarding claim 4, Willis et al. and Dupont et al. teaches the limitations as indicated above. Willis et al. and Dupont et al. differs from the claimed invention in that they are silent regarding a plurality of discriminative models.
Shi et al. relates to image analysis and processing using a generative adversarial network (GAN) (Abstract; [0002]-[0004]). Shi et al. teaches “A “cycle-consistent generative adversarial network,” also called a “cycleGAN” is a type of generative adversarial network that uses two generative models and two discriminator models.” ([0032], the generative adversarial network comprises a plurality of discriminative models). Shi et al. establishes that using a GAN with a plurality of discriminative models for image analysis and processing is part of the knowledge of one of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known technique of image analysis and processing using a GAN with two discriminative models in the known method and system of Willis et al. and Dupont et al. to improve Willis et al. and Dupont et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. and Dupont et al. thereby resulting increase accuracy of the denoised output. The result yields no more than a predictable outcome which one of ordinary skill would have expected to achieve with this common tool of the trade.
Regarding claim 11, Willis et al. and Dupont et al. teaches the limitations as indicated above. Willis et al. and Dupont et al. differs from the claimed invention in that they are silent regarding a plurality of discriminative models.
Shi et al. relates to image analysis and processing using a generative adversarial network (GAN) (Abstract; [0002]-[0004]). Shi et al. teaches “A “cycle-consistent generative adversarial network,” also called a “cycleGAN” is a type of generative adversarial network that uses two generative models and two discriminator models.” ([0032], the generative adversarial network comprises a plurality of discriminative models). Shi et al. establishes that using a GAN with a plurality of discriminative models for image analysis and processing is part of the knowledge of one of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known technique of image analysis and processing using a GAN with two discriminative models in the known method and system of Willis et al. and Dupont et al. to improve Willis et al. and Dupont et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. and Dupont et al. thereby resulting increase accuracy of the denoised output. The result yields no more than a predictable outcome which one of ordinary skill would have expected to achieve with this common tool of the trade.
Regarding claim 18, Willis et al. and Dupont et al. teaches the limitations as indicated above. Willis et al. and Dupont et al. differs from the claimed invention in that they are silent regarding a plurality of discriminative models.
Shi et al. relates to image analysis and processing using a generative adversarial network (GAN) (Abstract; [0002]-[0004]). Shi et al. teaches “A “cycle-consistent generative adversarial network,” also called a “cycleGAN” is a type of generative adversarial network that uses two generative models and two discriminator models.” ([0032], the generative adversarial network comprises a plurality of discriminative models). Shi et al. establishes that using a GAN with a plurality of discriminative models for image analysis and processing is part of the knowledge of one of ordinary skill in the art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the known technique of image analysis and processing using a GAN with two discriminative models in the known method and system of Willis et al. and Dupont et al. to improve Willis et al. and Dupont et al. with a reasonable expectation that it would result in improving the efficiency of Willis et al. and Dupont et al. thereby resulting increase accuracy of the denoised output. The result yields no more than a predictable outcome which one of ordinary skill would have expected to achieve with this common tool of the trade.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
He et al. in Foreign Patent Document CN 116703740 A teaches “an image de-noising method, device and computer readable storage medium, the method comprises…performing noise modelling by using the noise set and the improved generation adversarial network GAN; said improved GAN is composed of two generators and two discriminators…training the deep neural network CNN model based on the training data set to obtain a de-noising model for de-noising the image to be processed.” (Abstract the generative adversarial network comprises a plurality of discriminative models).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MISCHITA HENSON whose telephone number is (571)270-3944. The examiner can normally be reached Monday-Thursday 9am-6pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Arleen Vazquez can be reached at 571-272-2619. 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.
/MI'SCHITA' HENSON/Primary Examiner, Art Unit 2857