DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status
2. This communication is in response to the Application filed on 07.16.2024. Claims 1-20 will be subject to further examination and evaluation in due course, and will be presented for examination, as detailed below.
Oath/Declaration
3. The Applicant’s oath/declaration has been reviewed by the Examiner and is found to conform to the requirements prescribed in 37 C.F.R. 1.63.
Information Disclosure Statement
4. As required by M.P.E.P. 609(C), the Applicant’s submission of the Information Disclosure Statement (IDS) dated 07.16.2024 is acknowledged by the Examiner. The cited references have been considered in the examination of the claims. As required by M.P.E.P 609 C (2), a copy of the PTOL-1449 initialed, signed and dated by the Examiner is attached to the instant Office action.
Priority / Filing Date
5. Applicant’s claim for priority of Foreign Application filed on 07.17.2023 is acknowledged. The Examiner takes the US Application date of 07.17.2023 into consideration.
Claim Rejections - 35 USC § 103
6. 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.
7. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
8. Claims 1-7 are rejected under 35 U.S.C. 103 as being unpatentable over Di et al., Pub. No.: US 2023/0026857 in view of Liu et al., Pub. No.: US 2023/0375735.
As per claim 1, Di discloses a subsurface property estimation [see at least the abstract (e.g., a subsurface domain, receiving one or more well logs representing one or more subsurface properties in the subsurface domain, and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain at a location that does not correspond to an existing well based on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data)] method comprising:
creating, by a computer device, a training data set by preprocessing well-log data and first seismic data [see at least ¶0064 (e.g., SWI engine 504 may be configured to make connections between the seismic data, seismic features, and the well logs, in order to predict subsurface properties (e.g., the subsurface properties represented by the well logs 506) at locations where a well does not exist (e.g., a planned location)), and as illustrated in FIG. 5A below]:
FIG. 5A illustrates a conceptual, schematic view of a workflow for seismic acoustic impedance estimation.
PNG
media_image1.png
370
552
media_image1.png
Greyscale
the computer device including at least one processor for executing computer-readable instructions included in a data storage device [see at least ¶0075 (e.g., FIG. 8 illustrates an example of such a computing system 800. The computing system 800 may include a computer or computer system 801A, which may be an individual computer system 801A or an arrangement of distributed computer systems. The computer system 801A includes one or more analysis module(s) 802 configured to perform various tasks …. the analysis module 802 executes independently, or in coordination with, one or more processors 804, which is (or are) connected to one or more storage media 806 …...)]:
FIG. 8 illustrates a schematic view of a computing system.
PNG
media_image2.png
637
546
media_image2.png
Greyscale
creating, by the computer device, an estimation model by using the training data set, the estimation model including: an encoder model configured to create a latent space that reflects features of strata based on input data [see at least ¶0065 (e.g., FIG. 5B illustrates another functional diagram of the system 500 …… the SWI engine 504 implements an encoder and decoder, as shown, and may also include a fine-tuner. In particular, a 2D encoder, 2D decoder, and 1D fine-tuner may be employed, which may individually contain a set of convolutional layers. The encoder, as a feature generator, extracts a set of 2D features from an input 2D seismic image (e.g., derived from a 3D seismic cube). The decoder, as a feature integrator, combines these 2D features into a set of 1D features. Finally, the fine-tuner maps these 1D features with the given 1D well log)]:
FIG. 5B illustrates a conceptual, schematic view of an architecture of a deep learning neural network for seismic-well integration in the workflow.
PNG
media_image3.png
292
583
media_image3.png
Greyscale
Di discloses all elements per claimed invention as explained above. Di further discloses a decoder model configured to generate a first factor corresponding to a subsurface property [see at least ¶0065 (e.g., the SWI engine 504 implements an encoder and decoder, as shown, and may also include a fine-tuner. In particular, a 2D encoder, 2D decoder, and 1D fine-tuner may be employed, which may individually contain a set of convolutional layers. The encoder, as a feature generator, extracts a set of 2D features from an input 2D seismic image (e.g., derived from a 3D seismic cube). The decoder, as a feature integrator, combines these 2D features into a set of 1D features. Finally, the fine-tuner maps these 1D features with the given 1D well log)]; a regression model configured to estimate a second factor corresponding to the subsurface property [see at least ¶0056 (e.g., the second model may integrate three-dimensional (3D) seismic data and one-dimensional (1D) well logs by using the regional features already learned in the first machine learning model, which reduces the risk of overfitting and improves the lateral consistency in the subsurface property estimation)]; and estimating the second factor corresponding to the subsurface property by inputting second seismic data to the estimation model [see at least ¶0078 (e.g., computing system 800 contains one or more subsurface property estimation module(s) 808), and as illustrated in FIG. 8 below].
FIG. 8 illustrates a schematic view of a computing system.
PNG
media_image4.png
636
550
media_image4.png
Greyscale
Di does not expressly disclose: the subsurface property based on the latent space. However, Liu discloses the subsurface property based on the latent space [see at least Liu: as illustrated in FIGs. 1, 7 and 8]:
FIG. 1. An autoencoder 110 may learn a latent representation Z while reconstructing the image along with the following two functions: (1) an encoding function (performed by encoder 120) parameterized by θ that takes in image x as an input and outputs the values of latent variable z=(x); and (2) a decoding function (performed by decoder 130) parameterized by μ it that takes in the values of latent variables and outp-uts an image, x′=(z) [see Liu: FIG. 1].
PNG
media_image5.png
469
589
media_image5.png
Greyscale
FIG. 7 is an illustration of preparing test data points for latent space interpretation.
PNG
media_image6.png
356
403
media_image6.png
Greyscale
FIG. 8 is a graph of the relational property (latent space z) of the test data points.
PNG
media_image7.png
354
480
media_image7.png
Greyscale
Therefore, it would have been obvious to a person having ordinary skill in the art at the time the invention was made to incorporate the teaching of Liu in order to provide latent variable models [Liu: ¶0045].
As per claim 2, Di discloses wherein the creating of the estimation model comprises: creating the encoder model by extracting the features of the strata from the training data set by performing a self-supervised learning on the training data set [see at least ¶0056 (e.g., the first model may “learn” (e.g., unsupervised or “self” learning))]; creating the decoder model for reconstructing the first factor based on the latent space; creating the regression model for estimating the second factor based on the latent space; and training the encoder model and the decoder model simultaneously by applying weightings of a loss function such that a reconstruction error of the first factor and an estimation error of the second factor are simultaneously minimized [see at least the rejection of claim 1 above. Similar rationale is noticed for the combination of Di and Liu, as noted in claim 1 above. In light of the preceding examination, claim 2 is hereby rejected on grounds substantially similar to those articulated in the rejection of claim 1. As detailed in the prior rejection, the rationale and basis for rejecting claim 1 are applicable to claim 2. For a comprehensive understanding of the rejection grounds, reference is made to the detailed explanation provided in the rejection of claim 1, which is incorporated herein by reference].
As per claim 3, Di discloses wherein the creating of the encoder model includes performing a self-supervised learning algorithm to train an encoder portion of the self-supervised learning algorithm and extract the features of the strata from the training data included in the training data set, and the encoder portion is extracted to obtain the encoder model [see at least ¶0056 (e.g., the first model may “learn” (e.g., unsupervised or “self” learning)), and the rejection of claim 1 above. Similar rationale is noticed for the combination of Di and Liu, as noted in claim 1 above. In light of the preceding examination, claim 3 is hereby rejected on grounds substantially similar to those articulated in the rejection of claim 1. As detailed in the prior rejection, the rationale and basis for rejecting claim 1 are applicable to claim 3. For a comprehensive understanding of the rejection grounds, reference is made to the detailed explanation provided in the rejection of claim 1, which is incorporated herein by reference].
As per claim 4, Di discloses wherein the decoder model is created to reconstruct the first factor based on the latent space created by the encoder model, and the decoder model is trained using the reconstruction error that is obtained by comparing the first factor of first label data included in the training data set with the first factor output by the decoder model when the training data included in the training data set is input to the encoder model [see at least the rejection of claim 1 above. Similar rationale is noticed for the combination of Di and Liu, as noted in claim 1 above. In light of the preceding examination, claim 4 is hereby rejected on grounds substantially similar to those articulated in the rejection of claim 1. As detailed in the prior rejection, the rationale and basis for rejecting claim 1 are applicable to claim 4. For a comprehensive understanding of the rejection grounds, reference is made to the detailed explanation provided in the rejection of claim 1, which is incorporated herein by reference].
As per claim 5, Di discloses wherein the creating of the regression model includes creating a regression equation to estimate the second factor based on the latent space created by the encoder model [see at least the rejection of claim 1 above. Similar rationale is noticed for the combination of Di and Liu, as noted in claim 1 above. In light of the preceding examination, claim 5 is hereby rejected on grounds substantially similar to those articulated in the rejection of claim 1. As detailed in the prior rejection, the rationale and basis for rejecting claim 1 are applicable to claim 5. For a comprehensive understanding of the rejection grounds, reference is made to the detailed explanation provided in the rejection of claim 1, which is incorporated herein by reference].
As per claim 6, Di discloses wherein the training of the encoder model and the decoder model simultaneously includes: obtaining the reconstruction error of an output of the first factor by the decoder model and the estimation error of an output of the second factor by the regression model are obtained upon inputting the training data of the training data set to the encoder model; training the encoder model and the decoder model based on the reconstruction error of the first factor, the encoder model based on the estimation error of the second factor; and forming the weightings such that the loss function for simultaneously training the encoder model and the decoder model reflects the estimation error of the second factor more than the reconstruction error of the first factor [see at least the rejection of claim 1 above. Similar rationale is noticed for the combination of Di and Liu, as noted in claim 1 above. In light of the preceding examination, claim 6 is hereby rejected on grounds substantially similar to those articulated in the rejection of claim 1. As detailed in the prior rejection, the rationale and basis for rejecting claim 1 are applicable to claim 6. For a comprehensive understanding of the rejection grounds, reference is made to the detailed explanation provided in the rejection of claim 1, which is incorporated herein by reference].
As per claim 7, Di discloses wherein the creating of the training data set comprises: performing a data preprocessing to: convert the well-log data into time-domain data; sample the well-log data to have a same resolution as the seismic data; and apply a smoothing in a horizontal direction of the strata to the first factor to be reconstructed; creating the training data by extracting, for each factor from the seismic data, data in a cube with width, length, and height; creating first label data by extracting, from the seismic data, the first factor of the width, the length, and the height corresponding to the cubes of the training data; and creating second label data by extracting, from the well-log data, the second factor corresponding to the width, the length, or the height of the cubes of the training data [see at least the rejection of claim 1 above. Similar rationale is noticed for the combination of Di and Liu, as noted in claim 1 above. In light of the preceding examination, claim 7 is hereby rejected on grounds substantially similar to those articulated in the rejection of claim 1. As detailed in the prior rejection, the rationale and basis for rejecting claim 1 are applicable to claim 7. For a comprehensive understanding of the rejection grounds, reference is made to the detailed explanation provided in the rejection of claim 1, which is incorporated herein by reference].
9. Claims 8-14, which are parallel to claims 1-7 in terms of scope, limitations, and share similar characteristics, as discussed and examined above. Consequently, they are rejected based on the same logical and underlying reasoning, and justification that apply to claims 1-7. The similarity between these claims necessitates the same grounds for rejection, as explained in detail above [note the discussion of claims 1-7].
10. Claims 15-20, which are parallel to claims 1-7 in terms of scope, limitations, and share similar characteristics, as discussed and examined above. Consequently, they are rejected based on the same logical and underlying reasoning, and justification that apply to claims 1-7. The similarity between these claims necessitates the same grounds for rejection, as explained in detail above [note the discussion of claims 1-7].
Conclusion
11. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The PTO-1449 form has been reviewed and considered.
US 2023/0032044, Li: discloses estimate wavelets without a well-log calibration.
US 2020/0309979, Wang: discloses method for property estimation including receiving a seismic dataset representative of a subsurface volume of interest and a well log from a well location within the subsurface volume of interest.
WO 2022140717, DENLI HUSEYIN: discloses method for identifying one or more geological features of interest from seismic data.
12. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Garcia Ade whose telephone number is (571)272-5586. The examiner can normally be reached on Monday - Friday.
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, Florian Zeender can be reached on 517-272-6790. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
13. 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). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Garcia Ade/Primary Examiner, Art Unit 3627
/GA/Primary Examiner, Art Unit 3627
GARCIA ADE
Primary Examiner
Art Unit 3687
Prosecution Insights