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 .
Priority
Acknowledgement is made for application priority to PCT/CN2024/098709 filed on 06/12/2024.
Information Disclosure Statement
The information disclosure statement (IDS) was submitted on 07/30/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Objections
Claim 5 is objected to because of the following informalities:
Claim 5 details the limitation “the trained velocity network based on one or more trained velocity parameters” which should read “the trained velocity network is based on one or more trained velocity parameters”.
Claim 5 details the limitation “the trainable velocity network is based on one or more velocity parameters” which should read “a trainable velocity network is based on one or more velocity parameters” as this is the first mention of “trainable velocity network”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Independent Claims 1, 5, and 12 detail a limitation of a “prediction location”. Merriam-webster (https://www.merriam-webster.com/dictionary/prediction) defines “prediction” as “an act of predicting” or “something that is predicted : forecast”. Merriam-webster (https://www.merriam-webster.com/dictionary/predict) further defines “predict” as “to declare or indicate in advance, especially foretell on the basis of observation, experience, or scientific reason”. [0084] of the instant application details that the prediction locations are formed as a set of distinct points in a region of interest. That is, it is not clear from the definition of prediction how locations are prediction locations, as the claims nor the specification detail any prediction occurring with respect to the locations, and instead details the locations as being related to set of points in a region of interest. Examiner interprets the “prediction locations” as “locations”.
Claims 2-4, 6-11, and 13-20 are rejected due to dependence on Claims 1, 5, and 12.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-10 and 12-19 are rejected under 35 U.S.C. 101. The claimed invention is directed to the abstract concept of performing abstract steps without significantly more. The claim(s) recite(s) the following abstract concepts in BOLD of
1. A method, comprising:
obtaining, from a data acquisition system, a seismic dataset of seismic traces pertaining to a region of interest, wherein each seismic trace within the seismic dataset comprises a seismic source location and a seismic receiver location;
determining, for each seismic trace within the seismic dataset, an observed travel time between the seismic source location of the seismic trace and the seismic receiver location of the seismic trace;
obtaining a trainable velocity network configured to receive, as input, a prediction location in the region of interest and return, as output, a velocity value, wherein the trainable velocity network depends on one or more velocity parameters;
obtaining a trainable travel time network configured to receive, as input, a source location and a prediction location and return, as output, a travel time value, wherein the trainable travel time network depends on one or more travel time parameters;
training the trainable travel time network and the trainable velocity network, wherein the training comprises:
obtaining a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on the trainable travel time network and the trainable velocity network;
constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output, a cost based on:
the travel times equation;
a derivative of the travel times equation, and
a travel time mismatch between:
a first observed travel time between a first seismic source location and a first seismic receiver location, and
a first travel time value output by the trainable travel time network upon receiving, as inputs, the first seismic source location and the first seismic receiver location, and
computing, with an optimizer, one or more trained travel times parameters and one or more trained velocity parameters, wherein the optimizer is configured to seek to minimize the cost function, and
building an image of a velocity model using the trainable velocity network and the one or more trained velocity parameters.
5. A method, comprising:
obtaining a first plurality of prediction locations discretizing a region of interest;
obtaining a trained velocity network configured to receive, as input, a prediction location in the region of interest and return, as output, a velocity value at the prediction location, the trained velocity network based on one or more trained velocity parameters, wherein the one or more trained velocity parameters are determined by using an optimizer that seeks to minimize a cost fiction based on:
a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on a trainable velocity network and a trainable travel time network, wherein:
the trainable velocity network is based on one or more velocity parameters;
the one or more velocity parameters are received by the cost function as inputs, and
the trained velocity network is obtained upon replacing, in the trainable velocity network, the one or more velocity parameters with the one or more trained velocity parameters, and
a derivative of the travel times equation, and
determining a velocity model for the region of interest, the velocity model comprising one velocity value for each prediction location within the first plurality of prediction locations, wherein, for each prediction location, the velocity value is determined by inputting the prediction location to the trained velocity network.
12. A system, comprising:
a seismic acquisition system configured to acquire a seismic dataset of seismic traces pertaining to a region of interest,
wherein each seismic trace within the seismic dataset comprising a seismic source location and a seismic receiver location, and
wherein, for each seismic trace, a receiver at the seismic receiver location of the seismic trace detects ground motion of a seismic wave radiating from the seismic source location of the seismic trace, and
a seismic processing system, configured to:
receive the seismic dataset from the seismic acquisition system;
determine, for each seismic trace within the seismic dataset, an observed travel time between the seismic source location of the seismic trace and the seismic receiver location of the seismic trace;
form a trainable velocity network configured to receive, as input, a prediction location in the region of interest and return, as output, a velocity value, wherein the trainable velocity network depends on one or more velocity parameters;
forma a trainable travel time network configured to receive, as input, a source location and a prediction location and return, as output, a travel time value, wherein the trainable travel time network depends on one or more travel time parameters, and
train the trainable travel time network and the trainable velocity network, wherein training the trainable travel time network and the trainable velocity network comprises:
obtaining a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on the trainable travel time network and the trainable velocity network;
constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output, a cost based on:
the travel times equation;
a derivative of the travel times equation, and
a travel time mismatch between:
a first observed travel time between a first seismic source location and a first seismic receiver location, and
a first travel time value output by the trainable travel time network upon receiving, as inputs, the first seismic source location and the first seismic receiver location, and
computing, with an optimizer, one or more trained travel times parameters and one or more trained velocity parameters, wherein the optimizer is configured to seek to minimize the cost function.
Under step 1 of the eligibility analysis, we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: process, machine, manufacture, or composition of matter. The above claims are considered to be in a statutory category.
Under Step 2A, Prong One, we consider whether the claim recites a judicial exception (abstract idea). In the above claim, the highlighted portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitation the fall into/recite abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, it falls into the grouping of subject matter that, when recited as such in a claim limitation, covers performing mathematics or mental steps.
Next, under Step 2A, Prong Two, we consider whether the claim that recites a judicial exception is integrated into a practical application. In this step, we evaluate whether the claim recites additional elements that integrate the exception into a practical application of that exception.
This judicial exception is not integrated into a practical application because there is no improvement to another technology or technical field; improvements to the functioning of the computer itself; a particular machine; effecting a transformation or reduction of a particular article to a different state or thing. Examiner notes that since the claimed methods and system are not tied to a particular machine or apparatus, they do not represent an improvement to another technology or technical field. Similarly there are no other meaningful limitations linking the use to a particular technological environment. Finally, there is nothing in the claims that indicates an improvement to the functioning of the computer itself or transform a particular article to a new state.
Finally, under Step 2B, we consider whether the additional elements are sufficient to amount to significantly more than the abstract idea. Claims 1, 5, and 12 does not include additional elements that are sufficient to amount to significantly more than the judicial exception because obtaining a seismic data set and receiving travel time is considered necessary data gathering. As recited in MPEP section 2106.05(g), necessary data gathering (i.e. obtaining/receiving data) is considered extra solution activity in light of Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015). The optimizer of Claims 1, 5, and 12 is interpreted under broadest reasonable interpretation to be a generic computer element as it is detailed as performing a computing operation. Generic computer elements are not considered significantly more than the abstract idea and do not integrate the abstract idea into a practical application. As recited in the MPEP, 2106.05(b), merely adding a generic computer, generic computer components, or a programmed computer to perform generic computer functions does not automatically overcome an eligibility rejection. Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 134 S. Ct. 2347, 2359-60, 110 USPQ2d 1976, 1984 (2014). See also OIP Techs. v. Amazon.com, 788 F.3d 1359, 1364, 115 USPQ2d 1090, 1093-94. The additional element of Claims 5 and 12 of a receiver at the seismic receiver location detects ground motion of a seismic wave radiation from the seismic source location is considered to be necessary data gathering. Furthermore, it is well understood, routine, and conventional in the art to utilize seismic receivers to gather seismic data, as evidenced by [0012] in Ma (CN117991377A) and [0026] in Sun (US20230203943).
Claims 2-4, 6-9, 13-18 further limit the abstract ideas without integrating the abstract concept into a practical application or including additional limitations that can be considered significantly more than the abstract idea.
Claims 10 and 19 recite the additional elements of seismic interpretation workstation and well planning system. The seismic interpretation workstation and well planning system is not sufficient to amount to significantly more than the abstract idea because the seismic interpretation workstation and well planning system are interpreted under broadest reasonable interpretation in light of the specification to be generic computers. Generic computer elements are not considered significantly more than the abstract idea and do not integrate the abstract idea into a practical application. As recited in the MPEP, 2106.05(b), merely adding a generic computer, generic computer components, or a programmed computer to perform generic computer functions does not automatically overcome an eligibility rejection. Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 134 S. Ct. 2347, 2359-60, 110 USPQ2d 1976, 1984 (2014). See also OIP Techs. v. Amazon.com, 788 F.3d 1359, 1364, 115 USPQ2d 1090, 1093-94.
Claims 11 and 20 are not rejected under 35 U.S.C. 101 because the additional limitation of drilling a wellbore guided by the wellbore trajectory integrates the judicial exception into a practical application.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-8 and 12-17 rejected under 35 U.S.C. 103 as being unpatentable over Ma (CN117991377A) in view of Sun (US20230203943).
In regards to Claim 1, Ma teaches “obtaining, from a data acquisition system, a seismic dataset of seismic traces pertaining to a region of interest, wherein each seismic trace within the seismic dataset comprises a seismic source location and a seismic receiver location (Collect data including spatial sampling point location data [i.e. seismic source location], shot point location data, geophone point location data [i.e. seismic receiver location], first arrival wave travel time data, micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]);
determining, for each seismic trace within the seismic dataset, an observed travel time between the seismic source location of the seismic trace and the seismic receiver location of the seismic trace (Collect data including spatial sampling point location data, shot point location data, geophone point location data, first arrival wave travel time data [i.e. observed travel time], micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]);
obtaining a trainable velocity network configured to receive, as input, a prediction location in the region of interest and return, as output, a velocity value, wherein the trainable velocity network depends on one or more velocity parameters (construct a travel-time field neural network and a velocity neural network – [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]; A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters [i.e. output a velocity value]. – [0019]; Where, is the total number of micrologging velocities, is the horizontal position of the micrologging, is the micrologging velocity at the horizontal position output by the velocity neural network, and is the actual micrologging velocity at the horizontal position - [0029]; Vtheta2 is the squared velocity at position xnj, ynj [i.e. prediction location], output by the velocity neural network- [0038]);
obtaining a trainable travel time network configured to receive, as input, a source location and a prediction location and return, as output, a travel time value, wherein the trainable travel time network depends on one or more travel time parameters (construct a travel-time field neural network and a velocity neural network – [0013]; A travel time field neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 4 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate the forward travel time field process. - [0018]; First-arrival travel time constraints are set for the travel time field neural network constructed in step S2. To constrain the travel time data acquired through sparse detectors, the expression for the first-arrival travel time constraint term is as follows:- [0021];
PNG
media_image1.png
65
362
media_image1.png
Greyscale
- [0022]; Where Ns is the total number of shot points, Nt is the total number of receiver points corresponding to each shot point, (xni, yni) is the position of the nth shot point [i.e. source location] and the ith receiver point [i.e. prediction location], Ttheta(xni, yni) [i.e. travel time value output] is the travel time of the position output by the travel time field neural network, and T-tilda (xni, yni) is the observed travel time of the position (xni, yni).- [0023]; The training process first requires the input point position coordinates to be given in space. After the network is trained, the velocity and travel time corresponding to the input point are generated. - [0043]);
training the trainable travel time network and the trainable velocity network (Construct [i.e. training] a travel-time field neural network and a velocity neural network - [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]), wherein the training comprises:
obtaining a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on the trainable travel time network and the trainable velocity network (First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An [eikonal] equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model [i.e. travel times equation] is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]);
constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return (The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]), as output, a cost based on:
the travel times equation (first-arrival time tomography network model, eikonal equation – [0014]); and
computing, with an optimizer, one or more trained travel times parameters and one or more trained velocity parameters, wherein the optimizer is configured to seek to minimize the cost function (In step S4.1, the training and iteration process of the first arrival wave travel time tomography network model involves calculating the loss function based on the parameters of the current neural network model and performing backpropagation. This process synchronously updates the model parameters of the travel time field neural network and the velocity neural network to reduce the loss function. This is achieved using the Adam optimizer. - [0044]), and
building an image of a velocity model using the trainable velocity network and the one or more trained velocity parameters (Furthermore, the specific implementation method of step S5 is to input the positions of all coordinate points in the model space to be predicted from the data test set obtained in step S1 into the first-arrival wave travel-time tomography network model trained in step S4, and output the velocity parameters in the model space to be predicted, thereby obtaining the near-surface velocity first-arrival wave travel-time tomography prediction result. - [n0011]; Figure 2-C and Figure 3-C show the first arrival travel time tomography results [i.e. an image of a velocity model]).”
Ma is silent with regards to the language of “constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output, a cost based on: the travel times equation; a derivative of the travel times equation, and a travel time mismatch between: a first observed travel time between a first seismic source location and a first seismic receiver location, and a first travel time value output by the trainable travel time network upon receiving, as inputs, the first seismic source location and the first seismic receiver location.”
Sun teaches “constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output, a cost based on: the travel times equation; a derivative of the travel times equation, and a travel time mismatch between: a first observed travel time between a first seismic source location and a first seismic receiver location, and a first travel time value output by the trainable travel time network upon receiving, as inputs, the first seismic source location and the first seismic receiver location (“Still another radial tomography method proposed by Zhang and Toksöz (“Nonlinear refraction traveltime tomography.” Geophysics 63.5 (1998): 1726-1737) may determine a velocity map along the axis of the wellbore ( 102 ) and radially away from the wellbore ( 102 ) using a still further alternate inversion scheme. A shortest path raytracing method with an optimized node distribution within a grid that represents a rock formation ( 104 ) is used to calculate travel times and ray paths for any velocity model. The nonlinear regularized inverse problem minimizes the residuals of the objective function [i.e. minimize the cost function]:
PNG
media_image2.png
36
355
media_image2.png
Greyscale
, where d is the set of travel times [i.e. first observed travel time], G(m) [i.e. travel time equation] is the calculated set of travel times for the current model m [i.e. first travel time value output by the trainable travel time network], {circumflex over (d)} is the gradient of the set of travel times, Ĝ(m) is the calculated gradient of the set of travel times [i.e. derivative of the travel times equation], D is a regularization, τ is a smoothing trade-off parameter, and ω is a weighting factor.” – [0040]).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma to incorporate the teaching of Sun to minimize the cost function that is based on the difference between the set of travel times and the calculated set of travel times for the model m, the gradient of the set of travel times and calculated set of travel times. By minimizing this objective function, this is an improvement that yields predictable results in the evaluation of seismic data (sonic data) for the determination of the tomography of subterranean features for discovering oil and gas resources.
In regards to Claims 2, 6, and 13, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “the trainable velocity network comprises a first neural network (A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters. – [0019]), and
the trainable travel time network comprises a second neural network (A travel time field neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 4 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate the forward travel time field process. - [0018]).
In regards to Claims 3, 7, and 14, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “wherein the travel times equation is further based on an Eikonal equation (first-arrival time tomography network model, eikonal equation – [0014]).”
In regards to Claims 4 and 15, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “wherein the cost function is further based on an interface condition associated with the travel times equation (First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An [eikonal] equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model [i.e. travel times equation] is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]).”
In regards to Claim 5, Ma teaches “obtaining a first plurality of prediction locations discretizing a region of interest (positions xn,i, yn,i – [0023]);
obtaining a trained velocity network configured to receive, as input, a prediction location in the region of interest and return, as output, a velocity value at the prediction location, the trained velocity network based on one or more trained velocity parameters (construct a travel-time field neural network and a velocity neural network – [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]; A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters [i.e. output a velocity value]. – [0019]; Where, is the total number of micrologging velocities, is the horizontal position of the micrologging, is the micrologging velocity at the horizontal position output by the velocity neural network, and is the actual micrologging velocity at the horizontal position - [0029]; Vtheta2 is the squared velocity at position xnj, ynj [i.e. prediction location], output by the velocity neural network- [0038]), wherein the one or more trained velocity parameters are determined by using an optimizer that seeks to minimize a cost fiction based on (In step S4.1, the training and iteration process of the first arrival wave travel time tomography network model involves calculating the loss function based on the parameters of the current neural network model and performing backpropagation. This process synchronously updates the model parameters of the travel time field neural network and the velocity neural network to reduce the loss function. This is achieved using the Adam optimizer. - [0044]):
a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on a trainable velocity network and a trainable travel time network (First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An [eikonal] equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model [i.e. travel times equation] is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]), wherein:
the trainable velocity network is based on one or more velocity parameters (construct a travel-time field neural network and a velocity neural network – [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]; A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters [i.e. output a velocity value]. – [0019]; Where, is the total number of micrologging velocities, is the horizontal position of the micrologging, is the micrologging velocity at the horizontal position output by the velocity neural network, and is the actual micrologging velocity at the horizontal position - [0029]);
the one or more velocity parameters are received by the cost function as inputs (First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]), and
the trained velocity network is obtained upon replacing, in the trainable velocity network, the one or more velocity parameters with the one or more trained velocity parameters (Construct a travel-time field neural network and a velocity neural network – [0013]; Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. - [0014]; A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters. - [0019]; Micrologging velocity constraints are set for the velocity neural network constructed in step S2. The expression for the micrologging velocity constraint term is:
PNG
media_image3.png
137
552
media_image3.png
Greyscale
- [0027]), and
determining a velocity model for the region of interest, the velocity model comprising one velocity value for each prediction location within the first plurality of prediction locations, wherein, for each prediction location, the velocity value is determined by inputting the prediction location to the trained velocity network (Furthermore, the specific implementation method of step S5 is to input the positions of all coordinate points in the model space to be predicted from the data test set obtained in step S1 into the first-arrival wave travel-time tomography network model trained in step S4, and output the velocity parameters in the model space to be predicted, thereby obtaining the near-surface velocity first-arrival wave travel-time tomography prediction result. - [n0011]; Figure 2-C and Figure 3-C show the first arrival travel time tomography results).”
Ma is silent with regards to the language of “using an optimizer that seeks to minimize a cost fiction based on: a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on a trainable velocity network and a trainable travel time network; a derivative of the travel times equation.”
Sun teaches “using an optimizer that seeks to minimize a cost fiction based on: a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on a trainable velocity network and a trainable travel time network; a derivative of the travel times equation (“Still another radial tomography method proposed by Zhang and Toksöz (“Nonlinear refraction traveltime tomography.” Geophysics 63.5 (1998): 1726-1737) may determine a velocity map along the axis of the wellbore ( 102 ) and radially away from the wellbore ( 102 ) using a still further alternate inversion scheme. A shortest path raytracing method with an optimized node distribution within a grid that represents a rock formation ( 104 ) is used to calculate travel times and ray paths for any velocity model. The nonlinear regularized inverse problem minimizes the residuals of the objective function [i.e. minimize the cost function]:
PNG
media_image2.png
36
355
media_image2.png
Greyscale
, where d is the set of travel times [i.e. first observed travel time], G(m) [i.e. travel time equation] is the calculated set of travel times for the current model m [i.e. first travel time value output by the trainable travel time network], {circumflex over (d)} is the gradient of the set of travel times, Ĝ(m) is the calculated gradient of the set of travel times [i.e. derivative of the travel times equation], D is a regularization, τ is a smoothing trade-off parameter, and ω is a weighting factor.” – [0040]).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma to incorporate the teaching of Sun to minimize the cost function that is based on the difference between the set of travel times and the calculated set of travel times for the model m, the gradient of the set of travel times and calculated set of travel times. By minimizing this objective function, this is an improvement that yields predictable results in the evaluation of seismic data (sonic data) for the determination of the tomography of subterranean features for discovering oil and gas resources.
In regards to Claim 8, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “obtaining, from a seismic acquisition system, a seismic dataset of seismic traces pertaining to a region of interest (Collect data including spatial sampling point location data, shot point location data, geophone point location data, first arrival wave travel time data, micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]),
wherein each seismic trace within the seismic dataset comprises a seismic source location and a seismic receiver location (Collect data including spatial sampling point location data, shot point location data [i.e. seismic source location], geophone point location data [i.e. seismic receiver location], first arrival wave travel time data, micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]), and
wherein, for each seismic trace, a receiver at the seismic receiver location of the seismic trace detects ground motion of a seismic wave radiating from the seismic source location of the seismic trace (Collect data including spatial sampling point location data, shot point location data, geophone [i.e. seismic receiver that detects ground motion of a seismic wave] point location data, first arrival wave travel time data, micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]), and
forming a seismic image of the region of interest based on the seismic dataset and the velocity model (Furthermore, the specific implementation method of step S5 is to input the positions of all coordinate points in the model space to be predicted from the data test set obtained in step S1 into the first-arrival wave travel-time tomography network model trained in step S4, and output the velocity parameters in the model space to be predicted, thereby obtaining the near-surface velocity first-arrival wave travel-time tomography prediction result. - [n0011]; Figure 2-C and Figure 3-C show the first arrival travel time tomography results [i.e. an image of a velocity model]).”
In regards to Claim 12, Ma teaches “a seismic acquisition system configured to acquire a seismic dataset of seismic traces pertaining to a region of interest, wherein each seismic trace within the seismic dataset comprising a seismic source location and a seismic receiver location, and wherein, for each seismic trace, a receiver at the seismic receiver location of the seismic trace detects ground motion of a seismic wave radiating from the seismic source location of the seismic trace (Collect data including spatial sampling point location data [i.e. seismic source location], shot point location data, geophone point location data [i.e. seismic receiver location], first arrival wave travel time data, micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]), and
a seismic processing system (A system for a first-arrival travel-time tomography method based on multi-source information fusion includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed, it implements the steps of the first-arrival travel-time tomography method based on multi-source information fusion - [n0012]), configured to:
receive the seismic dataset from the seismic acquisition system (Collect data including spatial sampling point location data, shot point location data, geophone point location data, first arrival wave travel time data, micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set; - [0012]);
determine, for each seismic trace within the seismic dataset, an observed travel time between the seismic source location of the seismic trace and the seismic receiver location of the seismic trace (Collect data including spatial sampling point location data, shot point location data, geophone point location data, first arrival wave travel time data [i.e. observed travel time], micrologging velocity data, and surface geological outcrop stratigraphic data to construct a data training set and a data test set - [0012]);
form a trainable velocity network configured to receive, as input, a prediction location in the region of interest and return, as output, a velocity value, wherein the trainable velocity network depends on one or more velocity parameters (construct a travel-time field neural network and a velocity neural network – [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]; A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters [i.e. output a velocity value]. – [0019]; Where, is the total number of micrologging velocities, is the horizontal position of the micrologging, is the micrologging velocity at the horizontal position output by the velocity neural network, and is the actual micrologging velocity at the horizontal position - [0029]; Vtheta2 is the squared velocity at position xnj, ynj [i.e. prediction location], output by the velocity neural network- [0038]);
forma a trainable travel time network configured to receive, as input, a source location and a prediction location and return, as output, a travel time value, wherein the trainable travel time network depends on one or more travel time parameters (construct a travel-time field neural network and a velocity neural network – [0013]; A travel time field neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 4 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate the forward travel time field process. - [0018]; First-arrival travel time constraints are set for the travel time field neural network constructed in step S2. To constrain the travel time data acquired through sparse detectors, the expression for the first-arrival travel time constraint term is as follows:- [0021];
PNG
media_image1.png
65
362
media_image1.png
Greyscale
- [0022]; Where Ns is the total number of shot points, Nt is the total number of receiver points corresponding to each shot point, (xni, yni) is the position of the nth shot point [i.e. source location] and the ith receiver point [i.e. prediction location], Ttheta(xni, yni) [i.e. travel time value output] is the travel time of the position output by the travel time field neural network, and T-tilda (xni, yni) is the observed travel time of the position (xni, yni).- [0023]; The training process first requires the input point position coordinates to be given in space. After the network is trained, the velocity and travel time corresponding to the input point are generated. - [0043]), and
train the trainable travel time network and the trainable velocity network (Construct [i.e. training] a travel-time field neural network and a velocity neural network - [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]), wherein training the trainable travel time network and the trainable velocity network comprises:
obtaining a travel times equation modeling a travel time of a seismic wave in the region of interest according to a seismic velocity, the travel times equation based on the trainable travel time network and the trainable velocity network (First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An [eikonal] equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model [i.e. travel times equation] is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]);
constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output (The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model - [0014]), a cost based on:
the travel times equation (first-arrival time tomography network model, eikonal equation – [0014]);
computing, with an optimizer, one or more trained travel times parameters and one or more trained velocity parameters, wherein the optimizer is configured to seek to minimize the cost function (In step S4.1, the training and iteration process of the first arrival wave travel time tomography network model involves calculating the loss function based on the parameters of the current neural network model and performing backpropagation. This process synchronously updates the model parameters of the travel time field neural network and the velocity neural network to reduce the loss function. This is achieved using the Adam optimizer. - [0044]).”
Ma is silent with regards to the language of “constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output, a cost based on: the travel times equation; a derivative of the travel times equation, and a travel time mismatch between: a first observed travel time between a first seismic source location and a first seismic receiver location, and a first travel time value output by the trainable travel time network upon receiving, as inputs, the first seismic source location and the first seismic receiver location.”
Sun teaches “constructing a cost function configured to receive, as inputs, the one or more travel times parameters and the one or more velocity parameters and return, as output, a cost based on: the travel times equation; a derivative of the travel times equation, and a travel time mismatch between: a first observed travel time between a first seismic source location and a first seismic receiver location, and a first travel time value output by the trainable travel time network upon receiving, as inputs, the first seismic source location and the first seismic receiver location (“Still another radial tomography method proposed by Zhang and Toksöz (“Nonlinear refraction traveltime tomography.” Geophysics 63.5 (1998): 1726-1737) may determine a velocity map along the axis of the wellbore ( 102 ) and radially away from the wellbore ( 102 ) using a still further alternate inversion scheme. A shortest path raytracing method with an optimized node distribution within a grid that represents a rock formation ( 104 ) is used to calculate travel times and ray paths for any velocity model. The nonlinear regularized inverse problem minimizes the residuals of the objective function [i.e. minimize the cost function]:
PNG
media_image2.png
36
355
media_image2.png
Greyscale
, where d is the set of travel times [i.e. first observed travel time], G(m) [i.e. travel time equation] is the calculated set of travel times for the current model m [i.e. first travel time value output by the trainable travel time network], {circumflex over (d)} is the gradient of the set of travel times, Ĝ(m) is the calculated gradient of the set of travel times [i.e. derivative of the travel times equation], D is a regularization, τ is a smoothing trade-off parameter, and ω is a weighting factor.” – [0040]).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma to incorporate the teaching of Sun to minimize the cost function that is based on the difference between the set of travel times and the calculated set of travel times for the model m, the gradient of the set of travel times and calculated set of travel times. By minimizing this objective function, this is an improvement that yields predictable results in the evaluation of seismic data (sonic data) for the determination of the tomography of subterranean features for discovering oil and gas resources.
In regards to Claim 16, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “form a trained velocity network by replacing, in the trainable velocity network, the one or more velocity parameters with the one or more trained velocity parameters (Construct a travel-time field neural network and a velocity neural network – [0013]; Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. - [0014]; A velocity neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 2 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate and inversely solve for velocity parameters. - [0019]; Micrologging velocity constraints are set for the velocity neural network constructed in step S2. The expression for the micrologging velocity constraint term is:
PNG
media_image3.png
137
552
media_image3.png
Greyscale
- [0027]), and
determine a velocity model for the region of interest, the velocity model comprising one velocity value for each prediction location within a first plurality of prediction locations, wherein, for each prediction location within a first plurality of prediction locations, the velocity value is determined by inputting the prediction location to the trained velocity network (Furthermore, the specific implementation method of step S5 is to input the positions of all coordinate points in the model space to be predicted from the data test set obtained in step S1 into the first-arrival wave travel-time tomography network model trained in step S4, and output the velocity parameters in the model space to be predicted, thereby obtaining the near-surface velocity first-arrival wave travel-time tomography prediction result. - [n0011]; Figure 2-C and Figure 3-C show the first arrival travel time tomography results).”
In regards to Claim 17, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “wherein the seismic processing system is further configured to form a seismic image of the region of interest based on the seismic dataset and the velocity model (Furthermore, the specific implementation method of step S5 is to input the positions of all coordinate points in the model space to be predicted from the data test set obtained in step S1 into the first-arrival wave travel-time tomography network model trained in step S4, and output the velocity parameters in the model space to be predicted, thereby obtaining the near-surface velocity first-arrival wave travel-time tomography prediction result. - [n0011]; Figure 2-C and Figure 3-C show the first arrival travel time tomography results [i.e. an image of a velocity model]).”
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Ma in view of Sun as applied to claim 8 and 17 above, and further in view of Liu (US20230184976).
In regards to claim 9, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “obtaining a trained travel time network configured to receive, as input, a source location in the region of interest and a prediction location in the region of interest and return, as output, a travel time value of a seismic wave between the source location and the prediction location, the trained travel time network based on one or more trained travel time parameters (construct a travel-time field neural network and a velocity neural network – [0013]; A travel time field neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 4 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate the forward travel time field process. - [0018]; First-arrival travel time constraints are set for the travel time field neural network constructed in step S2. To constrain the travel time data acquired through sparse detectors, the expression for the first-arrival travel time constraint term is as follows:- [0021];
PNG
media_image1.png
65
362
media_image1.png
Greyscale
- [0022]; Where Ns is the total number of shot points, Nt is the total number of receiver points corresponding to each shot point, (xni, yni) is the position of the nth shot point [i.e. source location] and the ith receiver point [i.e. prediction location], Ttheta(xni, yni) [i.e. travel time value output] is the travel time of the position output by the travel time field neural network, and T-tilda (xni, yni) is the observed travel time of the position (xni, yni).- [0023]; The training process first requires the input point position coordinates to be given in space. After the network is trained, the velocity and travel time corresponding to the input point are generated. - [0043]), wherein:
the one or more trained travel time parameters are determined using the optimizer;
the trainable travel time network is based on one or more travel time parameters (In step S4.1, the training and iteration process of the first arrival wave travel time tomography network model involves calculating the loss function based on the parameters of the current neural network model and performing backpropagation. This process synchronously updates the model parameters of the travel time field neural network and the velocity neural network to reduce the loss function. This is achieved using the Adam optimizer. - [0044]);
the cost function further receives, as inputs, the one or more travel time parameters (First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]), and
the trained travel time network is obtained upon replacing, in the trainable travel time network, the one or more travel time parameters with the one or more trained travel time parameters (Construct a travel-time field neural network and a velocity neural network – [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]; A travel time field neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 4 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate the forward travel time field process- [0018]; Boundary condition constraints are set for the travel-time field neural network constructed in step S2, such that the travel time of the first arrival wave corresponding to the nth shot point is 0. The expression for the boundary condition constraint term is as follows:
PNG
media_image4.png
118
395
media_image4.png
Greyscale
- [0024]);
obtaining, a plurality of source locations in the region of interest (Collect data including spatial sampling point location data, shot point location data [i.e. source locations], geophone point location data - [0012]).”
Ma in view of Sun is silent with regards to the language of “obtaining a second plurality of prediction locations discretizing the region of interest, and
determining a travel time cube for the region of interest, the travel time cube comprising one travel time value for each pair composed of a source location within the plurality of source locations and prediction location within the second plurality of prediction locations wherein, for each a source location and each prediction location, the travel time value is determined by inputting the pair composed of the source location and the prediction location to the trained travel time network,
wherein forming the seismic image is based on the travel time cube.”
Liu teaches “obtaining a second plurality of prediction locations discretizing the region of interest (“In Step 610, the seismic partial images may be stored. Storage may be in any type of memory architecture having the capability to store the seismic partial images without departing from the scope of the invention. In some embodiments, the seismic partial image may be a portion of a Kirchhoff migrated stacked seismic image delimited by a geographical boundary. In other embodiments, the seismic partial image may be a contribution from a subset of seismic source locations (206) and a subset of seismic receiver locations (220) [i.e. the subset of locations is a second plurality of locations that discretize the region of interest] to a portion of a Kirchhoff migrated stacked seismic image delimited by a geographical boundary.” – [0042]); determining a travel time cube for the region of interest, the travel time cube comprising one travel time value for each pair composed of a source location within the plurality of source locations and prediction location within the second plurality of prediction locations wherein, for each a source location and each prediction location, the travel time value is determined by inputting the pair composed of the source location and the prediction location to the trained travel time network (“In general, in one aspect, embodiments relate to a system for forming three-dimensional (“3D”) seismic image of a subterranean region of interest including a seismic acquisition system, and a seismic processor configured to receive a seismic dataset from the seismic acquisition system, wherein the seismic dataset includes a plurality of source locations, a plurality of receiver locations, and a seismic trace for each pair of one source location and one receiver location, receive a 3D travel-time cube for each source location and each receiver location, and divide the seismic dataset into a plurality of seismic subsets, each subset comprising: a first set of source locations; a second set of receiver locations; the seismic trace for each pair of one source location from the first set and one receiver location from the second set; and the 3D travel-time cube for each source in the first set and 3D travel-time cube for each source in the second set, wherein a first size of the first set and a second size of the second set differ by less than fifty percent of an average of the first size and the second size; for each seismic subset; transmit, to a random-access memory block of a computer processing unit (“CPU”), the seismic subset; form, using the CPU, a seismic partial image based, at least in part, on the seismic subset; and determine the 3D seismic image based, at least in part, on a combination of the seismic partial image for each seismic subset” – [0006]; “A two-way travel time cube ( 306 ), TWT(x, y, z), for a source location ( 206 ) and a receiver location ( 220 ), represents the predicted travel time taken for a seismic wave to propagated from the source location ( 206 ) to a position (x, y, z) in the subsurface from the position TWT(x, y, z) to the receiver location ( 220 ). The two-way travel time cube is invariant with respect to switching the receiver location ( 220 ) to the source location ( 206 ) and the source location ( 106 ) to the receiver location ( 220 ). The source travel time cube ( 306 ) may be determined from a seismic velocity model, that specifies the seismic propagation velocity at, at least, a sampling of points within the subsurface, by solving an eikonal equation for a source location ( 206 ). Similarly, the receiver travel time cube ( 308 ) may be determined from the seismic velocity model and a receiver location ( 220 ). Frequently, both the seismic velocity model and a 3D travel time cube will be defined on a grid of position points representing the subsurface” – [0028]),
wherein forming the seismic image is based on the travel time cube (“The seismic processing algorithm requires a plurality of seismic traces, together with a source travel time cube and a receiver travel time cube for each trace to generate a seismic partial image ( 412 )” – [0030]).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma in view of Sun to incorporate the teaching of Liu to utilize travel time cubes. By utilizing travel time cubes, this is an improvement that yields predictable results in the evaluation of the seismic data to determine the locations of hydrocarbon reservoirs in subterranean regions of interest.
In regards to claim 18, Ma in view of Sun discloses the claimed invention as detailed above. Ma further teaches “the seismic processing system is further configured to:
form a trained travel time network by replacing, in the trainable travel time network, the one or more travel time parameters with the one or more trained travel time parameters (Construct a travel-time field neural network and a velocity neural network – [0013]; First-arrival travel time constraints and boundary condition constraints are set for the travel time field neural network constructed in step S2. Micro-logging velocity constraints and surface geological outcrop stratigraphic information constraints are set for the velocity neural network. An equation is set to connect the travel time field neural network and the velocity neural network as the equation constraint conditions for the travel time field neural network and the velocity neural network. The first-arrival travel time tomography network model is constructed and the loss function is set to obtain the first-arrival travel time tomography network model. - [0014]; A travel time field neural network is constructed, comprising an input layer, a hidden layer, and an output layer. The input layer is connected to the hidden layer, and the hidden layer is connected to the output layer. The input layer consists of 4 neurons, the hidden layer consists of 20 fully connected layers, each of which consists of 50 neurons, and the output layer consists of 1 neuron. This network is used to simulate the forward travel time field process- [0018]; Boundary condition constraints are set for the travel-time field neural network constructed in step S2, such that the travel time of the first arrival wave corresponding to the nth shot point is 0. The expression for the boundary condition constraint term is as follows:
PNG
media_image4.png
118
395
media_image4.png
Greyscale
- [0024]).”
Ma in view of Sun is silent with regards to the language of “determine a travel time cube for the region of interest, the travel tune cube comprising one travel time value for each pair composed of a source location within a plurality of source locations and prediction location within a second plurality of prediction locations wherein, for each a source location within a plurality of source locations and each prediction location within the second plurality of prediction locations, the travel time value is determined by inputting a pair composed of the source location and the prediction location to the trained travel time network, and
forming the seismic image is based on the travel time cube.”
Liu teaches “determine a travel time cube for the region of interest, the travel tune cube comprising one travel time value for each pair composed of a source location within a plurality of source locations and prediction location within a second plurality of prediction locations wherein, for each a source location within a plurality of source locations and each prediction location within the second plurality of prediction locations, the travel time value is determined by inputting a pair composed of the source location and the prediction location to the trained travel time network (“In general, in one aspect, embodiments relate to a system for forming three-dimensional (“3D”) seismic image of a subterranean region of interest including a seismic acquisition system, and a seismic processor configured to receive a seismic dataset from the seismic acquisition system, wherein the seismic dataset includes a plurality of source locations, a plurality of receiver locations, and a seismic trace for each pair of one source location and one receiver location, receive a 3D travel-time cube for each source location and each receiver location, and divide the seismic dataset into a plurality of seismic subsets, each subset comprising: a first set of source locations; a second set of receiver locations; the seismic trace for each pair of one source location from the first set and one receiver location from the second set; and the 3D travel-time cube for each source in the first set and 3D travel-time cube for each source in the second set, wherein a first size of the first set and a second size of the second set differ by less than fifty percent of an average of the first size and the second size; for each seismic subset; transmit, to a random-access memory block of a computer processing unit (“CPU”), the seismic subset; form, using the CPU, a seismic partial image based, at least in part, on the seismic subset; and determine the 3D seismic image based, at least in part, on a combination of the seismic partial image for each seismic subset” – [0006]; “A two-way travel time cube ( 306 ), TWT(x, y, z), for a source location ( 206 ) and a receiver location ( 220 ), represents the predicted travel time taken for a seismic wave to propagated from the source location ( 206 ) to a position (x, y, z) in the subsurface from the position TWT(x, y, z) to the receiver location ( 220 ). The two-way travel time cube is invariant with respect to switching the receiver location ( 220 ) to the source location ( 206 ) and the source location ( 106 ) to the receiver location ( 220 ). The source travel time cube ( 306 ) may be determined from a seismic velocity model, that specifies the seismic propagation velocity at, at least, a sampling of points within the subsurface, by solving an eikonal equation for a source location ( 206 ). Similarly, the receiver travel time cube ( 308 ) may be determined from the seismic velocity model and a receiver location ( 220 ). Frequently, both the seismic velocity model and a 3D travel time cube will be defined on a grid of position points representing the subsurface” – [0028]), and
forming the seismic image is based on the travel time cube (“The seismic processing algorithm requires a plurality of seismic traces, together with a source travel time cube and a receiver travel time cube for each trace to generate a seismic partial image ( 412 )” – [0030]).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma in view of Sun to incorporate the teaching of Liu to utilize travel time cubes. By utilizing travel time cubes, this is an improvement that yields predictable results in the evaluation of the seismic data to determine the locations of hydrocarbon reservoirs in subterranean regions of interest.
Claims 10-11 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Ma in view of Sun as applied to claim 8 and 17 above, and further in view of Zhu (US20230046786).
In regards to Claims 10 and 19, Ma in view of Sun discloses the claimed invention as detailed above. Ma in view of Sun is silent with regards to the language of “a seismic interpretation workstation, configured to: receive the seismic image from the seismic processing system, and identify a drilling target based, at least in part, on the seismic image, and a well planning system, configured to: receive the drilling target from the seismic interpretation workstation, and plan a wellbore trajectory guided by the drilling target.”
Zhu teaches “a seismic interpretation workstation, configured to: receive the seismic image from the seismic processing system, and identify a drilling target based, at least in part, on the seismic image, and a well planning system, configured to: receive the drilling target from the seismic interpretation workstation, and plan a wellbore trajectory guided by the drilling target (“FIG. 8 illustrates systems in accordance with one or more embodiments. As shown in FIG. 8, a well (802) may be drilled by a drill bit (804) attached by a drillstring (806) to a drill rig (808) located on the Earth's surface (116). The well may traverse a plurality of overburden layers (810) and one or more cap-rock layers (812) to a hydrocarbon reservoir (814). In accordance with one or more embodiments, the artifact attenuated seismic image, as shown in FIG. 7B, may be used to identify portions of the subsurface with a likelihood of a presence of a hydrocarbon reservoir(814) and to plan the trajectory of the well (802).” – [0055]; “identifying a portion of a subterranean region of interest with a likelihood of containing hydrocarbons based, at least in part, on the artifact attenuated seismic image; determining a well path through the subterranean region of interest based, at least in part, on the identified portion of the subterranean region of interest; and performing the well path using a drilling system” – Claim 2).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify ma in view of Sun to incorporate the teaching of Zhu to utilize the seismic image to determine the trajectory for a wellbore and to drill the wellbore. By utilizing the seismic image to determine the trajectory of the wellbore this is an improvement to the determination and extraction of hydrocarbons from subterranean features.
In regards to Claims 11 and 20, Ma in view of Sun and Zhu discloses the claimed invention as detailed above. Ma is silent with regards to the language of “receive the wellbore trajectory from the well planning system, and drill a wellbore guided by the wellbore trajectory.
Zhu further teaches “receive the wellbore trajectory from the well planning system, and drill a wellbore guided by the wellbore trajectory (“identifying a portion of a subterranean region of interest with a likelihood of containing hydrocarbons based, at least in part, on the artifact attenuated seismic image; determining a well path through the subterranean region of interest based, at least in part, on the identified portion of the subterranean region of interest; and performing the well path using a drilling system” – Claim 2).”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify ma in view of Sun to incorporate the teaching of Zhu to utilize the seismic image to determine the trajectory for a wellbore and to drill the wellbore. By utilizing the seismic image to determine the trajectory of the wellbore this is an improvement to the determination and extraction of hydrocarbons from subterranean features.
Examiner’s Note
The following prior art, while not utilized in a prior art rejection, are considered to be of interest:
Biondi (US20240427045) teaches in [0042]-[0045] the minimizing of an objective function of travel times to obtain coordinates of seismic events.
Sun’325 (US20220317325) teaches in [0058] utilizing seismic images to plan locations to drill a borehole and plan the trajectory of the borehole.
Zhang (US20190324167) teaches in [0051] minimizing an objective function with travel times and derivative operators.
Bush (US7525873) teaches on Column 14 a gradient method to minimize an objective function in terms of unknown reflection coefficients and travel times.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YOSSEF KORANG-BEHESHTI whose telephone number is (571)272-3291. The examiner can normally be reached Monday - Friday 10:00 am - 6:30 pm.
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, Catherine Rastovski can be reached at (571) 270-0349. 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.
/YOSSEF KORANG-BEHESHTI/Primary Examiner, Art Unit 2857