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 .
Response to Amendment/Arguments
(Submitted 12/8/2025)
Applicant’s arguments with respect to claims 1, 7 and 14 have been considered but are moot because
the new ground of rejection does not rely on any reference applied in the prior rejection of record for
any teaching or matter specifically challenged in the argument. The examiner has used two new
references “Ram” and “Dorn” to teach the amended claims 1, 7 and 14.
In regard to 101 Rejections
- The applicant argues on Page 8-11 specific to the examiner in the previous Office Action that the “selecting a point with the geometric shape” and “ determining the selected grouping of the subsurface image data” are abstract ideas. Further on Page 9, the applicant argues that using the context of Step 2A and Step 2B, the examiner “should evaluate” whether the claim contains the improvement to technical function of a computer. Specifically, the applicant argued that providing a trained model that fits the training data set are necessary for evaluation.
Examiner’s Response
First, examiner submits that the applicant has amended the claims 1, 7 and 14 that recites”
“label locations [[in]] within each grouping that include a horizon that passes through the selected for each respective grouping, each location labeled having a geological age approximately equal to the geological age at the selected point within each respective grouping of subsurface image data”. The examiner submits that providing a trained model that fits the training data to an algorithmic model is generally not sufficient on its own to overcome "101 rejections". It is merely applying a standard machine learning algorithm to a dataset is often deemed an "abstract idea". The "Improvement" must come from showing increased efficiency, better accuracy, reduced memory usage(as example) rather than just a new use of an old algorithm. The claims are showing "training a model" or "using a neural network" without describing a specific, improved training process or a specialized, improved model structure. The examiner recognizes the specification [0042] recites “ The algorithm continues at block 64. At block 64, the algorithm determines if a trained algorithmic model generates predictive results in a manner that satisfies a performance criteria, such as for efficiency and accuracy”. However, the examiner submits that an algorithm that determines if a trained model satisfies performance criteria (such as accuracy, precision, and recall) is considered a model improvement (specifically, part of the model evaluation and optimization process). While this process can enhance efficiency, it focuses on refining the model's predictive capabilities rather than directly improving the computer hardware or underlying computing infrastructure. The present argument of the applicant does not overcome 101 rejections. The steps of labeling geological ages along horizons, in isolation, constitute a mental process as a method of organizing geological data. In summary, a model that fits the data is required for functionality. The examiner submits that only a model that provides a demonstrable technical improvement is necessary to overcome 101 rejections. The examiner submits that neural network (NN) model may not be needed, or that it is not patent-eligible, as the examiner strongly interprets that the application only presents a seismic data interpretation and horizon prediction without providing a specific, technical improvement to computer functionality within the context of a seismic application. In overall, the examiner submits that there is nothing detailed neural network model characterization and its broad results are provided in the claim limitations to seismic data.
In CONCLUSION, the examiner MAINTAINS the 101 rejections on independent claims 1, 7, and 14 and on all dependent claims 2-6, 8-13 and 15-20.
In regard to 103 Rejections
- The applicant on Page 11-15 argues specifically on reference “Tschan” stating that the current references fails to teach the single horizon (Pages 12-13).
Examiner’s Response
The examiner has considered the applicant’s arguments respect to claims 1, 7 and 14 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Claims 2-3, 6-9, 12-16, and 19-20 that are relevant to amendments have been taught by new references “Ram” and “Dorn”. The teaching for claims 4-5,10-11 and 17-18 have been retained by reference “Imhof”.
In CONCLUSION, the examiner rejects claim 1, 7, and 14 and on all dependent claims 2-6, 8-13 and 15-20 under 103 and MOVES the application to FINAL REJECTION under 103.
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 1-20 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
According to the first part of the analysis, claim 1 and claim 7 are apparatus and system claims. Claim 14 is a method claim. Thus, claims 1, 7 and 14 does fall into any one of the four statutory categories (i.e. process, machine, manufacture, or composition of matter).
In regard to claim 1: (Currently Amended)
Step 2A Prong 1:
“ select groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” is a mental process of mathematics concepts.
(Note: Without specific technical limitations, "selecting" data based on a "shared geometric shape" is considered an abstract mathematical concept)
“ select a point within the shared geometric shape” is a mental step of finding a point within the intersection of two geometric shapes.
“ label locations [[in]] within each grouping that include a horizon that passes through the selected point for each respective grouping, each location labeled having a geological age approximately equal to the geological age at the selected point within each respective grouping of subsurface image data;” is a mental step of finding a point within the intersection of two geometric shapes.
(Note: without any technical improvement related in this phrase, this simply a data analysis and interpretation)
“fitting the at least one training set tomental process of data fitting as a mathematical concept unless it is tied to a specific technological improvement
Step 2A Prong 2:
“An apparatus for generating a trained algorithmic model, the apparatus comprising:” recited in the preamble do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ tracking and data preprocessing module that includes a processor, the processor configured to: “do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“receive seismic data representing a geological formation” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“create at least one training data set based on the labeled groupings of subsurface image data” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ and generate a trained algorithmic model “ do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“An apparatus for generating a trained algorithmic model, the apparatus comprising:” recited in the preamble does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ tracking and data preprocessing module that includes a processor, the processor configured to: receive seismic data representing a geological formation select groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ a training module configured by a processor to:” ” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“create at least one training data set based on the labeled groupings of subsurface image data” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“and generate a trained algorithmic model” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 2: (Previously Presented)
Step 2A Prong 1:
“each grouping of subsurface image data has a plurality of spatial coordinates values and a common depth value associated with the plurality of spatial coordinates, wherein the common depth value is unique to each grouping” is mental step of data association.
Step 2A Prong 2: no additional elements
Step 2B: no additional elements
In regard to claim 3: (Previously Presented)
Step 2A Prong 2:
“the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“ “the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 4: (Previously Presented)
Step 2A Prong 2:
“the horizon locations are determined using the corresponding geological age model [[,]] and the subsurface image data for each grouping” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“the horizon locations are determined using the corresponding geological age model [[,]] and the subsurface image data for each grouping” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 5: (Currently Amended)
Step 2A Prong 2:
“wherein the selected point for each grouping is at midpoint of the grouping and wherein the horizon is determined based on the midpoint, a contour and a geographical age model” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“wherein the selected point for each grouping is at midpoint of the grouping and wherein the horizon is determined based on the midpoint, a contour and a geographical age model” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 6: (Currently Amended)
Step 2A Prong 2:
“generating a trained algorithmic includes applying a convolutional neural network” does not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“generating a trained algorithmic includes applying a convolutional neural network” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 7: (Currently Amended)
“ select groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” is a mental process of mathematics concepts.
“ select a point within the shared geometric shape” is a mental step of finding a point within the intersection of two geometric shapes.
“ label locations [[in]] within each grouping that include a horizon that passes through the selected point for each respective grouping, each location labeled having a geological age approximately equal to the geological age at the selected point within each respective grouping of subsurface image data;” is a mental step of finding a point within the intersection of two geometric shapes.
“fitting the at least one training set tomental process of data fitting as a mathematical concept unless it is tied to a specific technological improvement
Step 2A Prong 2:
“A system for generating a trained algorithmic model, the system comprising:” recited in the preamble do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ tracking and data preprocessing module configured by a processor to: receive seismic data representing a geological formation select groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ create, at least one training data set based on the labeled groupings of subsurface image data” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“and generate a trained algorithmic model” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ A storage model, the storage module configured by a processor to store the labeled groupings of subsurface image data ” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“A system for generating a trained algorithmic model, the system comprising:” recited in the preamble does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ tracking and data preprocessing module configured by a processor to: receive seismic data representing a geological formation select groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“create, at least one training data set based on the labeled groupings of subsurface image data” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“and generate a trained algorithmic model “ does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ A storage model, the storage module configured by a processor to store the labeled groupings pf subsurface image data” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 8: (Previously Presented)
Step 2A Prong 1:
“each grouping of subsurface image data has a plurality of spatial coordinates values and a common depth value associated with the plurality of spatial coordinates, wherein the common depth value is unique to each grouping” is mental step of data association.
Step 2A Prong 2: no additional elements
Step 2B: no additional elements
In regard to claim 9: (Previously Presented)
Step 2A Prong 2:
“the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 10: (Previously Presented)
Step 2A Prong 2:
“the horizon locations are determined using the corresponding geological age model [[,]] and the subsurface image data for each grouping” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“the horizon locations are determined using the corresponding geological age model [[,]] and the subsurface image data for each grouping” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 11: (Previously Presented)
Step 2A Prong 2:
“wherein the selected point for each grouping is at midpoint of the grouping and wherein the horizon is determined based on the midpoint, a contour and a geographical age model” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“wherein the selected point for each grouping is at midpoint of the grouping and wherein the horizon is determined based on the midpoint, a contour and a geographical age model” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 12: (Currently Amended)
Step 2A Prong 2:
“generating a trained algorithmic model includes applying a convolutional neural network” does not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“generating a trained algorithmic model includes applying a convolutional neural network” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 13: (Currently Amended)
Step 2A Prong 2:
“ predictive engine module configured by a processor to generate predictive results that identify horizon passing through the selected point of each of the groupings of subsurface of image data using the trained algorithmic model ” does not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“ predictive engine module configured by a processor to generate predictive results that identify horizon passing through the selected point of each of the groupings of subsurface of image data using the trained algorithmic model ” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 14: (Currently Amended)
Step 2A Prong 1:
“ selecting groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” is a mental process of mathematics concepts.
“ selecting a common point within the shared geometric shape” is a mental step of finding a point within the intersection of two geometric shapes.
“ labeling locations [[in]] within each grouping that include a horizon that passes through the selected point for each respective grouping, each location labeled having a geological age approximately equal to the geological age at the selected point within each respective grouping of subsurface image data;” is a mental step of finding a point within the intersection of two geometric shapes.
“fitting the at least one training set tomental process of data fitting as a mathematical concept unless it is tied to a specific technological improvement
Step 2A Prong 2:
“A method for generating a trained algorithmic model, the method comprising:” recited in the preamble do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“receiving seismic data representing a geological formation” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ creating at least one training data set based on the labeled groupings of subsurface image data” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“and generating a trained algorithmic model” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ storing labeled groupings of subsurface image data” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
A method for generating a trained algorithmic model, the method comprising:” recited in the preamble does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ tracking and data preprocessing module configured by a processor to: receive seismic data representing a geological formation select groupings of subsurface image data from the received seismic data, wherein the selected groupings have a shared geometric shape” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“creating at least one training data set based on the labeled groupings of subsurface image data” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“and generate a trained algorithmic model” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
“ A storing the labeled groupings of subsurface image data” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 15: (Previously Presented)
Step 2A Prong 1:
“each grouping of subsurface image data has a plurality of spatial coordinates values and a common depth value associated with the plurality of spatial coordinates, wherein the common depth value is unique to each grouping” is mental step of data association.
Step 2A Prong 2: no additional elements
Step 2B: no additional elements
In regard to claim 16: (Original)
Step 2A Prong 2:
“the tracking module selects groupings that form image tiles, with each tile having a predetermined size” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“the tracking module selects groupings that form image tiles, with each tile having a predetermined size” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 17: (Previously Presented)
Step 2A Prong 2:
“the horizon locations are determined using the corresponding geological age model [[,]] and the subsurface image data for each grouping” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“the horizon locations are determined using the corresponding geological age model [[,]] and the subsurface image data for each grouping” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 18: (Currently Amended)
Step 2A Prong 2:
“wherein the selected common point [[for]] within each grouping is at a midpoint of the grouping and wherein the horizon is determined based on the midpoint, a contour and a geographical age model” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“wherein the selected common point [[for]] within each grouping is at a midpoint of the grouping and wherein the horizon is determined based on the midpoint, a contour and a geographical age model” “does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
In regard to claim 19: (Currently Amended)
Step 2A Prong 2:
“generating a trained algorithmic model includes applying a convolutional neural network” do not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“generating a trained algorithmic model includes applying a convolutional neural network” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Regarding claim 20: (Currently Amended)
Step 2A Prong 2:
“ generating predictive results that identify horizon passing through the selected common point of each of the groupings of subsurface of image data using the trained algorithmic model ” does not integrate the judicial exception into a practical application. These additional elements are merely directed to using a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Step 2B:
“generating predictive results that identify horizon passing through the selected common point of each of the groupings of subsurface of image data using the trained algorithmic model” does not amount to more than the judicial exception in the claim. These additional elements are merely directed to a computer as a tool to perform an abstract idea. See MPEP 2106.05(h).
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-3, and 6 are rejected under 35 U.S.C. 102 (a) (1) as being anticipated over Mats Ramfjord et.al (hereinafter Ram) US 2020/0301036 A1.
In regard to claim 1: (Currently Amended)
Ram discloses:
- An apparatus for generating a trained algorithmic model, the apparatus comprising: a tracking and data preprocessing module that includes a processor, the processor configure to:
In [0111]:
As an example, a workflow may aim to drill into an environment, for example, to form a bore defined by surrounding earth (e.g., rock, fluids, etc.).
In [0111]:
a workflow may utilize one or more frameworks that operate at least in part via a computer (e.g., a computing device, a computing system, etc.).
in [0128]:
The framework 700 can extend workflows into reservoir characterization and earth modelling.
In [0129]:
survey designs can be modelled to ensure quality of a seismic survey, which may account for structural complexity of the model. Such an approach can enable evaluation of how well a target zone will be illuminated. Such an approach may be part of a quality control process (e.g., task) as part of a seismic workflow.
In [0100]:
one or more of the sensors 464 can be provided for tracking pipe, tracking movement of at least a portion of a drillstring, etc.
in [0165]:
As to interpretation, a process referred to as picking may be implemented. For example, manual seismic interpretation can involve rendering a seismic image to a display and picking locations as corresponding to geologic features. Picking may be facilitated through use of a cursor navigable by a mouse, a trackball, etc., through use of a stylus, through use of a finger (e.g., on a touchscreen, a touchpad, etc.), etc. The term pick can be defined as interpreting data such as seismic sections by selecting and tracking marker beds or other events.
(BRI: one or more sensors can be provided for tracking pipe and the movement of at least a portion of a drill string, representing an apparatus that includes a tracking and data preprocessing module
It is known that an interpretation process involving "picking" (selecting/clicking) facilitated by a mouse or trackball, when combined with software that records these actions, represents an apparatus for tracking—specifically mouse tracking or cursor tracking)
- receive seismic data representing a geological formation
In [0027]:
In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 can include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114).
- select groupings of subsurface image data from received seismic data, wherein the selected groupings have shared geometric data,
In [0003]:
A method can include receiving seismic image data; processing the received seismic image data to generate stratigraphic information using a trained convolution neural network that includes channels subjected to convolution, activation and pooling
(BRI: stratigraphic information includes horizon information)
In [0044]:
As an example, reservoir simulation, petroleum systems modeling, etc. may be applied to characterize various types of subsurface environments, including environments such as those of FIG. 1. One or more operations may be performed in an environment based at least in part on such characterization of a subsurface environment or environments (e.g., via acquired data, simulation, modeling, etc.).
PNG
media_image1.png
306
496
media_image1.png
Greyscale
In [0047]:
In basin and petroleum systems modeling, quantities such as temperature, pressure and porosity distributions within the sediments may be modeled
In [0047]:
Modeling may also model geometry with respect to time, for example, to account for changes stemming from geological events (e.g., deposition of material, erosion of material, shifting of material, etc.).
(BRI: in modern subsurface modeling, geological events are often interpreted, modeled, and organized as specific groupings, sequences, or surfaces derived from subsurface image data (such as 3D seismic volumes)
- select a point within the shared geometric shape
In [0225]:
seismic image data acquired via the seismic survey can be tiled where a tile that overlaps with a well can be labeled with at least a portion of the well log data. In such an example, the tile can be tagged for augmentation such that a training data set includes multiple instances of information in that tile, which may be deemed to be more accurate as it includes well log data.
In [0161]:
FIG. 10 shows an example of a seismic image 1000 and some examples of windows of seismic data (e.g., windows or tiles of a seismic image, etc.), labeled A, B, C and D.
In [0092]:
As an example, a drilling operation can include directional drilling where, for example, at least a portion of a well includes a curved axis. For example, consider a radius that defines curvature where an inclination with regard to the vertical may vary until reaching an angle between about 30 degrees and about 60 degrees or, for example, an angle to about 90 degrees or possibly greater than about 90 degrees.
In [0091] :
FIG. 4 also shows some examples of types of holes that may be drilled. For example, consider a slant hole 472, an S-shaped hole 474, a deep inclined hole 476 and a horizontal hole 478.
In [0093] :
a directional well can include several shapes where each of the shapes may aim to meet particular operational demands
(BRI: A selected grouping where each member shares a geometric shape is generally referred to as classification by geometric attribute or geometric shape sorting. In these groupings, objects are collected based on shared characteristics such as the number of sides, corners, or specific geometric forms
- label locations [[in]] within each grouping that include a horizon that passes through the selected point for each respective grouping, each location labeled having a geological age approximately equal to the geological age at the selected point within each respective grouping of subsurface image data;
In [0045]:
n FIG. 2, the sedimentary basin 210, which is a geologic environment, includes horizons, faults, one or more geobodies and facies formed over some period of geologic time. These features are distributed in two or three dimensions in space, for example, with respect to a Cartesian coordinate system (e.g., x, y and z) or other coordinate system (e.g., cylindrical, spherical, etc.). As shown, the model building method 220 includes a data acquisition block 224 and a model geometry block 228,
in [0162]:
As shown in FIG. 10, the seismic image 1000 can be rendered using seismic image data that can be in the form of seismic traces, illustrated approximately in a graphic that includes waveforms of amplitude with respect to depth where traces are acquired with respect to time using seismic acquisition equipment
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
PNG
media_image2.png
682
543
media_image2.png
Greyscale
(BRI: the method leverages the fact that a horizon is a, physically continuous boundary; hence, training sets often contain sections where the horizon, if it extends through a specific location(commo reference location) , must be tracked, facilitating the identification of that horizon )
In [0045]:
Furthermore, data may include depth and thickness maps stemming from facies variations (e.g., due to seismic unconformities) assumed to following geological events (“iso” times) and data may include lateral facies variations (e.g., due to lateral variation in sedimentation characteristics).
In [0047]:
Modeling may also model geometry with respect to time, for example, to account for changes stemming from geological events (e.g., deposition of material, erosion of material, shifting of material, etc.).
(BRI: geological events are fundamental to determining geologic age, providing both relative sequences and absolute (numeric) ages. Events like sediment deposition, volcanic eruptions, and faulting are recorded in rock layers (strata), allowing scientists to use the law of superposition and radiometric dating to determine when events occurred in Earth's history)
In [0167] ]:
In picking, selecting can occur by positioning a cursor on a rendered seismic image at a particular location that is interpreted to be a point of interest (e.g., a seismic event, etc.).
In [0143]:
Seismic data includes information as to reflectors. A reflector can be an interface between layers of contrasting acoustic properties. Seismic waves can be reflected at such an interface. In seismic data, a reflector might represent a change in lithology, a fault or an unconformity. A reflector can be expressed as a reflection in seismic data. As an example, a seismic survey can have an associated acquisition geometry and acquisition parameters that can determine resolution. Where samples of seismic energy as acquired by one or more seismic energy sensors (e.g., receivers) provide for a depth spacing of about 10 m, a reflector may be interpreted to have a position as to depth that is accurate to within approximately 10 m,
(BRI: Perhaps known to POSTA, a reflector is a seismic horizon. In seismic interpretation, a horizon is defined as a specific reflector or a continuous seismic event picked on a profile)
In [0167]:
As an example, a series of selections can be associated with a particular structural feature of a subsurface region. Thus, for example, interpretation of a bed (e.g., a reflector) via picking can generate a series of points that are believed to be associated with the bed.
In [0161]:
FIG. 10 shows an example of a seismic image 1000 and some examples of windows of seismic data (e.g., windows or tiles of a seismic image, etc.), labeled A, B, C and D. The seismic image 1000 is rendered using seismic image data as a pixel image to a display using a computerized device or system, for example, by accessing seismic image data from a data storage device and processing the seismic image data to be pixels of a desired resolution (e.g., resolution of the display, etc.), which may be adjustable based on resolution of the seismic image date. As an example, for interpretation, selection of training data, etc., the seismic image 1000 may be zoomed in, zoomed out, etc.
(BRI: in machine learning for seismic interpretation, a seismic image (or window/patch of seismic data) is typically labeled with information regarding specific, pre-interpreted horizons (reflectors) to train models)
- a training module configured by a processor to: create at least one training data set based on the labeled groupings subsurface image data and
In [0148]:
a computational imaging framework uses deep convolutional neural networks (CNN) to detect stratigraphic units in images of seismic sections
(BRI: a computational imaging framework that uses deep convolutional neural networks (CNN) to detect stratigraphic units in seismic section images represents a training module)
In [0172]:
As to an example of a NNS, consider a “U” architecture NNS such as, for example, the U-Net architecture NNS. The U-Net can be applied as part of a deep network training method where annotated (e.g., labeled) training samples are utilized to train an NNS. The U-Net is a network and training strategy that can be implemented with use of data augmentation to use available annotated samples more efficiently (e.g., to generate additional training data).
[0216]:
As an example, a workflow can utilize a synthetic data generator to generate synthetic seismic sections along with labeled stratigraphic units.
(BRI: U-Net is a type of convolutional neural network (CNN) that can be applied within a deep network training method using annotated (labeled) training samples to perform semantic segmentation on subsurface image data. In many geological scenarios, labeled datasets are created specifically for training, often by employing synthetic data generation to create ground truth labels. Synthetic seismic sections paired with labeled stratigraphic units are considered highly effective labeled groupings of subsurface image data)
- generate a trained algorithmic model by fitting the at least one training set to an algorithmic model
In [0149]:
method can include receiving an amount of seismic data from an ongoing seismic survey, interpreting the seismic data via an interpreter, training a ML system using the interpreted seismic data to generate a trained ML system, and applying the trained ML system to additional seismic data acquired by the ongoing seismic survey
in [0115]:
Inversion can aim to generate a “best-fit” model by, for example, iterating between forward modeling and inversion while seeking to minimize differences between a synthetic trace or traces and actual seismic data.
In [0231]:
a method can include generating a series of outputs of 2D stratigraphic units based on a slice of seismic image data from a seismic cube
in [0231]:
As to interpolation, linear and/or nonlinear approaches may be implemented. As an example, a spline fitting approach may be implemented where constraints may be imposed, for example, based on output from a slice that may be orthogonal to the series of 2D stratigraphic units
(BRI: Split fitting" (commonly referred to as train-test splitting) represents the process of generating a trained machine learning model by fitting an algorithm to a specific subset of data (the training set))
In regard to claim 2: (Previously Presented)
Ram discloses:
- wherein each grouping of subsurface image data has a plurality of spatial coordinates values and a common depth value associated with the plurality of spatial coordinates, wherein the common depth value is unique to each grouping.
In [0062]:
FIG. 3 shows an example of an acquisition technique 340 to acquire seismic data (see, e.g., data 360).
In [0062]:
information about the geologic environment may become available as feedback (e.g., optionally as input to the system). As an example, an operation may pertain to a reservoir that exists in a geologic environment such as, for example, a reservoir. As an example, a technique may provide information (e.g., as an output) that may specifies one or more location coordinates of a feature in a geologic environment, one or more characteristics of a feature in a geologic environment, etc.
in [0069]:
In the example of FIG. 3, a diagram 390 shows acquisition equipment 392 emitting energy from a source (e.g., a transmitter) and receiving reflected energy via one or more sensors (e.g., receivers) strung along an inline direction.
In [0069]:
a sample time spacing of approximately 4 ms would correspond to a sample “depth” spacing of about 10 meters (e.g., assuming a path length from source to boundary and boundary to sensor)
(BRI: in seismic interpretation and mapping, a "unique" depth value refers to the calculated, specific physical distance (in meters or feet) from the surface to a subsurface geological horizon at a particular grid point,)
In regard to claim 3 (Previously Presented)
Ram discloses:
- wherein the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size.
In [0177] :
As an example, with respect to tiling, one or more parameters may be selected or otherwise determined, optionally at the time of interpretation of seismic data. For example, consider the example of FIG. 10 as to windows A, B, C and D being tile windows or tiles.
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
In [0181]:
FIG. 11 shows various dimensions of data as they are processed through the architecture 1100. For example, input data of a seismic image can be of a tile size of approximately 64 in lateral span and 448 in depth span (e.g., depth range). Such data can be processed via convolution (CV) and max pooling (MP) to be 32×112 and then 16×28 and then 8×14. Following such contractions, deconvolution (DCV) can be applied to generate a desired resolution map and ultimately an output image (e.g., stratigraphic information for an improved seismic image), noting that concatenation (CONC) operations along with convolution (CV) operations are performed at three levels in the example of FIG. 11.
In regard to claim 6: (Currently Amended)
Ram discloses:
- generating a trained algorithmic model by applying a convolutional neural network
In [Abstract]:
A method can include receiving seismic image data; processing the received seismic image data to generate stratigraphic information using a trained convolution neural network that includes channels subjected to convolution,
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 4-5 are rejected under 35 U.S.C. 103 as being unpatentable over
Mats Ramfjord et.al (hereinafter Ram) US 2020/0301036 A1,
further in view of Matthias Imhof et.al(hereinafter Imhof) US 2010/0149917 A1.
In regard to claim 4: (Previously Presented)
Ram does not explicitly disclose:
- wherein horizon locations are determined using a geological age model[[,]] and the subsurface image data for each grouping.
However, Imhof discloses:
- wherein horizon locations are determined using a geological age model[[,]] and the subsurface image data for each grouping.
In [0080]:
sound waves are sequentially excited at many different locations. From all these recordings, a two-dimensional (2D) or three-dimensional (3D) image of the subsurface can be obtained after data processing,
[Abstract]:
A method of transforming geologic data relating to a subsurface region between a geophysical depth domain and a geologic age domain is disclosed.
In [0198]:
Returning to FIG. 25, at block 260 a depth mapping volume that maps samples from the age domain to the depth domain is constructed similar to how the age mapping volume is constructed or generated. Once constructed or generated, any seismic data (block 262) or geologic model may be transformed from the depth domain to the age domain using flattening processes as described herein or elsewhere, as indicated at block 261.
In [0085]:
1. A rock layer may not overlap itself. If a layer overlaps itself, it is simultaneously younger and older than itself and the rock sandwiched in between. This statement may be called the condition of No Self Overlaps, illustrated in FIG. 3A
In [0099]:
FIG. 7 presents an application of the one embodiment of the present inventive method wherein a seismic attribute volume is reorganized using a topologically consistent set of surfaces, such as the present inventive method creates. Because the surfaces are consistent, there is at least one order which honors the individual above/below relations. If surfaces correspond to the boundaries between geologic strata, then such an order represents the sequence of their deposition. Typically, the order is non-unique because small features may be laterally disconnected without overlap, and thus their exact order cannot be established. Distorting the seismic data vertically (e.g., flattening the seismic surfaces) in such a way that the corresponding seismic surfaces are arranged in this order to allow the interpreter to analyze the seismic data in the order in which the geologic strata may have been deposited, which facilitates the exploration and production of hydrocarbons.
The examiner interprets the theme of the invention is to process a seismic data and using labeling and predict seismic horizon using neural network training with determination of horizon common point on the training data set.
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Ram, and Imhof.
Ram teaches grouping of subsurface, prediction of horizon and horizon points and its references to geological age and label.
Imhof teaches geological model.
One of ordinary skill would have motivation to combine Ram, and Imhof to provide improved speed of execution (Imhof [0119]).
In regard to claim 5: (Currently Amended)
Ram does not explicitly disclose:
- selected point for each grouping is at a midpoint of the grouping and
However, Imhof discloses:
- selected point for each grouping is at a midpoint of the grouping and
In [0061]:
FIGS. 22A-B show the depth contours for two surfaces over the seismic amplitudes extracted along the surfaces;
In [0194]:
Another method of age assignment relates to the surface depths, as may be expressed by
PNG
media_image3.png
30
399
media_image3.png
Greyscale
In Equation 2, z(j) denotes the minimal, maximal or some average depth of the surface with label, order, or level j.
In [0101]:
The first part of step 81 is event tracking. In this embodiment of the invention, tracking of all events involves correlating neighboring events and editing gaps and miscorrelations. Correlation begins by extracting all the desired seismic events, or reflection surfaces, across all traces
In [0101]:
FIG. 10A illustrates event tracking as performed in this embodiment of the invention. Shown at the left of the drawing, for each seismic trace, local minima are extracted to define troughs (dashed arrows), while local maxima define peaks (solid arrows). Seismic trace windows 101 indicated by brackets are centered on each event, and used for event correlation between different traces.
(BRI: Perhaps it might be known to a geologist that a seismic trace centered at a midpoint represents the common midpoint (CMP) gather, which is a grouping of seismic traces sharing the same midpoint on the surface between a source and a receiver)
- wherein the horizon is determined based on the midpoint, contour and geological age model
In [0220]:
the result of transforming the data in FIG. 29 from the depth domain to the age domain using the age mapping volume (FIG. 31) would be a representation similar to representation 338, with differences being at the youngest ages (top) and oldest ages (bottom) where boundary or extrapolation conditions differ.
In [0217]:
The differences between a push and pull are less relevant when the age and depth mapping volumes are used as maps instead of lookup tables because mapping may require resampling, for example by interpolation. Resampling can be performed either in the source or destination domain. The notation y=interp, Y, x) expresses the interpolation of some feature vector Y sampled at locations X such that it is sampled at x instead. The interpolator could, for example, be based on nearest neighbor interpolation, linear interpolation, cubic spline interpolation, piecewise cubic Hermite interpolation, polynomial interpolation, Fourier interpolation, or other known methods. Boundary conditions are irrelevant for the present discussion. In some applications, extrapolation may be performed if a new sample location is outside the range spanned by X. In other applications, the value of the closest sample location could be returned. Yet in other cases, a default value such as zero or the average of Y could be returned or a flag could be set to indicate an invalid new sample location.
In [0015] :
The method picks horizons by extracting, e.g., all peaks, but correlates them by clustering of waveforms. Picks belonging to the same cluster are used to define horizons patches which are merged into larger horizons by properties such as cluster indices, position, or seismic attributes. Specifically, the method defines with sub-sample precision the positions of seismic horizons through an extrema representation of a 3D seismic input volume. For each extrema, it derives coefficients that represent the shape of the seismic waveform in the vicinity of the extrema positions and sorts the extrema positions into groups that have similar waveform shapes by using unsupervised or supervised classification of these coefficients. It then extracts surface primitives as surface segments that are both spatially continuous along the extrema of the seismic volume and continuous in class index in the classification volume. By filtering on properties, such as class index, position, attribute values, etc. attached to each patch, a set of patches can be combined into a final horizon interpretation.
(BRI: It may be known to the art that an unseen horizon determined by midpoint, contour, and geological age model is a geological surface or boundary in the subsurface that has been extrapolated or interpolated based on limited data points and that combining a set of patches into a final horizon may form a key method for determining horizon locations in seismic interpretation)
Claims 7-9, 12-16, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over
Mats Ramfjord et.al (hereinafter Ram) US 2020/0301036 A1,
In view of Geoffrey Dorn et.al (hereinafter Dorn ) US 5894417 A.
In regard to claim 7 (Currently Amended)
Ram discloses:
- A system for generating a trained algorithmic model, the system comprising: a tracking and data preprocessing module configured by a processor to:
In [0111]:
As an example, a workflow may aim to drill into an environment, for example, to form a bore defined by surrounding earth (e.g., rock, fluids, etc.).
In [0111]:
a workflow may utilize one or more frameworks that operate at least in part via a computer (e.g., a computing device, a computing system, etc.).
in [0128]:
The framework 700 can extend workflows into reservoir characterization and earth modelling.
In [0129]:
survey designs can be modelled to ensure quality of a seismic survey, which may account for structural complexity of the model. Such an approach can enable evaluation of how well a target zone will be illuminated. Such an approach may be part of a quality control process (e.g., task) as part of a seismic workflow.
In [0100]:
one or more of the sensors 464 can be provided for tracking pipe, tracking movement of at least a portion of a drillstring, etc.
in [0165]:
As to interpretation, a process referred to as picking may be implemented. For example, manual seismic interpretation can involve rendering a seismic image to a display and picking locations as corresponding to geologic features. Picking may be facilitated through use of a cursor navigable by a mouse, a trackball, etc., through use of a stylus, through use of a finger (e.g., on a touchscreen, a touchpad, etc.), etc. The term pick can be defined as interpreting data such as seismic sections by selecting and tracking marker beds or other events.
(BRI: one or more sensors can be provided for tracking pipe and the movement of at least a portion of a drill string, representing an apparatus that includes a tracking and data preprocessing module. It is known that an interpretation process involving "picking" (selecting/clicking) facilitated by a mouse or trackball, when combined with software that records these actions, represents an apparatus for tracking—specifically mouse tracking or cursor tracking. The system is the workflow framework)
- receive seismic data representing a geological formation
In [0027]:
In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 can include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114).
- select groupings of subsurface image data from received seismic data, wherein the selected groupings have shared geometric data,
In [0003]:
A method can include receiving seismic image data; processing the received seismic image data to generate stratigraphic information using a trained convolution neural network that includes channels subjected to convolution, activation and pooling
(BRI: stratigraphic information includes horizon information)
In [0044]:
As an example, reservoir simulation, petroleum systems modeling, etc. may be applied to characterize various types of subsurface environments, including environments such as those of FIG. 1. One or more operations may be performed in an environment based at least in part on such characterization of a subsurface environment or environments (e.g., via acquired data, simulation, modeling, etc.).
PNG
media_image1.png
306
496
media_image1.png
Greyscale
In [0047]:
In basin and petroleum systems modeling, quantities such as temperature, pressure and porosity distributions within the sediments may be modeled
In [0047]:
Modeling may also model geometry with respect to time, for example, to account for changes stemming from geological events (e.g., deposition of material, erosion of material, shifting of material, etc.).
- select a point within the shared geometric shape
In [0225]:
seismic image data acquired via the seismic survey can be tiled where a tile that overlaps with a well can be labeled with at least a portion of the well log data. In such an example, the tile can be tagged for augmentation such that a training data set includes multiple instances of information in that tile, which may be deemed to be more accurate as it includes well log data.
In [0161]:
FIG. 10 shows an example of a seismic image 1000 and some examples of windows of seismic data (e.g., windows or tiles of a seismic image, etc.), labeled A, B, C and D.
In [0092]:
As an example, a drilling operation can include directional drilling where, for example, at least a portion of a well includes a curved axis. For example, consider a radius that defines curvature where an inclination with regard to the vertical may vary until reaching an angle between about 30 degrees and about 60 degrees or, for example, an angle to about 90 degrees or possibly greater than about 90 degrees.
In [0091] :
FIG. 4 also shows some examples of types of holes that may be drilled. For example, consider a slant hole 472, an S-shaped hole 474, a deep inclined hole 476 and a horizontal hole 478.
In [0093] :
a directional well can include several shapes where each of the shapes may aim to meet particular operational demands
- label locations [[in]] within each grouping that include a horizon that passes through the selected point for each respective grouping, each location labeled having a geological age approximately equal to the geological age at the selected point within each respective grouping of subsurface image data;
In [0045]:
in FIG. 2, the sedimentary basin 210, which is a geologic environment, includes horizons, faults, one or more geobodies and facies formed over some period of geologic time. These features are distributed in two or three dimensions in space, for example, with respect to a Cartesian coordinate system (e.g., x, y and z) or other coordinate system (e.g., cylindrical, spherical, etc.). As shown, the model building method 220 includes a data acquisition block 224 and a model geometry block 228,
in [0162]:
As shown in FIG. 10, the seismic image 1000 can be rendered using seismic image data that can be in the form of seismic traces, illustrated approximately in a graphic that includes waveforms of amplitude with respect to depth where traces are acquired with respect to time using seismic acquisition equipment
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
PNG
media_image2.png
682
543
media_image2.png
Greyscale
(BRI: the method leverages the fact that a horizon is a, physically continuous boundary; hence, training sets often contain sections where the horizon, if it extends through a specific location(commo reference location) , must be tracked, facilitating the identification of that horizon )
In [0045]:
Furthermore, data may include depth and thickness maps stemming from facies variations (e.g., due to seismic unconformities) assumed to following geological events (“iso” times) and data may include lateral facies variations (e.g., due to lateral variation in sedimentation characteristics).
In [0047]:
Modeling may also model geometry with respect to time, for example, to account for changes stemming from geological events (e.g., deposition of material, erosion of material, shifting of material, etc.).
(BRI: geological events are fundamental to determining geologic age, providing both relative sequences and absolute (numeric) ages. Events like sediment deposition, volcanic eruptions, and faulting are recorded in rock layers (strata), allowing scientists to use the law of superposition and radiometric dating to determine when events occurred in Earth's history)
In [0167] ]:
In picking, selecting can occur by positioning a cursor on a rendered seismic image at a particular location that is interpreted to be a point of interest (e.g., a seismic event, etc.).
In [0143]:
Seismic data includes information as to reflectors. A reflector can be an interface between layers of contrasting acoustic properties. Seismic waves can be reflected at such an interface. In seismic data, a reflector might represent a change in lithology, a fault or an unconformity. A reflector can be expressed as a reflection in seismic data. As an example, a seismic survey can have an associated acquisition geometry and acquisition parameters that can determine resolution. Where samples of seismic energy as acquired by one or more seismic energy sensors (e.g., receivers) provide for a depth spacing of about 10 m, a reflector may be interpreted to have a position as to depth that is accurate to within approximately 10 m,
(BRI: Perhaps known to POSTA, a reflector is a seismic horizon. In seismic interpretation, a horizon is defined as a specific reflector or a continuous seismic event picked on a profile)
In [0167]:
As an example, a series of selections can be associated with a particular structural feature of a subsurface region. Thus, for example, interpretation of a bed (e.g., a reflector) via picking can generate a series of points that are believed to be associated with the bed.
In [0161]:
FIG. 10 shows an example of a seismic image 1000 and some examples of windows of seismic data (e.g., windows or tiles of a seismic image, etc.), labeled A, B, C and D. The seismic image 1000 is rendered using seismic image data as a pixel image to a display using a computerized device or system, for example, by accessing seismic image data from a data storage device and processing the seismic image data to be pixels of a desired resolution (e.g., resolution of the display, etc.), which may be adjustable based on resolution of the seismic image date. As an example, for interpretation, selection of training data, etc., the seismic image 1000 may be zoomed in, zoomed out, etc.
(BRI: in machine learning for seismic interpretation, a seismic image (or window/patch of seismic data) is typically labeled with information regarding specific, pre-interpreted horizons (reflectors) to train models)
- a training module configured by a processor to: create at least one training data set based on the labeled groupings of subsurface image data
In [0148]:
a computational imaging framework uses deep convolutional neural networks (CNN) to detect stratigraphic units in images of seismic sections
(BRI: a computational imaging framework that uses deep convolutional neural networks (CNN) to detect stratigraphic units in seismic section images represents a training module)
In [0172]:
As to an example of a NNS, consider a “U” architecture NNS such as, for example, the U-Net architecture NNS. The U-Net can be applied as part of a deep network training method where annotated (e.g., labeled) training samples are utilized to train an NNS. The U-Net is a network and training strategy that can be implemented with use of data augmentation to use available annotated samples more efficiently (e.g., to generate additional training data).
[0216]:
As an example, a workflow can utilize a synthetic data generator to generate synthetic seismic sections along with labeled stratigraphic units.
(BRI: U-Net is a type of convolutional neural network (CNN) that can be applied within a deep network training method using annotated (labeled) training samples to perform semantic segmentation on subsurface image data. In many geological scenarios, labeled datasets are created specifically for training, often by employing synthetic data generation to create ground truth labels. Synthetic seismic sections paired with labeled stratigraphic units are considered highly effective labeled groupings of subsurface image data)
- and generate a trained algorithmic model by fitting the at least one training set to an algorithmic model;
In [0149]:
method can include receiving an amount of seismic data from an ongoing seismic survey, interpreting the seismic data via an interpreter, training a ML system using the interpreted seismic data to generate a trained ML system, and applying the trained ML system to additional seismic data acquired by the ongoing seismic survey
in [0115]:
Inversion can aim to generate a “best-fit” model by, for example, iterating between forward modeling and inversion while seeking to minimize differences between a synthetic trace or traces and actual seismic data.
In [0231]:
a method can include generating a series of outputs of 2D stratigraphic units based on a slice of seismic image data from a seismic cube
in [0231]:
As to interpolation, linear and/or nonlinear approaches may be implemented. As an example, a spline fitting approach may be implemented where constraints may be imposed, for example, based on output from a slice that may be orthogonal to the series of 2D stratigraphic units
(BRI: Split fitting" (commonly referred to as train-test splitting) represents the process of generating a trained machine learning model by fitting an algorithm to a specific subset of data (the training set))
Ram does not explicitly disclose:
- and a storage module, the storage module configured by a processor to store the labeled groupings of subsurface image data.
However, Dorn discloses:
- and a storage module, the storage module configured by a processor to store the labeled groupings of subsurface image data.
In [0033]:
FIG. 1 also shows an example of a framework 170 that includes a model simulation layer 180 along with a framework services layer 190, a framework core layer 195 and a modules layer 175. The framework 170 may include the OCEAN® framework where the model simulation layer 180 is the PETREL® model-centric software package that hosts OCEAN® framework applications. In an example embodiment, the PETREL® software may be considered a data-driven application. The PETREL® software can include a framework for model building and visualization.
(BRI: A framework for processing data may include features a software framework that utilizes a modules layer frequently includes a storage module (or a storage module within a dedicated "persistence layer") to manage data access.)
In [0035];
for 2D line and 3D seismic surveys. Modules for processing seismic data may include features for prestack seismic interpretation (PSI), optionally pluggable into a framework such as the OCEAN® framework
in [0161]:
FIG. 10 shows an example of a seismic image 1000 and some examples of windows of seismic data (e.g., windows or tiles of a seismic image, etc.), labeled A, B, C and DT. he seismic image 1000 is rendered using seismic image data as a pixel image to a display using a computerized device or system, for example, by accessing seismic image data from a data storage device and processing the seismic image data to be pixels of a desired resolution (e.g., resolution of the display, etc.), which may be adjustable based on resolution of the seismic image date. As an example, for interpretation, selection of training data, etc., the seismic image 1000 may be zoomed in, zoomed out, etc.
In [0167 ]:
positioning a cursor on a rendered seismic image at a particular location that is interpreted to be a point of interest (e.g., a seismic event, etc.). A user may select the point via a mouse click or another type of action or instruction (e.g., a keystroke, a depression of a stylus tip, a click of a stylus button, etc.). Once selected, information concerning the point can be saved to a storage device
The examiner interprets the theme of the invention is to predict seismic horizon using neural network training with determination of horizon common point on the training data set.
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Ram, and Dorn.
The examiner interprets the theme of the invention is to process a seismic data and using labeling and predict seismic horizon using neural network training with determination of horizon common point on the training data set.
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Ram, Dorn and Imhof.
Ram teaches grouping of subsurface, prediction of horizon and horizon points and its references to geological age and label.
Dorn teaches storage module.
One of ordinary skill would have motivation to combine Ram, and Dorn, and Imhof to provide improved the resolution of the trace of the surface location (Dorn[Col 8, lines 29-49])
In regard to claim 8: (Previously Presented)
Ram discloses:
- wherein each grouping of subsurface image data has a plurality of spatial coordinates values and a common depth value associated with the plurality of spatial coordinates, wherein the common depth value is unique to each grouping.
In [0062]:
FIG. 3 shows an example of an acquisition technique 340 to acquire seismic data (see, e.g., data 360).
In [0062]:
information about the geologic environment may become available as feedback (e.g., optionally as input to the system). As an example, an operation may pertain to a reservoir that exists in a geologic environment such as, for example, a reservoir. As an example, a technique may provide information (e.g., as an output) that may specifies one or more location coordinates of a feature in a geologic environment, one or more characteristics of a feature in a geologic environment, etc.
in [0069]:
In the example of FIG. 3, a diagram 390 shows acquisition equipment 392 emitting energy from a source (e.g., a transmitter) and receiving reflected energy via one or more sensors (e.g., receivers) strung along an inline direction.
In [0069]:
a sample time spacing of approximately 4 ms would correspond to a sample “depth” spacing of about 10 meters (e.g., assuming a path length from source to boundary and boundary to sensor)
(BRI: in seismic interpretation and mapping, a "unique" depth value refers to the calculated, specific physical distance (in meters or feet) from the surface to a subsurface geological horizon at a particular grid point)
In regard to claim 9 (Previously Presented)
Ram discloses:
- wherein the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size.
In [0177] :
As an example, with respect to tiling, one or more parameters may be selected or otherwise determined, optionally at the time of interpretation of seismic data. For example, consider the example of FIG. 10 as to windows A, B, C and D being tile windows or tiles.
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
In [0181]:
FIG. 11 shows various dimensions of data as they are processed through the architecture 1100. For example, input data of a seismic image can be of a tile size of approximately 64 in lateral span and 448 in depth span (e.g., depth range). Such data can be processed via convolution (CV) and max pooling (MP) to be 32×112 and then 16×28 and then 8×14. Following such contractions, deconvolution (DCV) can be applied to generate a desired resolution map and ultimately an output image (e.g., stratigraphic information for an improved seismic image), noting that concatenation (CONC) operations along with convolution (CV) operations are performed at three levels in the example of FIG. 11.
In regard to claim 12: (Currently Amended)
Ram discloses:
- generating a trained algorithmic model includes applying a convolutional neural network.
In [Abstract]:
A method can include receiving seismic image data; processing the received seismic image data to generate stratigraphic information using a trained convolution neural network that includes channels subjected to convolution,
In regard to claim 13: (Currently Amended)
Ram discloses:
- comprising a predictive engine module configured by a processor to generate predictive results that identify a horizon
In [0045]:
n FIG. 2, the sedimentary basin 210, which is a geologic environment, includes horizons, faults, one or more geobodies and facies formed over some period of geologic time. These features are distributed in two or three dimensions in space, for example, with respect to a Cartesian coordinate system (e.g., x, y and z) or other coordinate system (e.g., cylindrical, spherical, etc.). As shown, the model building method 220 includes a data acquisition block 224 and a model geometry block 228,
in [0162]:
As shown in FIG. 10, the seismic image 1000 can be rendered using seismic image data that can be in the form of seismic traces, illustrated approximately in a graphic that includes waveforms of amplitude with respect to depth where traces are acquired with respect to time using seismic acquisition equipment
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
PNG
media_image2.png
682
543
media_image2.png
Greyscale
(BRI: the method leverages the fact that a horizon is a, physically continuous boundary; hence, training sets often contain sections where the horizon, if it extends through a specific location(commo reference location) , must be tracked, facilitating the identification of that horizon )
In regard to claim 14 (Currently Amended)
Ram discloses:
- A method for generating a trained algorithmic model, the method comprising
In [0149]:
method can include receiving an amount of seismic data from an ongoing seismic survey, interpreting the seismic data via an interpreter, training a ML system using the interpreted seismic data to generate a trained ML system, and applying the trained ML system to additional seismic data acquired by the ongoing seismic survey
- receiving seismic data representing a geological formation
In [0027]:
In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 can include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114).
- labeling locations [[in]] within each selected grouping that include a horizon that passes through the common point in each respective grouping, each location labeled including a geological age approximately equal to the geological age at the [[a]] selected common point within each respective grouping of subsurface image data;
In [0045]:
n FIG. 2, the sedimentary basin 210, which is a geologic environment, includes horizons, faults, one or more geobodies and facies formed over some period of geologic time. These features are distributed in two or three dimensions in space, for example, with respect to a Cartesian coordinate system (e.g., x, y and z) or other coordinate system (e.g., cylindrical, spherical, etc.). As shown, the model building method 220 includes a data acquisition block 224 and a model geometry block 228,
in [0162]:
As shown in FIG. 10, the seismic image 1000 can be rendered using seismic image data that can be in the form of seismic traces, illustrated approximately in a graphic that includes waveforms of amplitude with respect to depth where traces are acquired with respect to time using seismic acquisition equipment
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
PNG
media_image2.png
682
543
media_image2.png
Greyscale
(BRI: the method leverages the fact that a horizon is a, physically continuous boundary; hence, training sets often contain sections where the horizon, if it extends through a specific location(commo reference location) , must be tracked, facilitating the identification of that horizon )
In [0045]:
Furthermore, data may include depth and thickness maps stemming from facies variations (e.g., due to seismic unconformities) assumed to following geological events (“iso” times) and data may include lateral facies variations (e.g., due to lateral variation in sedimentation characteristics).
In [0047]:
Modeling may also model geometry with respect to time, for example, to account for changes stemming from geological events (e.g., deposition of material, erosion of material, shifting of material, etc.).
(BRI: geological events are fundamental to determining geologic age, providing both relative sequences and absolute (numeric) ages. Events like sediment deposition, volcanic eruptions, and faulting are recorded in rock layers (strata), allowing scientists to use the law of superposition and radiometric dating to determine when events occurred in Earth's history)
In [0167] ]:
In picking, selecting can occur by positioning a cursor on a rendered seismic image at a particular location that is interpreted to be a point of interest (e.g., a seismic event, etc.).
In [0143]:
Seismic data includes information as to reflectors. A reflector can be an interface between layers of contrasting acoustic properties. Seismic waves can be reflected at such an interface. In seismic data, a reflector might represent a change in lithology, a fault or an unconformity. A reflector can be expressed as a reflection in seismic data. As an example, a seismic survey can have an associated acquisition geometry and acquisition parameters that can determine resolution. Where samples of seismic energy as acquired by one or more seismic energy sensors (e.g., receivers) provide for a depth spacing of about 10 m, a reflector may be interpreted to have a position as to depth that is accurate to within approximately 10 m,
(BRI: Perhaps known to POSTA, a reflector is a seismic horizon. In seismic interpretation, a horizon is defined as a specific reflector or a continuous seismic event picked on a profile)
In [0167]:
As an example, a series of selections can be associated with a particular structural feature of a subsurface region. Thus, for example, interpretation of a bed (e.g., a reflector) via picking can generate a series of points that are believed to be associated with the bed.
In [0161]:
FIG. 10 shows an example of a seismic image 1000 and some examples of windows of seismic data (e.g., windows or tiles of a seismic image, etc.), labeled A, B, C and D. The seismic image 1000 is rendered using seismic image data as a pixel image to a display using a computerized device or system, for example, by accessing seismic image data from a data storage device and processing the seismic image data to be pixels of a desired resolution (e.g., resolution of the display, etc.), which may be adjustable based on resolution of the seismic image date. As an example, for interpretation, selection of training data, etc., the seismic image 1000 may be zoomed in, zoomed out, etc.
(BRI: in machine learning for seismic interpretation, a seismic image (or window/patch of seismic data) is typically labeled with information regarding specific, pre-interpreted horizons (reflectors) to train models)
- creating at least one training data set based on the labeled groupings of subsurface image data;
In [0148]:
a computational imaging framework uses deep convolutional neural networks (CNN) to detect stratigraphic units in images of seismic sections
(BRI: a computational imaging framework that uses deep convolutional neural networks (CNN) to detect stratigraphic units in seismic section images represents a training module)
In [0172]:
As to an example of a NNS, consider a “U” architecture NNS such as, for example, the U-Net architecture NNS. The U-Net can be applied as part of a deep network training method where annotated (e.g., labeled) training samples are utilized to train an NNS. The U-Net is a network and training strategy that can be implemented with use of data augmentation to use available annotated samples more efficiently (e.g., to generate additional training data).
[0216]:
As an example, a workflow can utilize a synthetic data generator to generate synthetic seismic sections along with labeled stratigraphic units.
(BRI: U-Net is a type of convolutional neural network (CNN) that can be applied within a deep network training method using annotated (labeled) training samples to perform semantic segmentation on subsurface image data. In many geological scenarios, labeled datasets are created specifically for training, often by employing synthetic data generation to create ground truth labels. Synthetic seismic sections paired with labeled stratigraphic units are considered highly effective labeled groupings of subsurface image data)
- generating a trained algorithmic model by fitting the at least one training set to an algorithmic model;
In [0149]:
method can include receiving an amount of seismic data from an ongoing seismic survey, interpreting the seismic data via an interpreter, training a ML system using the interpreted seismic data to generate a trained ML system, and applying the trained ML system to additional seismic data acquired by the ongoing seismic survey
in [0115]:
Inversion can aim to generate a “best-fit” model by, for example, iterating between forward modeling and inversion while seeking to minimize differences between a synthetic trace or traces and actual seismic data.
In [0231]:
a method can include generating a series of outputs of 2D stratigraphic units based on a slice of seismic image data from a seismic cube
in [0231]:
As to interpolation, linear and/or nonlinear approaches may be implemented. As an example, a spline fitting approach may be implemented where constraints may be imposed, for example, based on output from a slice that may be orthogonal to the series of 2D stratigraphic units
(BRI: Split fitting" (commonly referred to as train-test splitting) represents the process of generating a trained machine learning model by fitting an algorithm to a specific subset of data (the training set))
Ram does not explicitly disclose:
- storing the labeled groupings of subsurface image data
However, Dorn discloses:
- storing the labeled groupings of subsurface image data
In [0033]:
FIG. 1 also shows an example of a framework 170 that includes a model simulation layer 180 along with a framework services layer 190, a framework core layer 195 and a modules layer 175. The framework 170 may include the OCEAN® framework where the model simulation layer 180 is the PETREL® model-centric software package that hosts OCEAN® framework applications. In an example embodiment, the PETREL® software may be considered a data-driven application. The PETREL® software can include a framework for model building and visualization.
(BRI: A framework for processing data may include features a software framework that utilizes a modules layer frequently includes a storage module (or a storage module within a dedicated "persistence layer") to manage data access.)
The examiner interprets the theme of the invention is to process a seismic data and using labeling and predict seismic horizon using neural network training with determination of horizon common point on the training data set.
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Ram, Dorn and Imhof.
Ram teaches grouping of subsurface, prediction of horizon and horizon points and its references to geological age and label.
Dorn teaches storage module for storing.
Imhof teaches geological model.
One of ordinary skill would have motivation to combine Ram, and Dorn, and Imhof to provide improved the resolution of the trace of the surface location (Dorn[Col 8, lines 29-49])
In regard to claim 15: (Previously Presented)
Ram discloses:
- wherein each grouping of subsurface image data has a plurality of spatial coordinates values and a common depth value associated with the plurality of spatial coordinates, wherein the common depth value is unique to each grouping.
In [0062]:
FIG. 3 shows an example of an acquisition technique 340 to acquire seismic data (see, e.g., data 360).
In [0062]:
information about the geologic environment may become available as feedback (e.g., optionally as input to the system). As an example, an operation may pertain to a reservoir that exists in a geologic environment such as, for example, a reservoir. As an example, a technique may provide information (e.g., as an output) that may specifies one or more location coordinates of a feature in a geologic environment, one or more characteristics of a feature in a geologic environment, etc.
in [0069]:
In the example of FIG. 3, a diagram 390 shows acquisition equipment 392 emitting energy from a source (e.g., a transmitter) and receiving reflected energy via one or more sensors (e.g., receivers) strung along an inline direction.
In [0069]:
a sample time spacing of approximately 4 ms would correspond to a sample “depth” spacing of about 10 meters (e.g., assuming a path length from source to boundary and boundary to sensor)
(BRI: in seismic interpretation and mapping, a "unique" depth value refers to the calculated, specific physical distance (in meters or feet) from the surface to a subsurface geological horizon at a particular grid point,)
In regard to claim 16 (Original)
Ram discloses:
- wherein the tracking and data preprocessing module selects groupings that form image tiles, with each tile having a predetermined size.
In [0177] :
As an example, with respect to tiling, one or more parameters may be selected or otherwise determined, optionally at the time of interpretation of seismic data. For example, consider the example of FIG. 10 as to windows A, B, C and D being tile windows or tiles.
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
In [0181]:
FIG. 11 shows various dimensions of data as they are processed through the architecture 1100. For example, input data of a seismic image can be of a tile size of approximately 64 in lateral span and 448 in depth span (e.g., depth range). Such data can be processed via convolution (CV) and max pooling (MP) to be 32×112 and then 16×28 and then 8×14. Following such contractions, deconvolution (DCV) can be applied to generate a desired resolution map and ultimately an output image (e.g., stratigraphic information for an improved seismic image), noting that concatenation (CONC) operations along with convolution (CV) operations are performed at three levels in the example of FIG. 11.
In regard to claim 19: ( Currently Amended)
Ram discloses:
- wherein the algorithmic model includes applying a convolutional neural network to the labeled groupings of subsurface image data.
In [0220] :
FIG. 15 shows an example of pre-processed seismic data 1510, which can be described as an implicit function model of a region of the Earth, and an example of a method 1550. The pre-processed seismic data 1510 is volumetric (e.g., from a seismic cube and optionally other data) and includes layers such as the layers labeled with 1521, 1522, 1523 and 1525 where such layers can be repeating with respect to an implicit function approach. An implicit function can be calculated for a geologic region where the values of the implicit function can represent iso-surfaces such as horizons (e.g., horizons of an implicit function model). While the values may repeat for use of an implicit function, the actual layers are distinct layers that can define one or more stratigraphic units. As an example, an implicit function can be solved for values using picked points in seismic data and/or points from well log data, which can constrain the solution. As mentioned, output from a solver can be implicit function values where the values correspond to iso-surfaces that approximate the locations of materials in the geologic region (e.g., beds, etc.). Such iso-surfaces and/or implicit function values may be utilized as or for generating labels for purposes of training a CNN to generate a trained CNN.
In regard to claim 20: (Currently Amended)
Ram discloses:
- comprising generating predictive results that identify a horizon
In [0045]:
n FIG. 2, the sedimentary basin 210, which is a geologic environment, includes horizons, faults, one or more geobodies and facies formed over some period of geologic time. These features are distributed in two or three dimensions in space, for example, with respect to a Cartesian coordinate system (e.g., x, y and z) or other coordinate system (e.g., cylindrical, spherical, etc.). As shown, the model building method 220 includes a data acquisition block 224 and a model geometry block 228,
in [0162]:
As shown in FIG. 10, the seismic image 1000 can be rendered using seismic image data that can be in the form of seismic traces, illustrated approximately in a graphic that includes waveforms of amplitude with respect to depth where traces are acquired with respect to time using seismic acquisition equipment
In [0169]:
As to depth, a scale is shown in FIG. 10 ranging from z meters to z+Δz meters. In such an example, z meters can be based on a reference location, which may be, for example, the surface of the Earth. As mentioned, time may be a proxy for depth (e.g., traveltime, etc.). In the example of FIG. 10, various windows (e.g., tiles) may be depth referenced with respect to a common reference location.
PNG
media_image2.png
682
543
media_image2.png
Greyscale
(BRI: the method leverages the fact that a horizon is a, physically continuous boundary; hence, training sets often contain sections where the horizon, if it extends through a specific location(commo reference location) , must be tracked, facilitating the identification of that horizon )
Claims 10-11 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over
Mats Ramfjord et.al (hereinafter Ram) US 2020/0301036 A1,
In view of Geoffrey Dorn et.al (hereinafter Dorn ) US 5894417 A.
further in view of Matthias Imhof et.al(hereinafter Imhof) US 2010/0149917 A1.
In regard to claim 10: (Previously Presented)
Ram and Dorn do not explicitly disclose:
- wherein horizon locations are determined using a geological age model and the subsurface image data for each grouping.
However, Imhof discloses:
- wherein horizon locations are determined using a geological age model and the subsurface image data for each grouping.
In [0080]:
sound waves are sequentially excited at many different locations. From all these recordings, a two-dimensional (2D) or three-dimensional (3D) image of the subsurface can be obtained after data processing,
[Abstract]:
A method of transforming geologic data relating to a subsurface region between a geophysical depth domain and a geologic age domain is disclosed.
In [0198]:
Returning to FIG. 25, at block 260 a depth mapping volume that maps samples from the age domain to the depth domain is constructed similar to how the age mapping volume is constructed or generated. Once constructed or generated, any seismic data (block 262) or geologic model may be transformed from the depth domain to the age domain using flattening processes as described herein or elsewhere, as indicated at block 261.
In [0085]:
1. A rock layer may not overlap itself. If a layer overlaps itself, it is simultaneously younger and older than itself and the rock sandwiched in between. This statement may be called the condition of No Self Overlaps, illustrated in FIG. 3A
In [0099]:
FIG. 7 presents an application of the one embodiment of the present inventive method wherein a seismic attribute volume is reorganized using a topologically consistent set of surfaces, such as the present inventive method creates. Because the surfaces are consistent, there is at least one order which honors the individual above/below relations. If surfaces correspond to the boundaries between geologic strata, then such an order represents the sequence of their deposition. Typically, the order is non-unique because small features may be laterally disconnected without overlap, and thus their exact order cannot be established. Distorting the seismic data vertically (e.g., flattening the seismic surfaces) in such a way that the corresponding seismic surfaces are arranged in this order to allow the interpreter to analyze the seismic data in the order in which the geologic strata may have been deposited, which facilitates the exploration and production of hydrocarbons.
The examiner interprets the theme of the invention is to process a seismic data and using labeling and predict seismic horizon using neural network training with determination of horizon common point on the training data set.
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Ram, Dorn and Imhof.
Ram teaches grouping of subsurface, prediction of horizon and horizon points and its references to geological age and label.
Dorn teaches storage module for storing.
Imhof teaches geological model.
One of ordinary skill would have motivation to combine Ram, Dorn, and Imhof to provide improved speed of execution (Imhof [0119]).
In regard to claim 11 (Previously Presented)
Ram, and Dorn do not explicitly disclose:
- selected point for each grouping is at a midpoint of the grouping and
However, Imhof discloses:
- selected point for each grouping is at a midpoint of the grouping and
In [0061]:
FIGS. 22A-B show the depth contours for two surfaces over the seismic amplitudes extracted along the surfaces;
In [0194]:
Another method of age assignment relates to the surface depths, as may be expressed by
PNG
media_image3.png
30
399
media_image3.png
Greyscale
In Equation 2, z(j) denotes the minimal, maximal or some average depth of the surface with label, order, or level j.
In [0101]:
The first part of step 81 is event tracking. In this embodiment of the invention, tracking of all events involves correlating neighboring events and editing gaps and miscorrelations. Correlation begins by extracting all the desired seismic events, or reflection surfaces, across all traces
In [0101]:
FIG. 10A illustrates event tracking as performed in this embodiment of the invention. Shown at the left of the drawing, for each seismic trace, local minima are extracted to define troughs (dashed arrows), while local maxima define peaks (solid arrows). Seismic trace windows 101 indicated by brackets are centered on each event, and used for event correlation between different traces.
(BRI: Perhaps it might be known to a geologist that a seismic trace centered at a midpoint represents the common midpoint (CMP) gather, which is a grouping of seismic traces sharing the same midpoint on the surface between a source and a receiver.
- wherein the horizon is determined based on the midpoint, contour and geological age model
In [0220]:
the result of transforming the data in FIG. 29 from the depth domain to the age domain using the age mapping volume (FIG. 31) would be a representation similar to representation 338, with differences being at the youngest ages (top) and oldest ages (bottom) where boundary or extrapolation conditions differ.
In [0217]:
The differences between a push and pull are less relevant when the age and depth mapping volumes are used as maps instead of lookup tables because mapping may require resampling, for example by interpolation. Resampling can be performed either in the source or destination domain. The notation y=interp, Y, x) expresses the interpolation of some feature vector Y sampled at locations X such that it is sampled at x instead. The interpolator could, for example, be based on nearest neighbor interpolation, linear interpolation, cubic spline interpolation, piecewise cubic Hermite interpolation, polynomial interpolation, Fourier interpolation, or other known methods. Boundary conditions are irrelevant for the present discussion. In some applications, extrapolation may be performed if a new sample location is outside the range spanned by X. In other applications, the value of the closest sample location could be returned. Yet in other cases, a default value such as zero or the average of Y could be returned or a flag could be set to indicate an invalid new sample location.
In [0015] :
The method picks horizons by extracting, e.g., all peaks, but correlates them by clustering of waveforms. Picks belonging to the same cluster are used to define horizons patches which are merged into larger horizons by properties such as cluster indices, position, or seismic attributes. Specifically, the method defines with sub-sample precision the positions of seismic horizons through an extrema representation of a 3D seismic input volume. For each extrema, it derives coefficients that represent the shape of the seismic waveform in the vicinity of the extrema positions and sorts the extrema positions into groups that have similar waveform shapes by using unsupervised or supervised classification of these coefficients. It then extracts surface primitives as surface segments that are both spatially continuous along the extrema of the seismic volume and continuous in class index in the classification volume. By filtering on properties, such as class index, position, attribute values, etc. attached to each patch, a set of patches can be combined into a final horizon interpretation.
(BRI: It may be known to the art that an unseen horizon determined by midpoint, contour, and geological age model is a geological surface or boundary in the subsurface that has been extrapolated or interpolated based on limited data points and that combining a set of patches into a final horizon may form a key method for determining horizon locations in seismic interpretation)
In regard to claim 17: (Previously Presented)
Ram and Dorn do not explicitly disclose:
- wherein horizon locations are determined using a geological age model
and the subsurface image data for each grouping.
However, Imhof discloses:
- wherein horizon locations are determined using a geological age model and the subsurface image data for each grouping.
In [0080]:
sound waves are sequentially excited at many different locations. From all these recordings, a two-dimensional (2D) or three-dimensional (3D) image of the subsurface can be obtained after data processing,
[Abstract]:
A method of transforming geologic data relating to a subsurface region between a geophysical depth domain and a geologic age domain is disclosed.
In [0198]:
Returning to FIG. 25, at block 260 a depth mapping volume that maps samples from the age domain to the depth domain is constructed similar to how the age mapping volume is constructed or generated. Once constructed or generated, any seismic data (block 262) or geologic model may be transformed from the depth domain to the age domain using flattening processes as described herein or elsewhere, as indicated at block 261.
In [0085]:
1. A rock layer may not overlap itself. If a layer overlaps itself, it is simultaneously younger and older than itself and the rock sandwiched in between. This statement may be called the condition of No Self Overlaps, illustrated in FIG. 3A
In [0099]:
FIG. 7 presents an application of the one embodiment of the present inventive method wherein a seismic attribute volume is reorganized using a topologically consistent set of surfaces, such as the present inventive method creates. Because the surfaces are consistent, there is at least one order which honors the individual above/below relations. If surfaces correspond to the boundaries between geologic strata, then such an order represents the sequence of their deposition. Typically, the order is non-unique because small features may be laterally disconnected without overlap, and thus their exact order cannot be established. Distorting the seismic data vertically (e.g., flattening the seismic surfaces) in such a way that the corresponding seismic surfaces are arranged in this order to allow the interpreter to analyze the seismic data in the order in which the geologic strata may have been deposited, which facilitates the exploration and production of hydrocarbons.
The examiner interprets the theme of the invention is to process a seismic data and using labeling and predict seismic horizon using neural network training with determination of horizon common point on the training data set.
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Ram, Dorn and Imhof.
Ram teaches grouping of subsurface, prediction of horizon and horizon points and its references to geological age and label.
Dorn teaches storage module.
Imhof teaches geological model.
One of ordinary skill would have motivation to combine Ram, Dorn, and Imhof to provide improved speed of execution (Imhof [0119]).
In regard to claim 18: (Currently Amended)
Ram and Dorn do not explicitly disclose:
- wherein the selected common point [[for]] each grouping is at a midpoint of the grouping and
- wherein the horizon is determined based on the midpoint, contour and geological age model
However, Imhof discloses:
- wherein the selected common point [[for]] each grouping is at a midpoint of the grouping and
In [0061]:
FIGS. 22A-B show the depth contours for two surfaces over the seismic amplitudes extracted along the surfaces;
In [0194]:
Another method of age assignment relates to the surface depths, as may be expressed by
PNG
media_image3.png
30
399
media_image3.png
Greyscale
In Equation 2, z(j) denotes the minimal, maximal or some average depth of the surface with label, order, or level j.
In [0101]:
The first part of step 81 is event tracking. In this embodiment of the invention, tracking of all events involves correlating neighboring events and editing gaps and miscorrelations. Correlation begins by extracting all the desired seismic events, or reflection surfaces, across all traces
In [0101]:
FIG. 10A illustrates event tracking as performed in this embodiment of the invention. Shown at the left of the drawing, for each seismic trace, local minima are extracted to define troughs (dashed arrows), while local maxima define peaks (solid arrows). Seismic trace windows 101 indicated by brackets are centered on each event, and used for event correlation between different traces.
- wherein the horizon is determined based on the midpoint, contour and geological age model
In [0220]:
the result of transforming the data in FIG. 29 from the depth domain to the age domain using the age mapping volume (FIG. 31) would be a representation similar to representation 338, with differences being at the youngest ages (top) and oldest ages (bottom) where boundary or extrapolation conditions differ.
In [0217]:
The differences between a push and pull are less relevant when the age and depth mapping volumes are used as maps instead of lookup tables because mapping may require resampling, for example by interpolation. Resampling can be performed either in the source or destination domain. The notation y=interp, Y, x) expresses the interpolation of some feature vector Y sampled at locations X such that it is sampled at x instead. The interpolator could, for example, be based on nearest neighbor interpolation, linear interpolation, cubic spline interpolation, piecewise cubic Hermite interpolation, polynomial interpolation, Fourier interpolation, or other known methods. Boundary conditions are irrelevant for the present discussion. In some applications, extrapolation may be performed if a new sample location is outside the range spanned by X. In other applications, the value of the closest sample location could be returned. Yet in other cases, a default value such as zero or the average of Y could be returned or a flag could be set to indicate an invalid new sample location.
In [0015] :
The method picks horizons by extracting, e.g., all peaks, but correlates them by clustering of waveforms. Picks belonging to the same cluster are used to define horizons patches which are merged into larger horizons by properties such as cluster indices, position, or seismic attributes. Specifically, the method defines with sub-sample precision the positions of seismic horizons through an extrema representation of a 3D seismic input volume. For each extrema, it derives coefficients that represent the shape of the seismic waveform in the vicinity of the extrema positions and sorts the extrema positions into groups that have similar waveform shapes by using unsupervised or supervised classification of these coefficients. It then extracts surface primitives as surface segments that are both spatially continuous along the extrema of the seismic volume and continuous in class index in the classification volume. By filtering on properties, such as class index, position, attribute values, etc. attached to each patch, a set of patches can be combined into a final horizon interpretation.
(BRI: It may be known to the art that an unseen horizon determined by midpoint, contour, and geological age model is a geological surface or boundary in the subsurface that has been extrapolated or interpolated based on limited data points and that combining a set of patches into a final horizon may form a key method for determining horizon locations in seismic interpretation)
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the
examiner should be directed to TIRUMALE KRISHNASWAMY RAMESH whose telephone number is (571)272-4605. The examiner can normally be reached by phone.
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, Li B Zhen can be reached on phone (571-272-3768). 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.
/TIRUMALE K RAMESH/Examiner, Art Unit 2121
/Li B. Zhen/Supervisory Patent Examiner, Art Unit 2121