DETAILED ACTION
This Office Action is in response to communication on February 4, 2025.
Claims 1, 5-6, 8, 12-13 and 21-24 are presented for examination.
Claims 1, 5-6, 13, and 22-24 have been amended.
Rejection of claims 1, 5-6, 8, 12-13 and 21-24 as being directed to unpatentable subject matter are maintained.
New rejection of 1, 5-6, 8, 12-13, 21, and 23 under 35 U.S.C. 103 as being obvious over Santoso in view of Heidari, Alwon, and Wang.
New rejection of claims 22 and 24 as being obvious over Santoso in view of Heidari, Alwon, Wang, and Buono.
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 Arguments
Regarding rejection of the independent claims under 35 U.S.C. 101:
Applicant first asserts that “determining, from the at least one 3D reservoir simulation, a plurality of production scenarios from which an enhanced recovery scheme is identified, wherein the enhanced recovery scheme boosts hydrocarbon flow from at least one production well in the reservoir region and comprises at least one new fracture” integrates the other claimed abstract ideas into a practical application because “[t]his limitation provides improvements to overcome the shortcomings of existing technologies described above.” Response at pg. 8.
The new limitation, however, is itself an abstract idea (see below where the limitation is identified as a mental process that can be performed by a human). Thus, the limitation cannot integrate the other abstract ideas into a practical application because it is itself an abstract idea.
An inventive concept “cannot be furnished by the unpatentable law of nature (or natural phenomenon or abstract idea) itself.” Genetic Techs. Ltd. v. Merial LLC, 818 F.3d 1369, 1376, 118 USPQ2d 1541, 1546 (Fed. Cir. 2016). See also Alice Corp., 573 U.S. at 21-18, 110 USPQ2d at 1981 (citing Mayo, 566 U.S. at 78, 101 USPQ2d at 1968 (after determining that a claim is directed to a judicial exception, “we then ask, ‘[w]hat else is there in the claims before us?”) (emphasis added)); RecogniCorp, LLC v. Nintendo Co., 855 F.3d 1322, 1327, 122 USPQ2d 1377 (Fed. Cir. 2017) (“Adding one abstract idea (math) to another abstract idea (encoding and decoding) does not render the claim non-abstract”). Instead, an “inventive concept” is furnished by an element or combination of elements that is recited in the claim in addition to (beyond) the judicial exception, and is sufficient to ensure that the claim as a whole amounts to significantly more than the judicial exception itself. Alice Corp., 573 U.S. at 27-18, 110 USPQ2d at 1981 (citing Mayo, 566 U.S. at 72-73, 101 USPQ2d at 1966). MPEP 2106.05(I).
Thus, Applicant’s argument is not persuasive.
Next, Applicant asserts that the limitation directed to “obtaining…” is not data gathering, as now recited, because it is performed “using an artificial neural network.”
Examiner first asserts that the detection, absent the “using an artificial neural network, is an abstract idea that can be performed by a human, such as by reviewing an image and pointing out the fractures, based on observation, evaluation, judgment, and opinion. See MPEP 2106.04(a). Implementing the process using a generic neural network (i.e., a neural network with a plurality of layers, trained using low resolution images) is mere instructions to apply a judicial exception (the “detecting”).
Second, Examiner would like to point out that training the neural network is not actively recited in the claim. Instead, the step of “training the neural network” is outside the scope of the claim and, as recited, has already been performed at the time of using the neural network.
Examiner suggests amending the claims to recite one or more of the following:
Training the neural network using recited specific training data to receive X as input and provide Y as output; and/or
Forming the coarsened images and providing them to the neural network to result in detection of fractures.
Thus, although Examiner appreciates the arguments directed to the claims reciting an improvement in the function of the neural network, without active recitation of the clauses, the claim is directed to detecting fractures using generic computer components.
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, 5-6, 8, 12-13 and 21-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to mental processes and mathematical calculations without any additional elements that provide a practical application or amount to significantly more than the abstract ideas.
Claim 1
Step 1: The claim is drawn to a process, falling under one of the four statutory categories of invention.
Step 2A, Prong 1: The claim 1 limitations recite (bolded for abstract idea identification):
Claim 1
Mapping Under Step 2A Prong 1
A method, comprising:
obtaining, by a computer processor, a set of high-resolution images of a fracture, wherein the set of high-resolution images comprises at least one wellbore image that is acquired by an acoustic logging tool and at least one wellbore image that is acquired by a resistivity logging tool;
detecting, by the computer processor and using an artificial neural network , a first set of detected fractures based on the first set of high-resolution images, wherein the artificial neural network comprises a plurality of layers that are
trained by a deep-learning algorithm using training data, wherein the training data comprise a plurality of grey-scaled images with a plurality of pixel labels; and
wherein detecting the set of detected fractures comprises forming a set of coarsened images from the set of high-resolution images;
extracting, by the computer processor using a convolution neural network (CNN), a hydraulic aperture and a fracture permeability of for each detected fracture detected fracture set based on the set of high-resolution images and the set of coarsened images, wherein the CNN comprises at least one convolutional layer, at least one batch normalization layer, and a pooling layer,
and wherein the CNN is trained using a plurality of numerical calculations of a plurality of Navier-Stokes equations describing a flow of incompressible fluids for a plurality of fractures;
generating, by the computer processor, at least one three-dimensional (3D) reservoir simulation of a reservoir region based on the hydraulic aperture and the fracture permeability of each detected fracture of the set of the detected fracture;
determining, from the at least one 3D reservoir simulation, a plurality of production scenarios from which an enhanced recovery scheme is identified, wherein the enhanced recovery scheme boosts hydrocarbon flow from at least one production well in the reservoir region and comprises at least one new fracture, and
fracturing a new fracture in the reservoir region, guided by the enhanced recovery scheme.
The claim is not directed to any specific computer implemented tool to perform the simulation.
Abstract Idea: Mathematical Calculations
An artificial neural network is comprised of a number of mathematical calculations in the form of an algorithm. Using an artificial neural network includes performing the one or more calculations that are recited as being performed by generic computer components. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mathematical Calculations
Training a machine learning model is, as recited, performed using an algorithm, which is includes mathematical calculations to carry out the training. As recited, “training the model” is not positively recited. However, even if included as a step in the method, training a machine learning model is a mathematical concept that is considered an abstract idea. See, e.g., Example 47, Claim 2 of the USPTO July 2024 Subject Matter Eligibility Examples.
Abstract Idea: Mathematical Calculations
A convolutional neural network is comprised of a number of mathematical calculations in the form of an algorithm. Using an artificial neural network to extract data from images includes performing the one or more calculations that are recited as being performed by generic computer components. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mathematical Calculations
Training a machine learning model is, as recited, performed using a plurality of equations, thus it includes performing mathematical calculations to carry out the training. As recited, “training the model” is not positively recited. However, even if included as a step in the method, training a machine learning model is a mathematical concept that is considered an abstract idea. See, e.g., Example 47, Claim 2 of the USPTO July 2024 Subject Matter Eligibility Examples.
Abstract Idea: Mathematical Calculations
A simulation is generated by performing one or more mathematical calculations using a number of functions. See MPEP § 2106.04(a)(2), Subsection I.
Step 2A, Prong 2: In accordance with this step, the judicial exceptions are not integrated into a practical application. The claim does not recite any additional elements other than generic computer components, extra-solution activities, and ideas of solutions that are not claimed with sufficient specificity (additional elements are bolded).
Claim 1
Mapping Under Step 2A Prong 2
A method, comprising:
obtaining, by a computer processor, a set of high-resolution images of a t fracture, wherein the first set of high-resolution images comprises at least one wellbore image that is
acquired by an acoustic logging tool and at least one wellbore image that is acquired by a resistivity logging tool;
obtaining, by the computer processor and using an artificial neural network , a first set of fracture detections based on the first set of high-resolution images, wherein the artificial neural network comprises a plurality of layers that are
trained by a deep-learning algorithm using first training data, and wherein the first training data comprise a plurality of grey-scaled images with a plurality of pixel labels;
extracting, by the computer processor using a convolution neural network (CNN), a hydraulic aperture of the first fracture and a fracture permeability of the first fracture based on the first set of high-resolution images, wherein the CNN comprises at least one convolutional layer, at least one batch normalization layer, and a pooling layer,
and wherein the CNN is trained using a plurality of numerical calculations of a plurality of Navier-Stokes equations describing a flow of incompressible fluids for a plurality of fractures;
generating, by the computer processor, a three-dimensional (3D) reservoir simulation of a reservoir region based on the hydraulic aperture and the fracture permeability of the first fracture; and
fracturing a new fracture in the reservoir region, based on a permeability determined by the 3D reservoir simulation in order to boost hydrocarbon flow at a production well in the reservoir region.
Under MPEP 2106.05(g), the step is mere data gathering, which does not integrate the judicial exception into a practical application. Further, limitation recites generic computer components, which is equivalent to reciting a step and indicating to “apply it.”
Using generic tools to perform an extra-solution activity, such as data gathering, merely links the judicial exception to a particular field of use and does not integrate the judicial exception into a practical application. See MPEP 2106.05(h).
The limitations is directed to the extra-solution activity of data gathering. In this instance, the data is generated by a judicial exception and the “obtaining” is merely a step of collecting the generated data to perform additional analysis. Thus, the limitation is a necessary activity that is required to be performed for any ANN.
Under MPEP 2106.05(f)(1), this limitation merely recites “only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished.” The limitation claims using the results of the simulation to generally induce a fracture without any specificity how the data is used to selectively perform the inducement. “The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words ‘apply it’.” MPEP 2106.05(f)(1).
Step 2B: In accordance with this step, additional elements are evaluated to determine whether the additional elements amount to more than the claimed judicial exception, or whether the additional elements merely recite insignificant extra-solution activities or activities that either have been found by courts to be insignificantly more than a recited judicial exception or are well-known, routine, and conventional. Regarding claim 1, none of the additional elements add significantly more than the previously identified judicial exceptions.
Regarding obtaining, by a computer processor, a first set of high-resolution images of a first fracture, wherein the first set of high-resolution images comprises at least one wellbore image, the claim merely recites insignificant extra-solution activities of data gathering, which courts have found does not amount to significantly more. See MPEP 2106.05(d); Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93. Further, reciting generic computer components as a tool to perform an existing process is equivalent to mere instructions to apply an exception. See MPEP 2106.05(f)(2).
Regarding acquired by an acoustic logging tool and at least one wellbore image that is acquired by a resistivity logging tool, using logging tools to generate logs is well-understood, routine, and conventional by a person of ordinary skill in the art. See, e.g., MPEP 2106.05(d); Suau, et al., “Fracture Detection from Well Logs,” March 1, 980 (“The effect on each type of log is discussed with particular emphasis on the Resistivity logs (including the Dipmeter Curves) and Acoustic logs.” Abstract).
Regarding obtaining, by the computer processor…a first set of fracture detections based on the first set of high-resolution images, using a trained model to detect the presence of an object in images, particularly fractures in images, is well-known, routine, and conventional activity that does not amount to significantly more. Evidence of an element being well-understood, routine, and conventional may be found in other prior art references. See MPEP 2106.05(d). Further, courts have found that mere data gathering is not significantly more than the recited judicial exception. See MPEP 2106.05(g).
Regarding performing, based on the 3D reservoir simulation of the reservoir region, a mechanically-induced fracture in the reservoir region in order to boost hydrocarbon flow at a production well in the reservoir region, the limitation is mere instructions to apply an exception, which does not amount to significantly more than the judicial exception. See 2106.05(f).
Because claim 1 recites a judicial exception and additional elements that are merely extra-solution activities and ideas of solutions, claim 1 is considered to be patent ineligible.
Claim 5
The claim recites wherein the artificial neural network performs a U-Net procedure comprising a contracting path and an expanding path. As previously indicated with regards to claim 1, the artificial neural network is comprised of mathematical functions that are utilized to perform one or more mathematical calculations and are therefore directed to judicial exceptions. Claim 5 merely specifies types of models that may be utilized in performing the calculations and does not claim significantly more than the judicial exceptions. Accordingly, claim 5 is considered to be patent ineligible.
Claim 6
The claim recites wherein the first set of high-resolution images further comprises a plurality of rock core images and a plurality of outcrop images. As previously indicated, obtaining the images is an insignificant extra-solution activity of data gathering. Claim 6 merely indicates the contents of the images and therefore does not add an additional element nor amount to significantly more than recited in claim 1. Accordingly, claim 6 is patent ineligible.
Claim 8
Claim 8 is directed to a system, which is a machine and therefore is one of the four statutory categories of invention.
Additionally, the claim recites an acoustic logging tool; a resistivity logging tool; a production well through a reservoir region. The recited hardware are recited at a generic level without additional limitations related to the structure and/or functionality of the elements. Using generic tools to perform an extra-solution activity, such as data gathering, merely links the judicial exception to a particular field of use and does not integrate the judicial exception into a practical application. See MPEP 2106.05(h).
Further, the claim recites a fracture manager comprising a computer processor, wherein the fracture manager is configured to perform the method of claim 1. Under MPEP 2106.05(f), use of a computer or other machinery in its ordinary capacity or a general purpose computer or computer components after the fact to an abstract idea (e.g., a mathematical equation) does not integrate a judicial exception into a practical application. The claim merely recites generic computer components and amounts to no more than reciting to apply the recited abstract idea using a general purpose computer. Accordingly, claim 8 is patent ineligible.
Claims 12 and 13
Regarding claims 12 and 13, the claims recite the system of claim 8 (see rejection of claim 8) and the steps previously recited in claims 5 and 6. Because the additional limitations are nothing more than a recitation of generic computer components and amount to no more than an application a judicial exception, claims 12 and 13 are patent ineligible for at least the same reasons as previously indicated for claims 5 and 6.
Claims 21 and 23
Claims 21 and 23 recite wherein the 3D reservoir simulation corresponds to a completion scheme for the production well. Under MPEP 2106.05(f)(1), this limitation merely recites “only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished.” The limitation claims using the results of the simulation to generally determine a recovery solution, but does not indicate with any specificity how the recovery schemes are determined. “The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application and courts have found that ideas of a solution do not provide significantly more because this type of recitation is equivalent to the words ‘apply it’.”
Claims 22 and 24
Claims 22 and 24 recite wherein obtaining the first set of high-resolution images further comprises: acquiring a plurality of rock core samples by drilling into one or more bedrocks in the reservoir region; and obtaining a plurality of rock core images based on the plurality of rock core samples. The claims merely further specify steps that are related to “obtaining the first set of high-resolution images,” which has previously been identified as the extra-solution activity of data gathering. The steps recited in these claims are further extra-solution activities that are well-understood, routine, and conventional methods of obtaining images of rock fractures. Santoso, et al., “Application of Machine-Learning to Construct Simulation Models from High-Resolution Fractured Formation,” at pg. 2, paragraph 5 (“In step two, the fracture effective hydraulic apertures are estimated based on wellbore or core images”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 5-6, 8, 12-13, 21, and 23 are rejected under 35 U.S.C. 103 as being obvious over Santoso, et al., (“Application of Machine-Learning to Construct Simulation Models from High-Resolution Fractured formation,” hereinafter Santoso), in view of Heidari, et al., (U.S. Pat. Pub. No. 2021/0223192, hereinafter “Heidari”), Alwon (U.S. Pat. Pub. 2019/0302290), and Wang, et al., (U.S. Pat. Pub. No. 2020/0256178, hereinafter “Wang”).
Claim 1
Santoso discloses:
detecting, by the computer processor and using an artificial neural network, a first set of detected fractures based on the first set of high-resolution images, wherein the artificial neural network comprises a plurality of layers that are
The proposed workflow is designed to automatize the construction of the DFN model based on the images of the fractured medium, such as high-resolution outcrop images. Santoso at pg. 4.
trained by a deep-learning algorithm using training data, wherein the training data comprise a plurality of grey-scaled images with a plurality of pixel labels; and
This resolution was selected to accelerate the recognition process and to simplify the variability in the training set. Santoso at ph. 4.
extracting, by the computer processor using a convolution neural network (CNN), a hydraulic aperture and a fracture permeability of for each detected fracture detected fracture set based on the set of high-resolution images
The characterized fractures are then fed into the next machine-learning stage to calculate effective hydraulic aperture. This stage utilizes a Convolutional Neural Network (CNN) architecture to perform image-to-value calculation (2nd and 3rd machine in Figure 2). This step is critical in the workflow to estimate the individual fracture permeability. Santoso at pg. 4.
wherein the CNN comprises at least one convolutional layer,
In our work, we developed a U-Net architecture to perform fracture recognition for the first time. Figure 1 shows the U-Net architecture, including the type of the input image and the output image. The contracting (convolutional) path consists of repeating two 3×3 convolutions (unpadded convolutions), each followed by a Rectified Linear Unit (ReLU) and a 2×2 max-pooling operation with stride 2 for down-sampling. Santoso at 3.
generating, by the computer processor, at least one
In this final step, all processed data from previous steps are collected to construct the reservoir model. It uses CNN architecture (4th machine in Figure 2) to perform the calculations. The inputs are identified fractures image in binary format, effective hydraulic aperture, and fracture configurations. Santoso at pg. 4.
Santoso does not appear to disclose:
A method, comprising: obtaining, by a computer processor, a set of high-resolution images of a first fracture, wherein the set of high-resolution images comprises at least one wellbore image that is acquired by an acoustic logging tool and at least one wellbore image that is acquired by a resistivity logging tool;
wherein detecting the set of detected fractures comprises forming a set of coarsened images from the set of high-resolution images;
CNN comprises…at least one batch normalization layer
and wherein the CNN is trained using a plurality of numerical calculations of a plurality of Navier-Stokes equations describing a flow of incompressible fluids for a plurality of fractures;
generating, by the computer processor, at least one three-dimensional (3D) reservoir simulation of a reservoir region
determining, from the at least one 3D reservoir simulation, a plurality of production scenarios from which an enhanced recovery scheme is identified, wherein the enhanced recovery scheme boosts hydrocarbon flow from at least one production well in the reservoir region and comprises at least one new fracture, and fracturing a new fracture in the reservoir region, guided by the enhanced recovery scheme.
Heidari, which is analogous art, discloses:
obtaining, by a computer processor, a set of high-resolution images of a first fracture, wherein the set of high-resolution images comprises at least one wellbore image that is acquired by an acoustic logging tool and at least one wellbore image that is acquired by a resistivity logging tool;
Porosity can be estimated via numerous approaches from well-log measurements (e.g., neutron-density logs and acoustic measurements). Heidari at [0048].
Non-limiting embodiments of this disclosure include (a) estimating parameters that quantify rock fabric features (e.g., tortuosity, effective pore size, throat-size distribution) by joint interpretation of electrical resistivity, dielectric permittivity, and NMR measurements… Heidari at [0004].
Heidari is analogous art to the claimed invention because both are associated with utilizing images generated from logging tools to further analyze rock formations. It would have been obvious to a person having skill in the art, before the effective filing date of the claimed invention, to combine Santoso and Heidari to result in a system that receives images from logging tools to identify fractures in rock formations. Motivation to combine includes a resulting system that completely facilitates, from collection to analysis, images that are utilized to perform the analysis.
Alwon, which is analogous art to the claimed invention, discloses:
wherein detecting the set of detected fractures comprises forming a set of coarsened images from the set of high-resolution images;
A discriminator model can be built according to a DCGAN framework. For example, it can take an image, either real or generated, as input, and pass it through a series of convolutional filters, or layers. In such an example, each layer of the network can downsample the image until a final layer is a single value representing the probability of the image being real (e.g., or fake). Alwon at [0086].
CNN comprises…at least one batch normalization layer
As to a discriminator architecture, after a last layer, a convolution may be applied to map to a 1-dimensional output, followed by a Sigmoid function (e.g., or other suitable function). As an example, batch normalization may or may not be applied to a layer. As an example, ReLU can be leaky with a slope or not leaky. Alwon at [0102].
Alwon is analogous art to the claimed invention because both are related to utilizing a CNN to perform analysis on images. It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to combine Santoso and Heidari with Alwon to result in a system that performs the analysis via a CNN. Motivation to combine includes accurately automating image analysis such that a human expert is not required to interpret captured images. “As CNNs can be modeled after the ways humans interpret information, a CNN-based approach can allow for identifying and attenuating noise in a seismic shot record, optionally without performing one or more domain transforms. As an example, a computing system can include circuitry that can implement a DCGAN approach that aims to replicate one or more results as may be achieved via a human and/or a more arduous computational path that involves experts and domain transforms.” Alwon at [0083].
Wang, which is analogous art to the claimed invention, discloses:
wherein the CNN is trained using a plurality of numerical calculations of a plurality of Navier-Stokes equations describing a flow of incompressible fluids for a plurality of fractures;
In some embodiments, the reservoir data 254 includes fluid data relating to well system fluids. The fluid data may identify types of fluids, fluid properties, thermodynamic conditions, and other information related to well system fluids. The fluid data can include flow models for compressible or incompressible fluid flow. For example, the fluid data can include systems of governing equations (e.g., Navier-Stokes equations, advection-diffusion equations, continuity equations, etc.) that represent fluid flow generally or fluid flow under certain types of conditions. Wang at [0029].
generating, by the computer processor, at least one three-dimensional (3D) reservoir simulation of a reservoir region
In some implementations, the computing subsystem 110 can simulate fluid flow in the well system 100. For example, the computing subsystem 110 can include flow models for simulating fluid flow in or between various locations of fluid flow in the well system, such as, for example, the wellbore 102, the perforations 120, the conduit 112 or components thereof, the dominant fractures 132, the natural fracture networks 130, the rock media in the subterranean region 104, or a combination of these and others. The flow models can model the flow of incompressible fluids (e.g., liquids), compressible fluids (e.g., gases), or a combination of multiple fluid phases. In some instances, the flow models can model flow in one, two, or three spatial dimensions. Wang at [0019].
determining, from the at least one 3D reservoir simulation, a plurality of production scenarios from which an enhanced recovery scheme is identified, wherein the enhanced recovery scheme boosts hydrocarbon flow from at least one production well in the reservoir region and comprises at least one new fracture, and fracturing a new fracture in the reservoir region, guided by the enhanced recovery scheme.
In some implementations, the computing subsystem 110 can simulate fluid flow in the well system 100. For example, the computing subsystem 110 can include flow models for simulating fluid flow in or between various locations of fluid flow in the well system. Wang at [0019].
Wang is analogous art to the claimed invention because both are directed to generating a three dimensional model to utilize in determining one or more production scenarios. Motivation to combine includes reduced computing resources by utilizing coarsened images and CNNs to perform the analysis that results from the invention disclosed in Wang. Further, Wang discloses further analysis and recommendations that can be generated from three-dimensional simulations. Motivation to combine the three-dimensional simulation and production scenarios of Wang with the other references includes providing additional analysis data to the user in a cost-effective manner. “The simulation resources 220 may be used to automate the reservoir simulation with various objectives such as providing a reduced cost of operating the simulation resources 220 and a simplified user experience. Simplifying the user experience can be accomplished by automating the configuration of the simulation resources 220, which reduces the risk of the simulation failure due to resource constraints during the reservoir simulation and removes the user from considering the configuration of the simulation resources.” Wang at [0035].
Claim 5
Santoso discloses:
wherein the artificial neural network performs a U-Net procedure comprising a contracting path and an expanding path.
The fracture network recognition starts with segmentation for the images of the fractured formation. The ultimate objective is to identify the fractures from RGB, greyscale, or hyperspectral images. We developed a U-Net-based algorithm to perform the segmentation using 64×64 pixel-resolution. pg. 1, paragraph 2.
The contracting (convolutional) path consists of repeating two 3×3 convolutions (unpadded convolutions), each followed by a Rectified Linear Unit (ReLU) and a 2×2 max-pooling operation with stride 2 for down-sampling. The expanding (de-convolutional) path consists of 2×2 up-convolution, concatenated with the correspondingly cropped feature map from the contracting path, and two 3×3 convolutions, each followed by a ReLU. Pg. 3, Paragraph 6.
Claim 6
Santoso discloses:
wherein the first set of high-resolution images further comprises a plurality of rock core images and a plurality of outcrop images
The input data is of multi-scale nature which includes high-resolution outcrop imaging at the field scale to capture the fracture network patterns. These images are obtained using laser scanning or digital camera. The outcrop data can be combined with bottom-hole images and core images at smaller scale to capture the effective fracture apertures. Pg. 4, paragraph 1.
Claim 8
As previously indicated, claim 1 is rejected under 35 U.S.C. 103 as being obvious over Santoso in view of Heidari, Alwon, and Wang. Accordingly, for at least the same reasons and with the same motivations to combine, the steps disclosed as being performed by the system are rejected under 35 U.S.C. 103.
Claim 8 further recites “a system” with the following components:
an acoustic logging tool;
a resistivity logging tool;
a production well through a reservoir region
a fracture manager comprising a computer processor
Santoso does not explicitly teach or disclose an acoustic logging tool, a resistivity logging tool, a production well through a reservoir region, and a fracture manager comprising a computer processor.
Heidari discloses:
an acoustic logging tool;
Porosity can be estimated via numerous approaches from well-log measurements (e.g., neutron-density logs and acoustic measurements). Heidari at [0048].
a resistivity logging tool;
Non-limiting embodiments of this disclosure include (a) estimating parameters that quantify rock fabric features (e.g., tortuosity, effective pore size, throat-size distribution) by joint interpretation of electrical resistivity, dielectric permittivity, and NMR measurements… Heidari at [0004].
a production well through a reservoir region
A reservoir simulation may involve performing by execution of a reservoir-simulator computer program on a processor, which computes composition, pressure, and/or movement of fluid as function of time and space for a specified scenario of injection and production wells by solving a set of reservoir fluid flow equations. Buono at [0038].
a fracture manager comprising a computer processor
using a processor to implement software stored in computerized memory, wherein the software is configured to independently calculate the directional permeability from fabric parameters comprising pore-size distribution (rP) and effective pore radii calculated from the NMR data, and wherein the software is further configured to calculate a statistical mean of directional permeability of the section of the porous media… Heidari at [0016].
Santoso does not explicitly disclose where the analyzed data originates. Heidari, on the other hand, discloses utilizing downhole tools to generate logs that can be utilized by the processes of Santoso to generate the three-dimensional simulations and productions schemes that are disclosed in Santoso. Motivation to combine includes utilizing an automated process to analyze well logs, thus reducing potential human errors in analyzing the logs, thus improving estimates of well conditions, such as permeability. See Heidari at [0046].
Claims 12 and 13
Claims 12 and 13 recite the system of claim 8 and limitations that are substantially similar to the limitations of claim 5 and 6. Thus, for at least the same reasons as previously provided with regards to claims 5 and 6, claims 12 and 13 are rejected for being obvious over Santoso, in view of Heidari, Alwon,, and Wang.
Claims 21 and 23
Santoso, Heidari, and Alwon do not appear to disclose wherein the 3D reservoir simulation corresponds to a completion scheme for the production well.
Wang discloses:
wherein the 3D reservoir simulation corresponds to a completion scheme for the production well.
In some implementations, the computing subsystem 110 can simulate fluid flow in the well system 100. For example, the computing subsystem 110 can include flow models for simulating fluid flow in or between various locations of fluid flow in the well system. Wang at [0019].
Wang discloses further analysis and recommendations that can be generated from three-dimensional simulations. Motivation to combine the three-dimensional simulation and production scenarios of Wang with the other references includes providing additional analysis data to the user in a cost-effective manner. “The simulation resources 220 may be used to automate the reservoir simulation with various objectives such as providing a reduced cost of operating the simulation resources 220 and a simplified user experience. Simplifying the user experience can be accomplished by automating the configuration of the simulation resources 220, which reduces the risk of the simulation failure due to resource constraints during the reservoir simulation and removes the user from considering the configuration of the simulation resources.” Wang at [0035].
Claim 23 recite the system of claim 8 and limitations that are substantially similar to the limitations of claim 21. Thus, for at least the same reasons as previously provided with regards to claim 21, claim 23 is rejected for being obvious over Santoso, in view of Heidari, Alwon, and Wang.
Claims 22 and 24 are rejected under 35 U.S.C. 103 as being obvious over Santoso, , in view of Heidari, Alwon, and Wang, and further in view of Buono (U.S. Patent Pub. No. 2018/0259467).
Claims 22 and 24
Santoso discloses:
wherein obtaining the first set of high-resolution images further comprises:
The input data is of multi-scale nature which includes high-resolution outcrop imaging at the field scale to capture the fracture network patterns. These images are obtained using laser scanning or digital camera. The outcrop data can be combined with bottomhole images and core images at smaller scale to capture the effective fracture apertures. Pg. 4, Paragraph 1.
obtaining a plurality of rock core images
This step is to estimate the effective hydraulic aperture using Borehole Image (BHI) and core images. Pg. 4, Paragraph 2.
Santoso does not appear to disclose:
acquiring a plurality of rock core samples by drilling into one or more bedrocks in the reservoir region; and
[obtaining a plurality of rock core images] based on the plurality of rock core samples.
Buono, which is analogous art, discloses:
acquiring a plurality of rock core samples by drilling into one or more bedrocks in the reservoir region; and
The method includes obtaining a core sample and data associated with a subsurface region, as shown in blocks 202 to 204… [0076].
obtaining a plurality of rock core images based on the plurality of rock core samples.
performing imaging on the core sample with one of flood fluid, imaging fluid, or any combination thereof during the imaging of the core sample, as shown in blocks 206 to 228. [0076].
Buono and the claimed invention are analogous art because both are related to analysis performed on images of rock core samples. It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to use the acquisition and imaging of Buono to generate images to provide to the neural networks disclosed in Santoso. Motivation to combine would be that the images would be high-resolution and therefore would result in better performance by the neural networks.
Claim 24 recites the system of claim 8 and limitations that are substantially similar to the limitations of claim 22. Thus, for at least the same reasons as previously provided with regards to claim 22, claim 24 is rejected for being obvious over Santoso, in view of Heidari, Alwon, and Wang, and further in view of Buono.
Conclusion
THIS ACTION IS MADE FINAL. 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.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Liang, et al., WO 2021/064585
Camargo, et al., U.S. Patent No. 11,578,596
Schaeffer, et al., U.S. Pat. No. 11,970,939
Communication
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH MORRIS whose telephone number is (703)756-5735. The examiner can normally be reached M-F 8:30-5:00.
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, Ryan Pitaro can be reached at (571) 272-4071. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
JOSEPH MORRIS
Examiner
Art Unit 2188
/JOSEPH P MORRIS/Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
Prosecution Insights