Notice of Pre-AIA or AIA Status
Claims 1-20 are currently presented for Examination.
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
The amendment filed on 12/12/2025 has been entered and considered by the examiner. By the
amendment, claims 1-2, 10, 16-17 and 20 are amended. Following Applicants arguments and amendments made on, the 103 rejection of the claims is modified and the 101 rejection is still maintained. See office action for detail.
Response to Arguments
Applicant 101 arguments
For example, claim 1 (and similarly claims 10 and 16) has been amended to recite, inter alia, the following:
generating a total emissions estimate of the second hydrocarbon operation location for a predetermined operation time using the emissions factor of the at least one equipment component of the second hydrocarbon operation location, wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location
Applicant respectfully submits that claim 1, as amended, includes additional elements that demonstrate that claim 1, as a whole, clearly improves upon wellsite operations with respect to reducing environmental emissions. Specifically, the claimed techniques leverage "high resolution data, real-time emission data and highly granular equipment level data" to inform machine-learning training and inference to predict "emission factors with reduced uncertainty [as] compared to other methods." Specification, para. [0009]. As a result of these machine- learning generated predictions, the "machine-learning model can provide insights into factors that contribute to emissions" at a granular level that was not possible before thereby providing a technical solution to a technical problem. Id. In addition, such insights "can help asset managers make fast, smart decisions related to the emissions and achieve yearly emissions commitments." Id. That is, the insights and predictions provided by the claimed techniques enable operators of wellsite operations to control equipment functionality accordingly to maintain emissions totals within commitment amounts over time (i.e., "to control the at least one equipment component of the second hydrocarbon operation location," as recited in amended claim 1). Further, the additional elements of the amended claims expressly tie the machine- learning outputs to equipment-specific, time-bounded operational control in a hydrocarbon operation location, thereby producing concrete effects in the physical world. For example, the amended claim recites training a machine learning model that is "specific to the at least one equipment component" and applying that model only after "identifying" the same component at a second site, to generate a total emissions value for a predetermined operation time that is "usable by an operator to control the at least one equipment component of the second hydrocarbon operation location.". In practice, this equipment-level indication triggers targeted operational control at identified components to meet emissions targets in the field (for example, retuning valve setpoints, modifying compressor duty cycles, adjusting flare routing, advancing maintenance, or swapping malfunctioning parts), which constitutes more than mere data analysis or reporting and instead imposes a meaningful limitation that improves a specific technological field. See MPEP 2106.05(a) (improving another technology or technical field); MPEP 2106.05(b) (use of a particular machine integral to the claim); and MPEP 2106.05(d) (meaningful application beyond linking to a field of use). Moreover, the amended claim's recitation of high-resolution and real-time emissions and equipment-level data, coupled with component-specific machine-learning training and inference, forecloses performance "in the human mind" and addresses an engineering problem of emissions estimation and mitigation with reduced uncertainty. This is analogous, for example, to claims upheld as non-abstract where specific rules or configurations improved a technological process or system. See e.g., McRO, Inc. v. Bandai Namco Games, 837 F.3d 1299, 1316-17 (Fed. Cir. 2016) and Thales Visionix Inc. v. United States, 850 F.3d 1343, 1348-49 (Fed. Cir. 2017). Here, the component-specific training, cross-site identification, and operator indication together effectuate real-world operational changes to achieve threshold emissions thereby integrating any alleged abstract concept into a practical application under Step 2A, Prong II, and for at least these reasons, claims 1-20 are patent eligible. Accordingly, Applicant respectfully requests withdrawal of the rejection under 35 U.S.C. § 101.
Examiner response
Examiner respectfully disagrees. Under MPEP 2106.04(d)(1), applying conventional machine learning methods to a new data environment—even "high resolution" or "granular" data—does not constitute a technological improvement unless the claim recites a specific improvement to the ML model itself (e.g., a novel architecture or training algorithm). Simply achieving a more accurate "outcome" through a generic ML application is an abstract idea, not a technical solution. The claim's recitation that the estimate is "usable by an operator to control" is a field-of-use restriction or a general instruction to "apply" the result of an abstract calculation. To integrate the idea into a practical application, the claim must recite the specific technical parameters of how the control is effectuated (e.g., automated closed-loop feedback) rather than merely providing an "indication" to a human operator. To be eligible, the claim must specify "how" the claim language provides for a technical solution rather than just reciting a functional result. Achieving a “commitment” is categorized as an administrative or business goal, which falls under the "Certain Methods of Organizing Human Activity" grouping of abstract ideas. Improving the efficiency of a business or regulatory process does not qualify as an improvement to "other technology" or a "technical field" under Step 2A, Prong 2. Under MPEP 2106, it maintains that performing human-like tasks (estimating, scheduling, mapping) with greater speed or efficiency via computers does not transform an abstract idea into eligible subject matter. The nature of generating an estimate remains a mathematical or mental concept even if computerized.
The current claims are very different from McRO. In McRO, the claims recited specific mathematical rules that replaced subjective human judgment to automate a technical task. In contrast, the present claim provides an indication that is "usable by an operator," meaning the human still exercises judgment.
Applicant 103 arguments
Applicant respectfully disagrees. Nevertheless, without conceding the correctness of the rejections and solely to advance prosecution, Applicant has amended the claims herein. For example, claim 1 (and similarly claims 10 and 16) has been amended to recite, inter alia, the following:
training at least one machine-learning model to estimate an emissions factor of at least one equipment component of the first hydrocarbon operation location using the first set of equipment data and the emissions data of the first hydrocarbon operation location, wherein the at least one machine-learning model is specific to the at least one equipment component of the first hydrocarbon operation location;
receiving a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location;
identifying, using the second set of equipment data, at least one equipment component of the second hydrocarbon operation location that is a same component as the at least one equipment component of the first hydrocarbon operation location;
applying the at least one machine-learning model to the second set of equipment data to estimate an emissions factor of at least one equipment component of the second hydrocarbon operation location
As agreed, upon during the Examiner Interview of November 19, 2025, Cousins does not teach or suggest each and every element of amended claim 1. As a result, amended claim 1 (and similarly amended claims 10 and 16) are allowable over Cousins. Each of claims 4-6, 8, 12- 14, and 18 depend either directly or indirectly from one of claim 1, 10, or 16 and are therefore allowable for at least the same reasons as well as for the individual elements they recite.
Examiner response
Examiner respectfully disagrees. The instant claim is different than the one presented in Examiner interview of November 19, 2025, thus Cousin reference is still applied here.
Cousin discloses training a machine-learning model using emissions measurement data collected from hydrocarbon operation locations to learn relationship between emissions measurements and equipment types (see para [0013], [0032-0035]). The trained model produces equipment-specific emissions estimates that characterize emissions behavior associated with particular equipment components.
Cousin further discloses receiving equipment data for a user-selected target site, including types and quantities of equipment present at that site (see [0045] [0062]). Cousin categorizes equipment by type (e.g., tanks, separators, valves) and stores emissions estimates indexed by equipment type ([0002], [0018], [0044]). Thus, identification of “the same equipment component” across sites is therefore disclosed in Cousin, as equipment components at the second hydrocarbon operation location are identified by matching their equipment types to the equipment types for which emissions estimates were previously generated.
Cousin further discloses applying machine-learning model derived emissions estimates to equipment present at a selected target site in order to generate total emission estimate for that site. ([0024], [0044-0046], [0062]). These emissions estimates are the result of the trained machine learning model and represent learned parameters associated with specific equipment components. Under the broadest reasonable interpretation, “applying the machine learning model” includes applying model-derived parameters or outputs such as equipment-specific emissions factors-to new equipment data. The claim does not require re-executing the trained model on the second-site data or performing real-time inference at the second site. Thus, the rejection is still maintained.
Claim Rejections - 35 USC §101
4. 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.
5. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. These claims are directed to an abstract idea without significantly more.
(Step 1) Is the claims to a process, machine, manufacture, or composition of matter?
Claims: 1-9 are directed method or process, which falls on the one of the statutory category.
Claims:10-15 is directed system or machine, which falls on the one of the statutory category.
Claim: 16-20 is directed to non-transitory computer readable storage medium storing one or more program, which falls on the one of the statutory category that is manufacture.
Regarding claims 1, 10 and 16
Step 1 Prong one
collecting a first set of equipment data from a first hydrocarbon operation location; collecting emissions data relating to the first hydrocarbon operation location; and receiving a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location; (A human could, in principle, go to different locations, observe the equipment and emissions, and note the data on a piece of paper or in their mind. This makes the steps akin to an unpatentable mental process. Claims recite a mental process since it contains limitations that can practically be performed in the human mind, including for example, observations, evaluations, judgments, and opinions. Examples of claims that recite mental processes include: See MPEP 2106.05(a)(2)(III)(A)• a claim to “collecting information, analyzing it, and displaying certain results of the collection and analysis,” where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016);
identifying, using the second set of equipment data, at least one equipment component of the second hydrocarbon operation location that is a same component as the at least one equipment component of the first hydrocarbon operation location; A claim describing "identifying a common component between two hydrocarbon locations by comparing their equipment lists" is a mental process because a human can: read a list of equipment for Location A (e.g., a "Model X Pressure Valve"), read a list for Location B and look for the same "Model X Pressure Valve." and mentally conclude that both locations use the same component)
generating a total emissions estimate of the second hydrocarbon operation location for a predetermined operation time using the emissions factor of the at least one equipment component of the second hydrocarbon operation location, A technician at a natural gas site (the second location) notes that a specific compressor (equipment component) has an emission factor of 2.5 kg CO2e per hour. To estimate total emissions for a 24-hour shift (predetermined time), they multiply 2.5 by 24 to get 60 kg CO2e. Because this can be done mentally, it is an abstract mental process. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgment that could be performed in the human mind or with the aid of pencil and paper therefore falls within the “Mental Process” grouping of abstract ideas. Also, the process relies on a basic mathematical relationship (Emissions = Activity Data × Emission Factor). So, it also falls under the mathematical concepts of abstract ideas)
Step 2A, Prong 2: Does the claim recite additional elements that integrate the judicial exception?
In accordance with Step 2A, Prong 2, the judicial exception is not integrated into a practical application. Also claim limitation such as collecting a first set of equipment data from a first hydrocarbon operation location; collecting emissions data relating to the first hydrocarbon operation location; and receiving a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location; which also can be recited at a high level of generality (i.e., as a general means of gathering data), and falls under the insignificant extra solution activity. (See MPEP 2106.05(g) The additional elements of training at least one machine-learning model to estimate an emissions factor of at least one equipment component of the first hydrocarbon operation location using the first set of equipment data and the emissions data of the first hydrocarbon operation location, wherein the at least one machine-learning model is specific to the at least one equipment component of the first hydrocarbon operation location and applying the at least one machine-learning model to the second set of equipment data to estimate an emissions factor of at least one equipment component of the second hydrocarbon operation location are amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) It merely applies a known tool (ML) to a new field (hydrocarbon emissions). The additional elements of “wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location” is further limiting it to a particular field of use (hydrocarbon process) and describing its intended use by an operator (usability to control) were considered "incidental or token additions" that did not provide a practical, non-generic application. The additional elements of a system comprising: a processor; and a memory in claim 10 are amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) The additional elements of a non-transitory computer-readable medium comprising instructions that are executable by a processor in claim 16 are amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) Therefore, claims 1, 10 and 16 are directed to abstract idea.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of collecting a first set of equipment data from a first hydrocarbon operation location; collecting emissions data relating to the first hydrocarbon operation location; and receiving a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location which is recited at a high level of generality (i.e., as a general means of gathering), and falls under the insignificant extra solution activity and is well-understood, routine or conventional. ((See MPEP 2106.05(d) i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) The additional elements of training at least one machine-learning model to estimate an emissions factor of at least one equipment component of the first hydrocarbon operation location using the first set of equipment data and the emissions data of the first hydrocarbon operation location, wherein the at least one machine-learning model is specific to the at least one equipment component of the first hydrocarbon operation location and applying the at least one machine-learning model to the second set of equipment data to estimate an emissions factor of at least one equipment component of the second hydrocarbon operation location are amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) It merely applies a known tool (ML) to a new field (hydrocarbon emissions). The additional elements of “wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location” is further limiting it to a particular field of use (hydrocarbon process) and describing its intended use by an operator (usability to control) were considered "incidental or token additions" that did not provide a practical, non-generic application. The claims do not describe an improvement to the underlying technology of the machine-learning model itself, the computer's functionality. The additional elements of a system comprising: a processor; and a memory in claim 10 are amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) The additional elements of a non-transitory computer-readable medium comprising instructions that are executable by a processor in claim 16 are amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) Therefore, claims 1, 10 and 16 are directed to abstract idea.
Claim 2 further recites wherein the total emissions estimate of the second hydrocarbon operation location is usable by the operator to control the at least one equipment component of the second hydrocarbon operation location to achieve a yearly emissions commitment. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgment that could be performed in the human mind or with the aid of pencil and paper therefore falls within the “Mental Process” grouping of abstract ideas. The underlying abstract idea is the mere calculation of emissions data and the general concept of using data to monitor compliance with a goal (a yearly emissions commitment). Data manipulation and goal setting are fundamental economic/business practices. While the estimate is 'usable by the operator to control the at least one equipment component,' this limitation is merely a field-of-use restriction or a merely instructs an operator to apply an exception using generic components to achieve a business or regulatory goal (the 'yearly emissions commitment'). and does not impose a meaningful limit on the abstract idea. The claim does not improve the functioning of the equipment itself but rather describes an administrative or regulatory goal (achieving a "yearly emissions commitment"). The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 3, 11 and 17 further recites wherein the emissions data comprises emissions rates, emissions plume heights, maximum emissions concentrations, emissions persistence, and a location of the at least one equipment component of the first hydrocarbon operation location. It is recited at a high level of generality (i.e., as a general means of gathering), and falls under the insignificant extra solution activity and is well-understood, routine or conventional. ((See MPEP 2106.05(d) i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 4 and 12 further recites preprocessing the first set of equipment data and the emissions data by standardizing units of the first set of equipment data and the emissions data. A person can determine which metrics need to be standardized (e.g., equipment power and CO2 emissions), what the target units will be (e.g., converting everything to kilowatts and kilograms of CO2e), and what conversion factors are needed. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgment that could be performed in the human mind or with the aid of pencil and paper therefore falls within the “Mental Process” grouping of abstract ideas. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 5 and 13 further recites wherein training the at least one machine-learning model comprises training a plurality of machine-learning models, wherein each machine-learning model of the plurality of machine-learning models is associated with an individual equipment component of the first hydrocarbon operation location. It amounts to no more than mere instructions to apply the exception using generic computer components. (MPEP 2106.05(f) This type of limitation merely confines the use of the abstract idea to a particular technological environment (machine learning) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h). The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 6, 14 and 18 further recites wherein the emissions factor comprises a methane emissions factor. It amounts to no more than mere instructions to apply the exception using generic computer components for estimating methane emission factor. (MPEP 2106.05(f) The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 7, 15 and 19 further recites wherein the at least one machine-learning model comprises a deep convolutional neural network (DCNN). This type of limitation merely confines the use of the abstract idea to a particular technological environment (machine learning) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h). The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 8 further recites wherein the emissions data comprises historical leak data extracted from leak detection and repair (LDAR) reports for the at least one equipment component of the first hydrocarbon operation location. It is recited at a high level of generality (i.e., as a general means of gathering), and falls under the insignificant extra solution activity and is well-understood, routine or conventional. ((See MPEP 2106.05(d) i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) v. Electronically scanning or extracting data from a physical document, Content Extraction and Transmission, LLC v. Wells Fargo Bank, 776 F.3d 1343, 1348, 113 USPQ2d 1354, 1358 (Fed. Cir. 2014) (optical character recognition); The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 9 and 20 further recites wherein the emissions data comprises weather characteristics extracted from local weather reports for the first hydrocarbon operation location. It is recited at a high level of generality (i.e., as a general means of gathering), and falls under the insignificant extra solution activity and is well-understood, routine or conventional. ((See MPEP 2106.05(d) i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) v. Electronically scanning or extracting data from a physical document, Content Extraction and Transmission, LLC v. Wells Fargo Bank, 776 F.3d 1343, 1348, 113 USPQ2d 1354, 1358 (Fed. Cir. 2014) (optical character recognition); The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 102
6. 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 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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
7. Claim(s) 1-2, 4-6, 8, 10, 12-14, 16 and 18 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Cousin et al. (PUB NO: US 20230065744 A1)
Regarding claim 1
Cousin teaches a method, comprising: collecting a first set of equipment data from a first hydrocarbon operation location; (see para 18-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 27- In some examples, operational data about equipment operation may be used in addition to, or as an alternative to, measurements from the fixed sensing equipment. See para 34-Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. See also para 44-45-As shown, the datastore 230 can include different types of equipment 302 a-n. Through the GUI, the user 226 can input, upload, or select a dataset specifying which types of equipment are located at a target site and how many pieces of each type of equipment are located at the target site. For example, the GUI may present first visual page through which the user 226 can input, upload, or select the dataset.)
collecting emissions data relating to the first hydrocarbon operation location; (see para 18-22-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. The data acquisition systems 114 can receive the measurements from the mobile sensing equipment and the fixed sensing equipment 118a-b. Additionally or alternatively, the data acquisition systems 114 can receive measurements of gaseous byproduct emissions from other data sources. The data acquisition systems 114 can receive, process, and store the measurements for subsequent use. )
training at least one machine-learning model to estimate an emissions factor of at least one equipment component of the first hydrocarbon operation location using the first set of equipment data and the emissions data of the first hydrocarbon operation location, wherein the at least one machine-learning model is specific to the at least one equipment component of the first hydrocarbon operation location;; (see para 13-The classification model may be a machine learning model capable of learning and improving in accuracy over time. The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. see para 32-35-The classification module 210 can receive the measurements 232 (e.g., the preprocessed measurements) and classify each measurement in the data as belonging to a particular type of equipment. In other examples, the classification model 234 can include a neural network, Naive Bayes classifier, decision tree, logistic regression classifier, a support vector machine, or any combination of these. The classification model 234 can learn how to divide a higher-level measurement among different types of equipment based on its exposure to training data. For example, the classification model 234 can be trained using the training data. The training data can include relationships between higher-level measurements and lower-level measurements. For example, the training data can include relationships between site-level measurements and equipment-level measurements. In some examples, the higher-level measurements and equipment-level measurements may be collected from the data sources 220a-d over a period of time, and the relationships in the training data can be generated based on those measurements. For example, data source 220a may provide a site-level measurement of an amount of methane gas emitted at a specific site. Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d. See para 40-44-The predetermined emissions estimates can be industry-standard emissions estimates, such as precomputed emissions factors for oil and gas equipment published by the American Petroleum Institute® or the Environmental Protection Agency®. One example of the information stored in the datastore 230 is shown in FIG. 3. As shown, the datastore 230 can include different types of equipment 302a-n mapped to their respective sets of measurements 304a-n, their respective first emissions estimates 306a-n generated using the first emissions estimation module 212, and their respective second emissions estimates 308a-n generated using the second emissions estimation module 214.)
receiving a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location; (see para 11-Having determined the emissions estimates, the GUI system can next use the emissions estimates to determine how much of the gaseous byproduct is emitted in total by each type of equipment at a target site or a target asset, which can be selected by the user. see para 18-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 27- In some examples, operational data about equipment operation may be used in addition to, or as an alternative to, measurements from the fixed sensing equipment. See para 34-Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. See para 45-. Through the GUI, the user 226 can input, upload, or select a dataset specifying which types of equipment are located at a target site and how many pieces of each type of equipment are located at the target site.)
identifying, using the second set of equipment data, at least one equipment component of the second hydrocarbon operation location that is a same component as the at least one equipment component of the first hydrocarbon operation location; (see para 18- Examples of such sites can include well sites, refinement sites, production sites, etc. Each site can include one or more hydrocarbon facilities with equipment used to produce hydrocarbons, bring them to the surface, store them, process them, and/or prepare them for export to market. Examples of this equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. The sites 102 a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 44- The datastore 230 can also include the number of pieces of each type of equipment 310 a-n that are located at a target site.)
Examiner note: Cousin categorizes equipment by type (e.g., tank, separators) consistently across sites and stores emission estimates by equipment type (see para [0002], [0018], [0044]). Identification of the “same component” across sites is achieved through equipment-type matching.
applying the at least one machine-learning model to the second set of equipment data to estimate an emissions factor of at least one equipment component of the second hydrocarbon operation location. (see para 13-The classification model may be a machine learning model capable of learning and improving in accuracy over time. The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. See para 24-The computing system 120 can then apply machine learning or other analysis techniques to the historical dataset to generate emissions estimates at the equipment level. For example, the computing system 120 can determine an emissions estimate for each individual type of equipment, where the emissions estimate for a given type of equipment is an estimate of gaseous byproduct emissions by that type of equipment during a particular time interval. see para 34-35-The classification model 234 can learn how to divide a higher-level measurement among different types of equipment based on its exposure to training data. For example, the classification model 234 can be trained using the training data. The training data can include relationships between higher-level measurements and lower-level measurements. For example, the training data can include relationships between site-level measurements and equipment-level measurements. In some examples, the higher-level measurements and equipment-level measurements may be collected from the data sources 220a-d over a period of time, and the relationships in the training data can be generated based on those measurements. For example, data source 220a may provide a site-level measurement of an amount of methane gas emitted at a specific site. Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d. See para 40-44-The predetermined emissions estimates can be industry-standard emissions estimates, such as precomputed emissions factors for oil and gas equipment published by the American Petroleum Institute® or the Environmental Protection Agency®. One example of the information stored in the datastore 230 is shown in FIG. 3. As shown, the datastore 230 can include different types of equipment 302a-n mapped to their respective sets of measurements 304a-n, their respective first emissions estimates 306a-n generated using the first emissions estimation module 212, and their respective second emissions estimates 308a-n generated using the second emissions estimation module 214.)
generating a total emissions estimate of the second hydrocarbon operation location for a predetermined operation time using the emissions factor of the at least one equipment component of the second hydrocarbon operation location. (See para 46- Next, the GUI generation module 206 can then determine the total amount of the gaseous byproduct emitted by a particular type of equipment over a selected time period. This can be referred to as a total emissions estimate. To determine the total emissions, estimate for a particular type of equipment, the GUI generation module 206 can use the following equation: Total emissions estimate = EE×Num where EE is an emissions estimate and Num is the number of pieces of that type of equipment specified in the dataset. See para 62- he computing system 120 may also receive a user input indicating a timespan to be analyzed. The computing system 120 can then determine one or more total emissions estimates over the selected timespan for a particular type of equipment input by the user. See para 65-66- The site-level estimates box 502 can describe the aggregate emissions of all the equipment at a target site estimated for a particular gaseous byproduct 522. The graphical user interface 500 also includes a site-level historical measurements box 504, which summarizes site-level emissions data over a specified time period 530.)
wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location. (See para 001-More specifically, but not by way of limitation, this disclosure relates to a graphical user interface for assisting operators in abating emissions of gaseous byproducts from one or more hydrocarbon assets associated with producing and processing hydrocarbons from a subterranean formation. See para 16-In some examples, the GUI system can also enable operators to monitor for potential problem assets. For example, the GUI can include alerting functionality for outputting alerts. The GUI system can output the alerts, for example, if certain types of equipment or certain hydrocarbon facilities emit an amount of a gaseous byproduct that meets or exceeds an alerting threshold. The alerts and alert thresholds may be selectable and customizable by the user. These and other aspects of the GUI system may allow operators to prevent catastrophes (e.g., if there is a leak of a volatile byproduct gas that could lead to an explosion or hazardous conditions), as well as more easily track and meet their reduction targets. See para 69- In another example event 702 b, a mitigation event 726 is displayed which affects the estimates associated with a type of equipment 724. The recent actions box 718 can also display recommendations 704 that might help reduce emissions at a particular site or for a particular type of equipment.)
Regarding claim 15
Cousin teaches a system comprising: a processor; and a memory that includes instructions executable by the processor for causing the processor to: (see fig 2 and para 28-The computing system 120 can include a processor 202 communicatively coupled to a memory 204. The processor 202 is hardware that can include one processing device or multiple processing devices. Non-limiting examples of the processor 202 include a Field-Programmable Gate Array (FPGA), an application-specific integrated circuit (ASIC), or a microprocessor. The processor 202 can execute instructions (e.g., software modules 206-218) stored in the memory 204 to perform computing operations. The instructions may include processor-specific instructions generated by a compiler or an interpreter from code written in any suitable computer-programming language, such as C, C++, C#, Python, or Java.)
collect a first set of equipment data from a first hydrocarbon operation location; (see para 18-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 27- In some examples, operational data about equipment operation may be used in addition to, or as an alternative to, measurements from the fixed sensing equipment. See para 34-Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. See also para 44-45-As shown, the datastore 230 can include different types of equipment 302 a-n. Through the GUI, the user 226 can input, upload, or select a dataset specifying which types of equipment are located at a target site and how many pieces of each type of equipment are located at the target site. For example, the GUI may present first visual page through which the user 226 can input, upload, or select the dataset.)
collect emissions data relating to the first hydrocarbon operation location; (see para 18-22-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. The data acquisition systems 114 can receive the measurements from the mobile sensing equipment and the fixed sensing equipment 118a-b. Additionally or alternatively, the data acquisition systems 114 can receive measurements of gaseous byproduct emissions from other data sources. The data acquisition systems 114 can receive, process, and store the measurements for subsequent use. )
train at least one machine-learning model to estimate an emissions factor of at least one equipment component of the first hydrocarbon operation location using the first set of equipment data and the emissions data of the first hydrocarbon operation location, wherein the at least one machine-learning model is specific to the at least one equipment component of the first hydrocarbon operation location;; (see para 13-The classification model may be a machine learning model capable of learning and improving in accuracy over time. The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. see para 32-35-The classification module 210 can receive the measurements 232 (e.g., the preprocessed measurements) and classify each measurement in the data as belonging to a particular type of equipment. In other examples, the classification model 234 can include a neural network, Naive Bayes classifier, decision tree, logistic regression classifier, a support vector machine, or any combination of these. The classification model 234 can learn how to divide a higher-level measurement among different types of equipment based on its exposure to training data. For example, the classification model 234 can be trained using the training data. The training data can include relationships between higher-level measurements and lower-level measurements. For example, the training data can include relationships between site-level measurements and equipment-level measurements. In some examples, the higher-level measurements and equipment-level measurements may be collected from the data sources 220a-d over a period of time, and the relationships in the training data can be generated based on those measurements. For example, data source 220a may provide a site-level measurement of an amount of methane gas emitted at a specific site. Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d. See para 40-44-The predetermined emissions estimates can be industry-standard emissions estimates, such as precomputed emissions factors for oil and gas equipment published by the American Petroleum Institute® or the Environmental Protection Agency®. One example of the information stored in the datastore 230 is shown in FIG. 3. As shown, the datastore 230 can include different types of equipment 302a-n mapped to their respective sets of measurements 304a-n, their respective first emissions estimates 306a-n generated using the first emissions estimation module 212, and their respective second emissions estimates 308a-n generated using the second emissions estimation module 214.)
receive a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location; (see para 11-Having determined the emissions estimates, the GUI system can next use the emissions estimates to determine how much of the gaseous byproduct is emitted in total by each type of equipment at a target site or a target asset, which can be selected by the user. see para 18-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 27- In some examples, operational data about equipment operation may be used in addition to, or as an alternative to, measurements from the fixed sensing equipment. See para 34-Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. See para 45-. Through the GUI, the user 226 can input, upload, or select a dataset specifying which types of equipment are located at a target site and how many pieces of each type of equipment are located at the target site.)
identify, using the second set of equipment data, at least one equipment component of the second hydrocarbon operation location that is a same component as the at least one equipment component of the first hydrocarbon operation location; (see para 18- Examples of such sites can include well sites, refinement sites, production sites, etc. Each site can include one or more hydrocarbon facilities with equipment used to produce hydrocarbons, bring them to the surface, store them, process them, and/or prepare them for export to market. Examples of this equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. The sites 102 a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 44- The datastore 230 can also include the number of pieces of each type of equipment 310 a-n that are located at a target site.)
Examiner note: Cousin categorizes equipment by type (e.g., tank, separators) consistently across sites and stores emission estimates by equipment type (see para [0002], [0018], [0044]). Identification of the “same component” across sites is achieved through equipment-type matching.
apply the at least one machine-learning model to the second set of equipment data to estimate an emissions factor of at least one equipment component of the second hydrocarbon operation location. (see para 13-The classification model may be a machine learning model capable of learning and improving in accuracy over time. The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. See para 24-The computing system 120 can then apply machine learning or other analysis techniques to the historical dataset to generate emissions estimates at the equipment level. For example, the computing system 120 can determine an emissions estimate for each individual type of equipment, where the emissions estimate for a given type of equipment is an estimate of gaseous byproduct emissions by that type of equipment during a particular time interval. see para 34-35-The classification model 234 can learn how to divide a higher-level measurement among different types of equipment based on its exposure to training data. For example, the classification model 234 can be trained using the training data. The training data can include relationships between higher-level measurements and lower-level measurements. For example, the training data can include relationships between site-level measurements and equipment-level measurements. In some examples, the higher-level measurements and equipment-level measurements may be collected from the data sources 220a-d over a period of time, and the relationships in the training data can be generated based on those measurements. For example, data source 220a may provide a site-level measurement of an amount of methane gas emitted at a specific site. Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d. See para 40-44-The predetermined emissions estimates can be industry-standard emissions estimates, such as precomputed emissions factors for oil and gas equipment published by the American Petroleum Institute® or the Environmental Protection Agency®. One example of the information stored in the datastore 230 is shown in FIG. 3. As shown, the datastore 230 can include different types of equipment 302a-n mapped to their respective sets of measurements 304a-n, their respective first emissions estimates 306a-n generated using the first emissions estimation module 212, and their respective second emissions estimates 308a-n generated using the second emissions estimation module 214.)
generate a total emissions estimate of the second hydrocarbon operation location for a predetermined operation time using the emissions factor of the at least one equipment component of the second hydrocarbon operation location. (See para 46- Next, the GUI generation module 206 can then determine the total amount of the gaseous byproduct emitted by a particular type of equipment over a selected time period. This can be referred to as a total emissions estimate. To determine the total emissions, estimate for a particular type of equipment, the GUI generation module 206 can use the following equation: Total emissions estimate = EE×Num where EE is an emissions estimate and Num is the number of pieces of that type of equipment specified in the dataset. See para 62- he computing system 120 may also receive a user input indicating a timespan to be analyzed. The computing system 120 can then determine one or more total emissions estimates over the selected timespan for a particular type of equipment input by the user. See para 65-66- The site-level estimates box 502 can describe the aggregate emissions of all the equipment at a target site estimated for a particular gaseous byproduct 522. The graphical user interface 500 also includes a site-level historical measurements box 504, which summarizes site-level emissions data over a specified time period 530.)
wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location. (See para 001-More specifically, but not by way of limitation, this disclosure relates to a graphical user interface for assisting operators in abating emissions of gaseous byproducts from one or more hydrocarbon assets associated with producing and processing hydrocarbons from a subterranean formation. See para 16-In some examples, the GUI system can also enable operators to monitor for potential problem assets. For example, the GUI can include alerting functionality for outputting alerts. The GUI system can output the alerts, for example, if certain types of equipment or certain hydrocarbon facilities emit an amount of a gaseous byproduct that meets or exceeds an alerting threshold. The alerts and alert thresholds may be selectable and customizable by the user. These and other aspects of the GUI system may allow operators to prevent catastrophes (e.g., if there is a leak of a volatile byproduct gas that could lead to an explosion or hazardous conditions), as well as more easily track and meet their reduction targets. See para 69- In another example event 702 b, a mitigation event 726 is displayed which affects the estimates associated with a type of equipment 724. The recent actions box 718 can also display recommendations 704 that might help reduce emissions at a particular site or for a particular type of equipment.)
Regarding claim 16
Cousin teaches a non-transitory computer-readable medium comprising instructions that are executable by a processor for causing the processor to perform operations comprising (see para 28 and fig 2-At least some of the memory 204 includes a non-transitory computer-readable medium from which the processor 202 can read instructions. A computer-readable medium can include electronic, optical, magnetic, or other storage devices capable of providing the processor 202 with computer-readable instructions or other program code. Some examples of a computer-readable medium include magnetic disks, memory chips, ROM, random-access memory (RAM), an ASIC, a configured processor, optical storage, or any other medium from which a computer processor can read the instructions.)
receiving a first set of equipment data from a first hydrocarbon operation location; (see para 18-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 27- In some examples, operational data about equipment operation may be used in addition to, or as an alternative to, measurements from the fixed sensing equipment. See para 34-Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. See also para 44-45-As shown, the datastore 230 can include different types of equipment 302 a-n. Through the GUI, the user 226 can input, upload, or select a dataset specifying which types of equipment are located at a target site and how many pieces of each type of equipment are located at the target site. For example, the GUI may present first visual page through which the user 226 can input, upload, or select the dataset.)
receiving emissions data relating to the first hydrocarbon operation location; (see para 18-22-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. The data acquisition systems 114 can receive the measurements from the mobile sensing equipment and the fixed sensing equipment 118a-b. Additionally or alternatively, the data acquisition systems 114 can receive measurements of gaseous byproduct emissions from other data sources. The data acquisition systems 114 can receive, process, and store the measurements for subsequent use. )
training at least one machine-learning model to estimate an emissions factor of at least one equipment component of the first hydrocarbon operation location using the first set of equipment data and the emissions data of the first hydrocarbon operation location, wherein the at least one machine-learning model is specific to the at least one equipment component of the first hydrocarbon operation location;; (see para 13-The classification model may be a machine learning model capable of learning and improving in accuracy over time. The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. see para 32-35-The classification module 210 can receive the measurements 232 (e.g., the preprocessed measurements) and classify each measurement in the data as belonging to a particular type of equipment. In other examples, the classification model 234 can include a neural network, Naive Bayes classifier, decision tree, logistic regression classifier, a support vector machine, or any combination of these. The classification model 234 can learn how to divide a higher-level measurement among different types of equipment based on its exposure to training data. For example, the classification model 234 can be trained using the training data. The training data can include relationships between higher-level measurements and lower-level measurements. For example, the training data can include relationships between site-level measurements and equipment-level measurements. In some examples, the higher-level measurements and equipment-level measurements may be collected from the data sources 220a-d over a period of time, and the relationships in the training data can be generated based on those measurements. For example, data source 220a may provide a site-level measurement of an amount of methane gas emitted at a specific site. Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d. See para 40-44-The predetermined emissions estimates can be industry-standard emissions estimates, such as precomputed emissions factors for oil and gas equipment published by the American Petroleum Institute® or the Environmental Protection Agency®. One example of the information stored in the datastore 230 is shown in FIG. 3. As shown, the datastore 230 can include different types of equipment 302a-n mapped to their respective sets of measurements 304a-n, their respective first emissions estimates 306a-n generated using the first emissions estimation module 212, and their respective second emissions estimates 308a-n generated using the second emissions estimation module 214.)
receiving a second set of equipment data from a second hydrocarbon operation location different from the first hydrocarbon operation location; (see para 11-Having determined the emissions estimates, the GUI system can next use the emissions estimates to determine how much of the gaseous byproduct is emitted in total by each type of equipment at a target site or a target asset, which can be selected by the user. see para 18-FIG. 1 depicts an example of a system 100 for abating emissions of gaseous byproducts from one or more sites 102a-d according to some aspects of the present disclosure. Some of the sites 102a-c can include wellbores 104a-c drilled through a subterranean formation 116. The wellbores 104a-c can be cased or uncased. The wellbores 104a-c may be drilled proximate to hydrocarbon reservoirs 106a-c for extracting the hydrocarbons therein from the subterranean formation 116. The sites 102a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 27- In some examples, operational data about equipment operation may be used in addition to, or as an alternative to, measurements from the fixed sensing equipment. See para 34-Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. See para 45-. Through the GUI, the user 226 can input, upload, or select a dataset specifying which types of equipment are located at a target site and how many pieces of each type of equipment are located at the target site.)
identifying, using the second set of equipment data, at least one equipment component of the second hydrocarbon operation location that is a same component as the at least one equipment component of the first hydrocarbon operation location; (see para 18- Examples of such sites can include well sites, refinement sites, production sites, etc. Each site can include one or more hydrocarbon facilities with equipment used to produce hydrocarbons, bring them to the surface, store them, process them, and/or prepare them for export to market. Examples of this equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. The sites 102 a-d can include different types of equipment for performing various operations, such as drilling, processing, and production operations. Examples of the different types of equipment can include well heads, flow lines, tanks, separators, trunk lines, etc. see para 44- The datastore 230 can also include the number of pieces of each type of equipment 310 a-n that are located at a target site.)
Examiner note: Cousin categorizes equipment by type (e.g., tank, separators) consistently across sites and stores emission estimates by equipment type (see para [0002], [0018], [0044]). Identification of the “same component” across sites is achieved through equipment-type matching.
applying the at least one machine-learning model to the second set of equipment data to estimate an emissions factor of at least one equipment component of the second hydrocarbon operation location. (see para 13-The classification model may be a machine learning model capable of learning and improving in accuracy over time. The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. See para 24-The computing system 120 can then apply machine learning or other analysis techniques to the historical dataset to generate emissions estimates at the equipment level. For example, the computing system 120 can determine an emissions estimate for each individual type of equipment, where the emissions estimate for a given type of equipment is an estimate of gaseous byproduct emissions by that type of equipment during a particular time interval. see para 34-35-The classification model 234 can learn how to divide a higher-level measurement among different types of equipment based on its exposure to training data. For example, the classification model 234 can be trained using the training data. The training data can include relationships between higher-level measurements and lower-level measurements. For example, the training data can include relationships between site-level measurements and equipment-level measurements. In some examples, the higher-level measurements and equipment-level measurements may be collected from the data sources 220a-d over a period of time, and the relationships in the training data can be generated based on those measurements. For example, data source 220a may provide a site-level measurement of an amount of methane gas emitted at a specific site. Data sources 220b-d may be sensors coupled to individual pieces of equipment at the site, where the sensor can provide equipment-level measurements of the amount of methane gas emitted from each individual piece of equipment at the site. Based on these measurements, it can be determined how much methane gas each individual type of equipment contributed to the site-level measurement. The proportion with which each individual type of equipment contributed to the site-level measurement can then be stored in the training data. This process can be repeated hundreds or thousands of times, using measurements from one or multiple sites, to create the training data. In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d. See para 40-44-The predetermined emissions estimates can be industry-standard emissions estimates, such as precomputed emissions factors for oil and gas equipment published by the American Petroleum Institute® or the Environmental Protection Agency®. One example of the information stored in the datastore 230 is shown in FIG. 3. As shown, the datastore 230 can include different types of equipment 302a-n mapped to their respective sets of measurements 304a-n, their respective first emissions estimates 306a-n generated using the first emissions estimation module 212, and their respective second emissions estimates 308a-n generated using the second emissions estimation module 214.)
generating a total emissions estimate of the second hydrocarbon operation location for a predetermined operation time using the emissions factor of the at least one equipment component of the second hydrocarbon operation location. (See para 46- Next, the GUI generation module 206 can then determine the total amount of the gaseous byproduct emitted by a particular type of equipment over a selected time period. This can be referred to as a total emissions estimate. To determine the total emissions, estimate for a particular type of equipment, the GUI generation module 206 can use the following equation: Total emissions estimate = EE×Num where EE is an emissions estimate and Num is the number of pieces of that type of equipment specified in the dataset. See para 62- he computing system 120 may also receive a user input indicating a timespan to be analyzed. The computing system 120 can then determine one or more total emissions estimates over the selected timespan for a particular type of equipment input by the user. See para 65-66- The site-level estimates box 502 can describe the aggregate emissions of all the equipment at a target site estimated for a particular gaseous byproduct 522. The graphical user interface 500 also includes a site-level historical measurements box 504, which summarizes site-level emissions data over a specified time period 530.)
wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location. (See para 001-More specifically, but not by way of limitation, this disclosure relates to a graphical user interface for assisting operators in abating emissions of gaseous byproducts from one or more hydrocarbon assets associated with producing and processing hydrocarbons from a subterranean formation. See para 16-In some examples, the GUI system can also enable operators to monitor for potential problem assets. For example, the GUI can include alerting functionality for outputting alerts. The GUI system can output the alerts, for example, if certain types of equipment or certain hydrocarbon facilities emit an amount of a gaseous byproduct that meets or exceeds an alerting threshold. The alerts and alert thresholds may be selectable and customizable by the user. These and other aspects of the GUI system may allow operators to prevent catastrophes (e.g., if there is a leak of a volatile byproduct gas that could lead to an explosion or hazardous conditions), as well as more easily track and meet their reduction targets. See para 69- In another example event 702 b, a mitigation event 726 is displayed which affects the estimates associated with a type of equipment 724. The recent actions box 718 can also display recommendations 704 that might help reduce emissions at a particular site or for a particular type of equipment.)
Regarding claim 4 and 12
Cousins further teaches preprocessing the first set of equipment data and the emissions data by standardizing units of the first set of equipment data and the emissions data. (See para 31- As shown in FIG. 2, the computing system 120 can include a data preprocessing module 208. The data preprocessing module 208 is executable to access the measurements 232 and apply one or more preprocessing techniques to the measurements 232. One example of such preprocessing techniques can include normalizing or otherwise standardizing the measurements 232. For example, the data preprocessing module 208 can normalize the measurements 232 so that they all have the same units, such as parts per million (ppm) or standard cubic feet per hour (scf/h). This may involve converting measurements from one type of unit to another type of unit using one or more predefined algorithms. Another example of the preprocessing techniques can include removing outliers from the measurements 232. For example, the data preprocessing module 208 can delete or otherwise remove measurements that fall outside of a predefined range of measurement values (e.g., an expected range of measurement values). Applying the preprocessing techniques can improve the accuracy of subsequent processes performed using the measurements 232. With the preprocessing complete, the data preprocessing module 208 can transmit the preprocessed measurements to the classification module 210.)
Regarding claim 5 and 13
Cousins further teaches wherein training the at least one machine-learning model comprises training a plurality of machine-learning models, wherein each
PNG
media_image1.png
9
4
media_image1.png
Greyscale
machine-learning model of the plurality of machine-learning models is associated with an individual equipment component of the first hydrocarbon operation location. (See para 24-The computing system 120 can then apply machine learning or other analysis techniques to the historical dataset to generate emissions estimates at the equipment level. For example, the computing system 120 can determine an emissions estimate for each individual type of equipment, where the emissions estimate for a given type of equipment is an estimate of gaseous byproduct emissions by that type of equipment during a particular time interval. Based on how many pieces of each type of equipment are located at the target site, the computing system 120 can compute the expected total emissions output from each individual type of equipment at the target site during a selected time interval. See para 35- In some examples, the classification model 234 can be periodically retrained. For example, additional measurements can be collected over time from the data sources 220a-d and used to update the training data. The classification model 134 can then be retrained using the updated training data. In this way, the classification model 234 may be capable of learning and improving in accuracy over time as it is exposed to more measurements from the data sources 220a-d.)
Regarding claim 6, 14 and 18
Cousins further teaches wherein the emissions factor comprises a methane emissions factor. (See para 15-In some examples, the GUI system can integrate a variety of data sources and machine learning together to help operators better understand how gaseous byproducts are emitted at their hydrocarbon facilities. With a better understanding of this footprint, operators can set more-realistic reduction targets (e.g., methane reduction targets) with respect to gaseous byproduct emissions. See also fig 5-7 and para 66- For example, the site-level historical measurements box 504 can display a graphical portrayal 526, such as a line graph, of one or more aggregate estimated gaseous byproduct emissions of all the equipment at a target site for a particular gaseous byproduct 522.)
Regarding claim 8
Cousins further teaches wherein the emissions data comprises historical leak data extracted from leak detection and repair (LDAR) reports for the at least one equipment component of the first hydrocarbon operation location. (See para 13- The classification module can “learn” and become “smarter” as it is exposed to more data over time, so that the classification module can accurately assign collected measurements to different types of equipment. This, in turn, can lead to more accurate emissions estimates. In some examples, operational data can also be used to improve the model’s accuracy over time. Examples of such operational data can include pressure readings and leak detection and repair (LDAR) reports. See para 24-More specifically, the computing system 120 can receive measurements collected from the sensing equipment over a period of time. The computing system 120 may receive the measurements directly from or indirectly from (e.g., via the data acquisition systems 114) the sensing equipment. The computing system 120 can then process the measurements to create a historical dataset. see fig 7 and para 68- FIG. 7 depicts another view of the graphical user interface 500 according to some aspects of the present disclosure. The equipment-level estimates summary box 706 shows the estimated gaseous byproduct emissions for various types of equipment at a target site 710 for a particular byproduct 716. The equipment-level estimates summary box 706 can display estimated emissions for various types of equipment at the target site using numerical values 714 or graphically 708, for example, as a bar graph.)
Claim Rejections - 35 USC § 103
8. 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.
9. 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.
10. Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Cousins et al. (PUB NO: US 20230065744 A1), in view of Scott et al., (PUB NO: US 20220091026 A1).
Regarding claim 2
Cousins further teaches wherein the total emissions estimate of the second hydrocarbon operation location is usable by an operator to control the at least one equipment component of the second hydrocarbon operation location (See para 001-More specifically, but not by way of limitation, this disclosure relates to a graphical user interface for assisting operators in abating emissions of gaseous byproducts from one or more hydrocarbon assets associated with producing and processing hydrocarbons from a subterranean formation. See para 16-In some examples, the GUI system can also enable operators to monitor for potential problem assets. For example, the GUI can include alerting functionality for outputting alerts. The GUI system can output the alerts, for example, if certain types of equipment or certain hydrocarbon facilities emit an amount of a gaseous byproduct that meets or exceeds an alerting threshold. The alerts and alert thresholds may be selectable and customizable by the user. These and other aspects of the GUI system may allow operators to prevent catastrophes (e.g., if there is a leak of a volatile byproduct gas that could lead to an explosion or hazardous conditions), as well as more easily track and meet their reduction targets. See para 69- In another example event 702 b, a mitigation event 726 is displayed which affects the estimates associated with a type of equipment 724. The recent actions box 718 can also display recommendations 704 that might help reduce emissions at a particular site or for a particular type of equipment.)
In the relative field of invention, Scott teaches to achieve a yearly emissions commitment; (See para 255-This process may provide a total emission estimation from one period to the next. Interpolation considering diurnal effects and seasonality may be used for padding the total flux estimate when measurements were unavailable, and total emission flux for periods of interest such as a week, a month, a quarter, a year or so on may be evaluated. See para 287- In particular, the analysis from the existing data stream informs about which sites are large emitters and which sites are emitting less. If an operator has many sites, such as in the upstream oil and gas industry, having different approaches for different sites may be a cost-effective emissions reduction strategy. The average number of failures or leaks per equipment type may be predicted from a maintenance report, and the combined number of failures or leaks per year for a site may be calculated from these equipment failures or leaks or extracted from the maintenance or leaks report data streams.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method for abating emissions of gaseous byproducts at hydrocarbon assets as disclosed by Cousins to include achieve a yearly emissions commitment as taught by Scott in the system of Cousins for reducing fugitive emissions and providing remote monitoring of facilities and/or equipment that often emit gasses. (see para [0007], Scott)
10. Claims 3, 9, 11, 17 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Cousins et al. (PUB NO: US 20230065744 A1), in view of Brandt et al., (PUB NO: US 20220357230 A1).
Regarding claim 3, 11 and 17
Cousins further teaches wherein the emissions data comprises emissions persistence, and a location for the at least one equipment component of the first hydrocarbon operation location. (See para 66-For example, the site-level historical measurements box 504 can display a graphical portrayal 526, such as a line graph, of one or more aggregate estimated gaseous byproduct emissions of all the equipment at a target site for a particular gaseous byproduct 522. The graphical portrayal 526 can indicate the estimated emissions 514 and baseline emissions 528 relative to emissions reductions targets 520b. The graphical portrayal 526 can also include historical event data 516 highlighting events that might affect the emissions estimates. The graphical portrayal 526 can also display historical data from previous time periods 512.)
Cousins does not teach wherein the emissions data comprises emissions rates, emissions plume heights, maximum emissions concentrations.
In the related field of invention, Brandt teaches wherein the emissions data comprises emissions rates, emissions plume heights, maximum emissions concentrations. (see para 60- In some embodiments, a sensor unit 120 may include two intake tubes 123, enabling the sensor unit 120 to collect air samples from two different heights (for example, at the top of the mast 126 and at the middle of the mast 126). In addition to increasing the likelihood that at least one of the intake tubes 123 will intercept the emissions plume of a gas leak, collecting spaced-vertically air samples helps to define the spatial distribution of gas within the plume, which can be used within a plume model (as described below with reference to FIGS. 6-17) to better define what the likely emissions rate is at the leak source. see para 166-117-FIG. 5B is a graph of the emission rates measured by all six sensor units 120 when METEC did not release gas. FIG. 5C is a graph of the emission rates measured by all six sensor units 120 when METEC released gas. METEC released methane at rates varying between 0.2 kg/hour and 2.3 kg/hour. FIGS. 5B and 5C show a clear difference in the measured emission rates when METEC released methane relative to when METEC did not release gas. FIG. 5D is a graph of the methane concentration measured by the gas leak detection system 100 when METEC did not release gas. FIG. 5E is a graph of the methane concentration measured by the gas leak detection system 100 when METEC released gas.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method for abating emissions of gaseous byproducts at hydrocarbon assets as disclosed by Cousins to include wherein the emissions data comprises emissions rates, emissions plume heights, maximum emissions concentrations as taught by Brandt in the system of Cousins in order to monitor gas concentrations at multiple locations across a site (e.g., a well pad or other oil or natural gas facility), enabling the gas leak detection system to model gas leak emission rates in two- or three-dimensional space to reveal the most likely origin of the gas leak. (See Abstract, Brandt)
Regarding claim 9 and 20
Cousins does not teach wherein the emissions data comprises weather characteristics extracted from local weather reports for the first hydrocarbon operation location.
In the related field of invention, Brandt wherein the emissions data comprises weather characteristics extracted from local weather reports for the first hydrocarbon operation location. (see para 115- FIG. 5A depicts the gas leak detection system 100 deployed for methane emissions testing and evaluation by the Methane Emissions Technology Evaluation Center (METEC) under a variety of weather conditions and gas release rates. The weather during the test varied wildly and included high winds, a light blizzard, low temperatures, and a sunny day, providing a robust test of emissions detection, quantification, and overall performance of the system 100. see para 138- FIG. 13 is a flowchart illustrating a surface layer air mixing conditions estimation process 1300 according to an exemplary embodiment. In the embodiment of FIG. 13, the Pasqill stability class 1310 is determined in step 1320 using a Pasquill stability class look-up table 1330 adapted from published literature and the solar irradiance 1120 (determined as described above with reference to FIG. 11), the sky cover estimate 1280 (determined as described above with reference to FIG. 12), the wind speed 1302 (determined, for example, by the anemometer 130 at the site 10), the wind variability 1304 (determined based on variance in the wind speed 1302 and wind direction 610 measurements over time, an external weather data source, etc.), the time 1102 of day, and the distance 730 from the sensor unit 120 to the grid cell 740 or the potential emissions source 750. External stability data 1340 from external sources 60, such as the U.S. Environmental Protection Agency (EPA) rawindsonde observations from online sources (e.g., University of Wyoming soundings database for North America), or estimations from forecast model output may also be used to identify the Pasquil stability class 1310.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method for abating emissions of gaseous byproducts at hydrocarbon assets as disclosed by Cousins to include wherein the emissions data comprises weather characteristics extracted from local weather reports for the first hydrocarbon operation location as taught by Brandt in the system of Cousins in order to monitor gas concentrations at multiple locations across a site (e.g., a well pad or other oil or natural gas facility), enabling the gas leak detection system to model gas leak emission rates in two- or three-dimensional space to reveal the most likely origin of the gas leak. (See Abstract, Brandt)
11. Claims 7, 15 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Cousins et al. (PUB NO: US 20230065744 A1), in view of MORIMOTO et al., (PUB NO: US 20230351568 A1).
Regarding claim 7, 15 and 19
Cousins does not teach wherein the at least one machine-learning model comprises a deep convolutional neural network (DCNN).
In the related field of invention, MORIMOTO teaches wherein the at least one machine-learning model comprises a deep convolutional neural network (DCNN). (See para 59-60-The machine learning unit 2141 is a circuit that executes machine learning on the basis of a combination of the first image received by the training image input unit 212 and the second image received by the correct image input unit 213 and generates a machine learning model. As the machine learning, for example, a convolutional neural network (CNN) can be used, and known software such as PyTorch can be used. FIG. 4(b) is a functional block diagram of the machine learning unit 2141 in the control unit 21. The machine learning model includes an input layer 51, an intermediate layer 52-1, intermediate layers 52-2, . . . , an intermediate layer 52-n, and an output layer 53, and an interlayer filter is optimized by learning.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method for abating emissions of gaseous byproducts at hydrocarbon assets as disclosed by Cousins to include wherein the at least one machine-learning model comprises a deep convolutional neural network (DCNN) as taught by MORIMOTO in the system of Cousins in order to reduce the influence of a change in the amount of infrared rays due to a high-luminance light source in a gas facility from an output image of a gas visualization imaging device, and it is possible to contribute to improvement of detection quality in gas leakage detection. (See para 0013, MORIMOTO)
Conclusion
12. Claims 1-20 are rejected.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 20170103325 A1 Meinrenken et al.
Discussing the systems for automating carbon footprinting are disclosed. In some embodiments, the methods include a plurality of steps. In some embodiments, related to predetermined resources associated with an item from predetermined data sources is obtained. Then, estimated emission factors are calculated for each of the resources. Next, a contributory uncertainty of the data and of the emission factors is determined. Then, a user is guided based on a comparison of the respective contributory uncertainty of data related to the resources or emission factors. Next, both data related to the resources and the estimated emission factors of the resources are utilized to determine a carbon footprint of the item.
US 20220372860 A1 Allen et al.
ii. Discussing method for generating a drilling plan for drilling a wellbore at a field includes receiving data. The data includes one or more of geological properties at the field, wellbore properties, drilling tool parameters, rig characteristics of drilling rigs, and working practices of a plurality of drilling crews. The method also includes generating a plurality of candidate drilling plans for drilling the wellbore at the field. The method also includes estimating one or more outputs for the candidate drilling plans based at least partially upon the data.
.
13. 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 PURSOTTAM GIRI whose telephone number is (469)295-9101. The examiner can normally be reached 7:30-5:30 PM, Monday to Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, RENEE CHAVEZ can be reached at 5712701104. 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.
/PURSOTTAM GIRI/Examiner, Art Unit 2186
/RENEE D CHAVEZ/Supervisory Patent Examiner, Art Unit 2186