Profile-based carbon capture forecasting

Abstract

A method includes processing sensor data corresponding to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period. The method includes predicting, based on processing the reference process parameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period. The method includes setting a profile associated with processing the gas by the processing facility with respect to at least the second temporal period based on predicting the performance parameter and a demand level for energy credits associated with processing the gas.

Description

PROFILE-BASED CARBON CAPTURE FORECASTINGCROSS REFEERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of an earlier filing date from Italian Application No. 102024000015103, filed July 1, 2024, the entire disclosure of which is incorporated herein by reference in its entirety.BACKGROUND

[0002] Various embodiments supported by aspects of the present disclosure relate to resource recovery and fluid sequestration industries, and more particularly, to carbon capture, utilization and storage (CCUS) industries. Various embodiments supported by aspects of the present disclosure relate to decentralized autonomous tracking, and more particularly, to carbon abatement / removal tracking.

[0003] In the resource recovery and fluid sequestration industries, some systems support carbon abatement / removal tracking as a technique for businesses to measure operational efficiency and sustainability. For example, in some cases, if a business does not stay in compliance with environmental and climate change regulations, the operations of the business may be adversely affected. In an example, international and state governments have greenhouse gas reporting requirements for businesses to comply with.

[0004] Carbon tracking may involve measuring carbon emissions from direct and indirect sources. In accordance with some reporting standards, entities are required to disclose Scope 1, Scope 2, and Scope 3 greenhouse gas emissions, which means the entities are responsible for tracking and recording emissions, and further, preparing for mandatory reporting. However, the majority of systems developed to monitor and manage carbon trade in industrial applications (e.g., processing industries, the petroleum industry and the like) are centralized, unreliable, and highly non-transparent.

[0005] Development of effective techniques for monitoring for potential carbon taxation and effective schemes for carbon trading are desired. In some cases, due to the lack of standardization among entities in the carbon emissions and carbon trading market with respect to monitoring and trading, navigation of the carbon trading market may be difficult. Though some approaches have implemented blockchain technology for effective carbon trading and driving real emissions reductions and intemet-of-things (loT) based smart devices for tracking and reporting real-time emissions, techniques for improved carbon abatement / removal tracking are desired.

[0006] Some challenges faced by organizations in association with carbon removal may include effective implementation of carbon removal by equipment. Some challenges faced by the organizations in association with carbon removal may include effective tracking of the amount of carbon removed by the equipment. Some other challenges faced by organizations may include effective calculation of carbon emissions, which may include a responsibility to identify all the carbon emission sources such as, for example, transportation, electricity consumption, HVAC emissions, and other, business operations, calculate the emissions from the sources, and determine a total emissions due to the sources. Some approaches for calculating carbon footprints are manual processes dependent on user intervention or oversight, which may increase the chance of error and be time consuming.SUMMARY

[0007] Embodiments of the present disclosure are directed to a computer- implemented method including: processing, by a computing device, sensor data corresponding to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, by the computing device based on processing the reference process parameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period.

[0008] Embodiments of the present disclosure are also directed to a system including: one or more sensors; and a computing device including a processor and a memory, wherein the memory includes instructions stored thereon that, when executed by the processor, cause the processor to perform operations including: processing sensor data provided by the one or more sensors, wherein the sensor data corresponds to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, based on processing the reference process parameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period.

[0009] Embodiments of the present disclosure are also directed to a computer program product including a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations including: processing sensor data corresponding to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, based on processing the reference processparameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period.

[0010] Further aspects supported by the present disclosure and features of example embodiments are illustrated in the accompanying drawings and / or described in the following description.BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The following descriptions should not be considered limiting in any way. With reference to the accompanying drawings, like elements are numbered alike.

[0012] FIG. 1 is a diagram illustrating an example embodiment of a system supportive of profile-based carbon capture forecasting and decentralized autonomous tracking in accordance with aspects of the present disclosure.

[0013] FIG. 2 illustrates an example block diagram in accordance with one or more embodiments of the present disclosure.

[0014] FIG. 3 illustrates an example block diagram in accordance with one or more embodiments of the present disclosure.

[0015] FIGS. 4A and 4B illustrate an example block diagram in accordance with one or more embodiments of the present disclosure.

[0016] FIG. 5 illustrates an example block diagram in accordance with one or more embodiments of the present disclosure.

[0017] FIG. 6 illustrates an example flowchart of a method in accordance with one or more embodiments of the present disclosure.

[0018] FIG. 7 illustrates an example system in accordance with one or more embodiments of the present disclosure.DETAILED DESCRIPTION

[0019] A detailed description of one or more embodiments of the disclosed apparatus and method are presented herein by way of exemplification and not limitation with reference to the Figures.

[0020] FIG. 1 is a diagram illustrating an example embodiment of a system 100 supportive of profile-based carbon capture forecasting, decentralized carbon abatement / removal tracking, and decentralized autonomous carbon emissions tracking in accordance with aspects of the present disclosure.

[0021] According to one or more embodiments of the present disclosure, the system 100 supports carbon emission tracking for measuring operational efficiency and sustainability. In some embodiments, the system 100 supports carbon abatement / removal tracking for measuring operational efficiency and sustainability. For example, the system 100 supports the tracking of carbon production, separation, capture, and abatement. In some aspects, the system 100 supports the tracking of equipment that actively removes carbon from a process, system, and / or environment. As will be described herein, aspects of the system 100 solve existing problems associated with a disconnect between the carbon capture industry and the carbon tracking / credit industry. Aspects of the system 100 support tracking and accounting carbon credits in near real-time. In some aspects, the system 100 may include or implement a blockchain based decentralized autonomous platform capable of providing privacy protected tracking and trading.

[0022] As will be described herein, the system 100 bridges the gap between the carbon capture industry and the carbon credit industry through an edge-to-cloud web portal capable of providing improved visibility into the demand for captured carbon compared to some other systems. Aspects of the system 100 facilitate real-time pricing for carbon credits, providing a mechanism by which operations may change a respective carbon capture profile based on demand. The system 100 supports demand driven carbon credit production and improved efficiency / marketability of carbon capture.

[0023] The system 100 includes industrial assets 101 (e.g., industrial asset 101-a, industrial asset 101-b, and the like) sensor devices 102, programmable logic controllers 103, computing devices 105 (e.g., computing device 105-a through computing device 105-e), and a cloud network 110.

[0024] Each industrial asset 101 may be an industrial site (e.g., oil well, a carbon capture site (carbon capture plant), a processing facility, or the like). The industrial asset 101 may include equipment located at the industrial site. In an example, the industrial asset 101 may be an industrial site which processes a gas (e.g., carbon).

[0025] The sensor devices 102 may be in operable communication with a respective programmable logic controller 103 and equipment associated with a respective industrial asset 101. The sensor devices 102 may capture sensor data associated with the industrial asset 101. In an example, the sensor data may include an amount of gas (e.g., carbon dioxide) processed at the industrial site and an amount of an element (e.g., carbon) captured from processing the gas.

[0026] Other non-limiting examples of the sensor data are later described herein. Non-limiting examples of the industrial asset 101 are later described herein.

[0027] In some aspects, the computing devices 105 may be edge devices or loT devices coupled to carbon capture products at an industrial site, and the computing devices 105 may collect and record data associated with the carbon captured by the individual products in near real-time. For example, the recorded data may include time series data. The computing device 105 may run workloads associated with a respective industrial asset 101.

[0028] Each programmable logic controller 103 may be a ruggedized computer supportive of automating operations associated with a respective industrial asset 101. For example, each programmable logic controller 103 may support automating a specific process, machine function, or even an entire production line associated with a respective industrial asset 101.

[0029] Each computing device 105 may be an edge computing device associated with a respective industrial asset 101. Each computing device 105 may support data storage and forwarding associated with the respective industrial asset 101. For example, computing device 105-a may collect and store data from industrial asset 101-a over a temporal period (e.g., several months). The computing device 105-a may forward the stored data to cloud network 110 based on one or more criteria (e.g., when an internet connection satisfying a target reliability or data transfer speed is established). Each computing device 105 may be capable of autonomously or semi-autonomously performing decisions, for example, for cases in which no internet connection is established at the computing device 105. In some examples, each computing device 105 (or some of the computing devices 105) may be an loT device.

[0030] In some aspects, each computing device 105 may be capable of storing, forwarding, and receiving data associated with decentralized autonomous tracking (e.g., carbon emissions tracking, carbon abatement / removal tracking, and the like). For example, each computing device 105 may be capable of storing time series data, executing machine learning models (e.g., light weight machine learning models), executing data analytics code, transmitting set points to a programmable logic controller 103, tokenizing credits, sending data to the cloud network 110, and receiving data from the cloud network 110.

[0031] The cloud network 110 may support cloud processing operations. The cloud network 110 may include cloud based applications or server based applications. Settings of the applications may be partially or entirely customizable and may be managed by one or more users, by automatic processing, and / or by artificial intelligence.

[0032] The cloud network 110 may be capable of creating dashboards 115. In an example, the dashboards 115 may be KPI dashboards. In some aspects, via the dashboards 115, the cloud network 110 may provide metrics on data acquired from industrial assets 101 (e.g., CCUS sites), viewable carbon capture targets from various industrial assets 101, amount of carbon credit available, sold, or the like, and real-time carbon pricing.

[0033] The blockchain based platform 120 may support a distributed ledger 122 (also referred to herein as a blockchain ledger or Eco ledger) for captured carbon. In some aspects, the blockchain based platform 120 and the distributed ledger 122 may support ensuring chain of custody and just in time delivery. The blockchain based platform 120 may store data provided by the computing devices 105. Using blockchain technology, the blockchain based platform 120 may provide a reporting system is transparent and immutable.

[0034] The blockchain based platform 120 may support tokenizing credits associated with decentralized autonomous tracking (e.g., carbon emissions tracking, carbon abatement / removal tracking, and the like). Example aspects of credits generated, updated, and tokenized by the blockchain based platform 120 are later described herein.

[0035] The sales module 125 may be a cloud-based clearinghouse supportive of selling and purchasing carbon credits.

[0036] The components of the system 100 may be in electronic communication with one another via one or more communication protocols. For example, the system 100 supports communication between the computing devices 105, the cloud network 110, and other devices of the system 700 via wired communication protocols, wireless communication protocols (e.g., electromagnetic (EM) signals, WiFi, Bluetooth™, ZigBee™, Ubiquiti™, 3G, 4G, LTE, and the like), and / or combinations including one or more of the foregoing.

[0037] The system 100 is configured to perform and support profile-based carbon capture forecasting and decentralized autonomous tracking (e.g., carbon emissions tracking, carbon abatement / removal tracking, and the like) in accordance with one or more embodiments of the present disclosure. However, example aspects of the techniques supported by the system 100 as described herein are not limited to decentralized autonomous tracking (e.g., carbon emissions tracking, carbon abatement / removal tracking) described herein, and the system 100 may support features for profile-based processing of other substances and decentralized autonomous tracking of other suitable parameters and operations.

[0038] Components of the system 100 may include processing circuitry capable of executing instructions stored on a memory in association with performing one or morefunctions described herein. For example, each of the programmable logic controllers 103, computing devices 105, and cloud network 110 may include processing circuitry capable of executing instructions stored on a memory in association with performing one or more functions described herein. The processing circuitry may utilize data stored in the memory as a neural network. The neural network may include a machine learning architecture. In some other aspects, the neural network may be or include any suitable machine learning network for performing operations described herein. Non-limiting examples of the machine learning network include a deep learning network, a convolutional neural network, a reconstructive neural network, a generative adversarial neural network, or any other neural network capable of accomplishing functions described herein. Some elements stored in the memory may be described as or referred to as instructions or instruction sets, and some functions may be implemented using machine learning techniques.

[0039] As will be described herein, the system 100 supports profile-based carbon capture forecasting and the creation and management of a decentralized platform for tracking and reporting data. In some examples, the tracked data may include carbon abatement / removal data, emissions data, or the like. The system 100 may use sensor devices 102 and computing devices 105 (e.g., loT devices) to collect the data on carbon abatement / removal by various equipment located at industrial assets 101, and the system 100 may record the data to the distributed ledger 122. The system 100 may use sensor devices 102 and computing devices 105 (e.g., loT devices) to collect the data on emissions from various sources such as, for example, industrial assets 101, and the system 100 may record the data to the distributed ledger 122. In an example, the collected data may include sensor data provided by the sensor devices 102 and data (e.g., time series data, data output by machine learning models, analytics data, and the like) provided by the computing devices 105.

[0040] The platform may support access to the recorded data included in the distributed ledger 122. In an example, based on the recorded data, companies and organizations may monitor respective carbon processing and identify areas where the companies and organizations can offset their carbon footprint. In some aspects, with respect to the distributed ledger 122, blockchain based incentives can offset carbon emissions.

[0041] In some aspects, each computing device 105 may support federated learning, a machine learning technology that supports the analysis of data stored on a device (e.g., a computing device 105) without the data leaving the device on which the data is stored. In an example, federated learning may include privacy preserving measures federated learning(PPBFL) techniques which support collaborative machine learning without centralizing sensitive (e.g., customer) data. Accordingly, for example, for a given industrial asset 101 (e.g., industrial asset 101-a, industrial asset 101-b, industrial asset 101-c, or the like) associated with an entity (e.g., a company), the platform enables the entity to share carbon emissions data associated with the industrial asset 101 without compromising privacy.

[0042] In the example illustrated at FIG. 1, industrial assets 101 and programmable logic controllers 103 respectively associated with computing device 105-d through computing device 105 -f are omitted for brevity.

[0043] The use of blockchain technology by the system 100 ensures that any reported carbon credits are authentic and traceable. For example, the distributed ledger 122 provided and managed by the blockchain based platform 120 may prevent inadvertent multiple counting and / or multiple selling of carbon credits. Accordingly, for example, the blockchain based system provided by the platform supports transparent and immutable recording of data (e.g., carbon abatement / removal tracking data, carbon emission data, and the like). In some aspects, the blockchain based system supports the development of smart contracts capable of automating emissions verification, ensuring tamperproof and auditable records. The distributed ledger 122 supports effective management of carbon emissions, as the distributed ledger 122 provides a transparent and tamper-proof ledger of emissions data.

[0044] The system 100 supports the tracking, management, and transaction of carbon captured by CCUS products in near real-time as carbon credits. The blockchain based platform 120 supports tracking and accounting of credits throughout a distributed network (e.g., cloud network 110). In an example implementation, in association with deploying a carbon capture product (e.g., cryogenic carbon capture (CCC), industrial climate solutions (ICS), or the like) at an industrial asset 101, the systems and techniques described herein may include deploying and associating a computing device 105 with the carbon capture product. The computing device 105 includes a data acquisition system configured to record / predict the amount of carbon dioxide captured by the carbon capture product on a given day and relay the data to the cloud network 110. The cloud network 110 may provide a web application portal supportive of selling, as carbon credits in near real-time, carbon that is going to be captured by the carbon capture product. The blockchain based platform 120 may track credits over the cloud network 110 and ensure target accounting and transaction practices for carbon credit auditing and chain of custody.

[0045] As will be described herein, in accordance with one or more embodiments of the present disclosure, the system 100 supports a platform and an automated process fordecentralized tracking (e.g., carbon emissions tracking, carbon abatement / removal tracking, and the like) which may be implemented with reduced manual intervention, reduced error, increased robustness and sustainability, and increased reliability compared to some other approaches, providing effective carbon footprint reduction and improved economic impact for entities with respect to carbon capture. The system 100 supports profile-based carbon capture forecasting as will be described herein.

[0046] FIG. 2 illustrates an example block diagram 200 in accordance with one or more embodiments of the present disclosure. Example aspects which may be implemented by a computing device 105 (e.g., edge computer, loT device), cloud network 110, and blockchain based platform 120 of FIG. 1 in accordance with one or more embodiments of the present disclosure are described with reference to FIG. 2.

[0047] It is to be understood that the example operations described with reference to the computing device 105, the cloud network 110, and the blockchain based platform 120 are not limited to the examples, and embodiments of the present disclosure support implementing any of the example operations at any of the computing device 105, the cloud network 110, and the blockchain based platform 120. That is, for example, in accordance with one or more embodiments of the present disclosure, operations described with reference to the computing device 105 may be implemented at the cloud network 110, operations described with reference to the cloud network 110 may be implemented at the computing device 105, and the like.

[0048] The computing device 105 may support computing operations for baseline carbon capture calculation. For example, the computing device 105 may store baseline data including a baseline amount of carbon captured by an industrial asset 101 associated with the computing device 105. In an example, the baseline data may be with respect to a temporal period (e.g., 15 days). In some aspects, the computing device 105 may support steady state real-time data collection of the amount of carbon captured by the industrial asset 101.

[0049] The computing device 105 may support computing operations for comparing the baseline amount to a carbon capture amount provided by a pre-trained carbon capture model. For example, the computing device 105 may support computing operations for determining a difference between the baseline amount and the carbon capture amount provided by the pre-trained carbon capture model.

[0050] The computing device 105 may provide a data storage mechanism for process and environmental parameters for the industrial asset 101. For example, the computing device 105 may store process and environmental parameters for the industrial asset 101 to a memoryof the computing device 105, a database accessible by the computing device 105, or data storage coupled to the cloud network 110.

[0051] The computing device 105 may implement a machine learning model capable of predicting performance of the industrial asset 101 based on the baseline data. For example, the machine learning model may be capable of predicting a future amount of carbon captured by the industrial asset 101 based on processing the baseline amount of carbon captured by the industrial asset 101. In some examples, the machine learning model may be a light weight machine learning model, but is not limited thereto.

[0052] For example, the computing device 105 (or a computing device 105 of the cloud network 110) may process sensor data corresponding to a reference process parameter associated with processing a gas (e.g., carbon dioxide gas) by an industrial asset 101 with respect to a first temporal period. Non- limiting examples of the reference process parameter include an amount of carbon dioxide gas received at or processed by the industrial asset 101, a percentage of carbon included in the carbon dioxide gas, or an amount of a product (e.g., clean air) output by the industrial asset 101 based on processing the carbon dioxide gas. The computing device 105 may predict based on processing the reference process parameter using the machine learning model, a performance parameter associated with processing the gas by the industrial asset 101 in association with a second temporal period which occurs after the first temporal period.

[0053] The computing device 105 may implement a machine learning model capable of estimating degradation of the industrial asset 101. For example, the computing device 105 may predict a degradation parameter associated with processing the gas (e.g., carbon dioxide gas) by the industrial asset 101 with respect to at least the second temporal period. In some examples, the computing device 105 may predict the degradation parameter based on processing a variable associated with the gas with respect to the first temporal period. Nonlimiting examples of the variable include a pressure associated with processing the gas, a temperature associated with processing the gas, a material density associated with processing the gas, and an amount of a target element (e.g., carbon) captured in association with processing the gas.

[0054] The computing device 105 may support computing operations associated with updating the machine learning model remotely via the cloud network 110. For example, embodiments of the present disclosure support remote updating of the machine learning model at the computing device 105 via the cloud network 110 (e.g., via another computingdevice). In some examples, embodiments of the present disclosure support autonomous and semi-autonomous updating or retraining of the machine learning model.

[0055] The computing device 105 may support a real-time data transfer mechanism capable of transmitting data acquired or generated by the computing device 105 to the cloud network 110.

[0056] For example, the computing device 105 may support real-time data transfer of carbon capture amounts from an entire value chain including capture, utilization, and storage. In an example, the computing device 105 may support real-time data transfer of data to the cloud network 110, in which the data includes a current carbon capture amount by the industrial asset 101. In some aspects, the data may include a future carbon capture amount by the industrial asset 101. Accordingly, for example, the computing device 105 may support continuous or semi-continuous (e.g., based on trigger criteria) data transfer of current and future amounts of carbon captured, utilized, or stored by the industrial asset 101.

[0057] The cloud network 110 may provide a data collection mechanism for process and environmental parameters for carbon capture from computing devices 105 respectively associated with industrial assets 101. For example, the cloud network 110 may support continuous or semi-continuous collection of data from the computing devices 105, in which the data includes amounts of carbon captured, utilized, or stored by the industrial assets 101.

[0058] The cloud network 110 may implement a machine learning model capable of determining future carbon capture levels using data aggregated from computing devices 105 respectively associated with industrial assets 101. For example, the cloud network 110 may predict future carbon capture levels associated with the industrial assets 101 using the process and environmental parameters collected from the computing devices 105. In some examples, the predicted future carbon capture levels may include a predicted future amount of carbon captured by any of the industrial assets 101 (e.g., industrial asset 101-a, industrial asset 101 - b, or the like).

[0059] The cloud network 110 may implement a machine learning model capable of estimating degradation of an industrial asset 101 using data aggregated from computing devices 105 respectively associated with industrial assets 101. For example, the cloud network 110 may estimate a current degradation and / or predict a future degradation of any of the industrial assets 101 (e.g., industrial asset 101-a, industrial asset 101-b, or the like). In an example, using the machine learning model, the cloud network 110 may predict a degradation parameter associated with processing the gas (e.g., carbon dioxide gas) by any of theindustrial assets 101 (e.g., industrial asset 101-a, industrial asset 101-b, or the like) with respect to a future temporal period.

[0060] The cloud network 110 may support computing operations for managing or updating the distributed ledger 122 based on carbon capture amounts from the entire value chain from capture, utilization, to storage. For example, the cloud network 110 may update the distributed ledger 122 based on carbon capture, utilization, and storage associated with all of the industrial assets 101.

[0061] The cloud network 110 may support computing operations associated with updating a machine learning model at a computing device 105. In some examples, the cloud network 110 may support computing operations associated with transmitting or uploading an updated machine learning model to the computing device 105. For example, the cloud network 110 may generate a retrained machine learning model based on processing data aggregated from multiple computing devices 105 coupled to the cloud network 110, and the cloud network 110 may provide the retrained machine learning model to any of the computing devices 105. In some aspects, the cloud network 110 may implement a retrained machine learning model at the cloud network 110 in association with implementing operations of the cloud network 110 described herein.

[0062] The blockchain based platform 120 may support computing operations for maintaining the distributed ledger 122. For example, the blockchain based platform 120 may maintain the distributed ledger 122 based on carbon capture amounts from the entire value chain from capture, utilization, to storage.

[0063] In some aspects, the blockchain based platform 120 may maintain scheduling utilization rates and storage rates associated with carbon dioxide production in the distributed ledger 122. In some aspects, the blockchain based platform 120 may maintain a current demand level or a predicted demand level for energy credits associated with processing a gas (e.g., carbon dioxide emissions). In an example, the current demand level or a predicted demand level may include demand levels respective to entities or a cumulative demand level among entities.

[0064] The blockchain based platform 120 may support computing operations for updating the distributed ledger 122. For example, the blockchain based platform 120 may update the distributed ledger 122 to discount the loss of carbon through a value chain.

[0065] The blockchain based platform 120 may support computing operations for tracking lifecycle carbon capture cost and efficiency. For example, the blockchain basedplatform 120 may track carbon capture cost and efficiency with respect to the lifecycle of an industrial asset 101 or respective lifecycles of multiple industrial assets 101.

[0066] The blockchain based platform 120 may support operations for executing transactions between entities with respect to future inventory of carbon. For example, the blockchain based platform 120 may support managing, by a computing device associated with the blockchain based platform 120, transactions associated with selling, purchasing, or exchanging energy credits between industrial assets 101.

[0067] Accordingly, for example, the blockchain based platform 120 may provide a mechanism which supports the ability of entities to effectively and transparently track carbon emissions, purchase / sell carbon credits, and plan or modify operations associated with processing carbon dioxide emissions.

[0068] FIG. 3 illustrates an example block diagram 300 in accordance with one or more embodiments of the present disclosure. Example aspects which may be implemented by a computing device 105 (e.g., edge computer, loT device) of FIG. 1 in accordance with one or more embodiments of the present disclosure are described with reference to FIG. 3.

[0069] The computing device 105 may collect and store data 305 including baseline data and steady state real-time data as described herein. Non-limiting examples of the data 305 collected by the computing device 105 include temporal information 310 (e.g., date, time), process parameters 315, and environmental parameters 320 associated with an industrial asset 101. Non-limiting examples of the process parameters 315 include an amount of gas received at or processed by an industrial asset 101 (also referred to herein as air in / post combustion flue gas intake measurement), percentage of carbon dioxide included in the gas, or an amount of a product (e.g., clean air) output or stored by the industrial asset 101 based on processing the gas. Non-limiting examples of the environmental parameters 320 include atmospheric temperature, wind speed, precipitation, and air quality index.

[0070] The computing device 105 may calculate a performance parameter 325 (e.g., carbon capture amount) associated with the industrial asset 101 based on the process parameters 315. For example, the computing device 105 may calculate the performance parameter 325 based on an equation in which the performance parameter 325 is equal to (‘Amount Of Gas Received At Or Processed By An Industrial Asset 101’ - ‘Amount Of Product Output Or Stored By The Industrial Asset 101 Based On Processing The Gas’) X ‘Percentage Of Carbon Dioxide Included In The Gas.’

[0071] Additionally, or alternatively, the computing device 105 may calculate the performance parameter 325 based on the process parameters 315 and further based on theenvironmental parameters 320. For example, the computing device 105 may apply a weight factor to the performance parameter 325 based on any of the process parameters 315 or environmental parameters 320.

[0072] The computing device 105 may predict performance of the industrial asset 101 based on the data 305. For example, using a trained machine learning model as described herein, the computing device 105 may generate carbon capture prediction information 330 including a future amount of carbon predicted to be captured by the industrial asset 101.

[0073] In an example, the carbon capture prediction information 330 may include a predicted performance parameter 335 (e.g., carbon capture amount) and temporal information (e.g., date, time) associated with the predicted performance parameter 335. In some aspects, the carbon capture prediction information 330 may include a comparison of the predicted performance parameter 335 and the performance parameter 325 (e.g., measured carbon capture amount, calculated carbon capture amount) included in data 305.

[0074] The computing device 105 may estimate degradation of the industrial asset 101 based on the data 305 and the carbon capture prediction information 330. For example, the computing device 105 may generate carbon capture degradation prediction data 345 associated with processing a gas by the industrial asset 101

[0075] In an example, the carbon capture degradation prediction data 345 may include temporal information (e.g., date, time), pressure 350 associated with a carbon capture material used for carbon capture, temperature 355 of the carbon capture material, material density 360 associated with the carbon capture material, a captured amount 365 of carbon, and a degradation parameter 370 (e.g., an estimated degradation, a degradation percentage or ratio) associated with processing the gas by the industrial asset 101. The captured amount 365 of carbon may be, for example, the performance parameter 325 included in the data 305. In some examples, the degradation parameter 370 may include a degradation associated with performance of the industrial asset 101 in association with carbon capture.

[0076] FIGS. 4 A and 4B illustrate an example block diagram 400 in accordance with one or more embodiments of the present disclosure. Example aspects which may be implemented by a cloud network 110 of FIG. 1 in accordance with one or more embodiments of the present disclosure are described with reference to FIGS. 4 A and 4B.

[0077] The cloud network 110 may collect and store data 405 including steady state real-time data as described herein with respect to various industrial assets 101. For example, the cloud network 110 may support real-time collection of data 405 from the computing devices 105 in association with respective industrial assets 101, in which the data includestemporal information 410 (e.g., date, time), process parameters 415, environmental parameters 420, location information 421 associated with an industrial asset 101, material type 422 associated with carbon capture or processing at the industrial asset 101, and a performance parameter 425 (e.g., carbon capture amount) associated with the industrial asset 101.

[0078] The temporal information 410, process parameters 415, environmental parameters 420, and performance parameter 425 include aspects of like elements described herein, and repeated descriptions of like elements are omitted for brevity.

[0079] The cloud network 110 may predict performance of all of the industrial assets 101 based on the data 405. For example, using a trained machine learning model as described herein, the cloud network 110 may generate carbon capture prediction information 430 including a future amount of carbon predicted to be captured by each industrial asset 101 (or one or more target industrial assets 101).

[0080] In an example, the carbon capture prediction information 430 may include a predicted performance parameter 435 (e.g., carbon capture amount), temporal information (e.g., date, time) associated with the predicted performance parameter 435, location information 421 (e.g., Latitude, Longitude) of the industrial asset 101 associated with the predicted performance parameter 435, and material type 422 associated with the predicted performance parameter 435. In some examples, the location information 421 may further include an identifier (e.g., Oklahoma City (OKC), Dallas, or the like) associated with the industrial asset 101. In some aspects, the carbon capture prediction information 430 may include a comparison of the predicted performance parameter 435 and the performance parameter 425 (e.g., measured carbon capture amount, calculated carbon capture amount) included in data 405.

[0081] The predicted performance parameter 435 includes aspects of a predicted performance parameter 335 described herein, and repeated descriptions of the same are omitted for brevity.

[0082] The cloud network 110 may estimate degradation of each industrial asset 101 (or one or more target industrial assets 101) based on the data 405 and the carbon capture prediction information 430. For example, the cloud network 110 may generate carbon capture degradation prediction data 445 associated with processing a gas by each industrial asset 101 (or one or more target industrial assets 101).

[0083] In an example, with respect to each industrial asset 101, the carbon capture degradation prediction data 445 may include temporal information (e.g., date, time), pressure450 associated with a carbon capture material used for carbon capture, temperature 455 of the carbon capture material, material density 460 associated with the carbon capture material, a captured amount 465 of carbon, a degradation parameter 470 (e.g., an estimated degradation) associated with processing the gas by the industrial asset 101, location information 421, and material type 422.

[0084] The captured amount 465 of carbon may be, for example, the performance parameter 425 included in the data 405. The degradation parameter 470 includes aspects of a degradation parameter 370 described herein, and repeated descriptions of the same are omitted for brevity.

[0085] FIG. 5 illustrates an example block diagram 500 in accordance with one or more embodiments of the present disclosure. Example aspects which may be implemented by a blockchain based platform 120 of FIG. 1 in accordance with one or more embodiments of the present disclosure are described with reference to FIG. 5.

[0086] The blockchain based platform 120 may support tokenizing credits associated with decentralized autonomous tracking (e.g., carbon emissions tracking, carbon abatement / removal tracking, and the like). The blockchain based platform 120 may generate carbon tokens (e.g., carbon token 510, carbon token 515) based on processing baseline data 505. In an example, the blockchain based platform 120 may retrieve the baseline data 505 from the cloud network 110 (or computing devices 105 via the cloud network 110), and the baseline data 505 may be associated with an industrial asset 101 or multiple industrial assets 101 as described herein. The baseline data 505 may include aspects of the baseline data (e.g., data 305, data 405) described with reference to FIGS. 2 through 4, and repeated descriptions of like elements are omitted for brevity.

[0087] In some aspects, the blockchain based platform 120 may generate a carbon token 510 for future or current capture based on the baseline data 505. In an example, the carbon token 510 may include the information: Carbon Capture Eocation: OKC Carbon Capture Type : Material 1 Carbon Capture Date: Mar 24, 2024 Ledger Creation Date : Mar 24, 2024 Prediction Date : Null Ledger Updated Date : Sequestration Location : Sequestration Date:Carbon Captured Prediction Amount : NullCarbon Captured Actual Amount : 1 TON Carbon Sequestered Amount : Discount Applied : 0

[0088] In some aspects, the blockchain based platform 120 may generate an updated carbon token 515 after sequestration, based on the baseline data 505. In an example, the updated carbon token 515 may include the information: Carbon Capture Location: OKC Carbon Capture Type : Material 1 Carbon Capture Date: Mar 24, 2024 Ledger Creation Date : Mar 24, 2024 Prediction Date : Null Ledger Updated Date : Mar 30, 2024 Sequestration Location : Kansas City, MO Sequestration Date: Mar 30, 2024 Carbon Captured Prediction Amount : Null Carbon Captured Actual Amount : 1 TON Carbon Sequestered Amount : 0.75 TON Discount Applied : 25%

[0089] The blockchain based platform 120 may generate carbon tokens (e.g., carbon token 530, carbon token 535) based on processing prediction data 525. In an example, the blockchain based platform 120 may retrieve the prediction data 525 from the cloud network 110 (or a computing device 105 via the cloud network 110), and the prediction data 525 may be associated with an industrial asset 101 or multiple industrial assets 101 as described herein. The prediction data 525 may include aspects of the prediction data (e.g., carbon capture prediction information 330, predicted performance parameter 335, carbon capture prediction information 430, predicted performance parameter 435) described with reference to FIGS. 2 through 4, and repeated descriptions of like elements are omitted for brevity.

[0090] In some aspects, the blockchain based platform 120 may generate a carbon token 530 for future or current capture based on the prediction data 525. In an example, the carbon token 530 may include the information: Carbon Capture Location: OKC Carbon Capture Type : Material 1 Carbon Capture Date: April 24, 2024Ledger Creation Date : Mar 24, 2024Prediction Date : Mar 24, 2024Ledger Updated Date :Sequestration Location :Sequestration Date:Carbon Captured Prediction Amount : 1 TONCarbon Captured Actual Amount :Carbon Sequestered Amount :Discount Applied : 0

[0091] In some aspects, the blockchain based platform 120 may generate an updated carbon token 535 after sequestration, based on the prediction data 525. In an example, the updated carbon token 535 may include the information: Carbon Capture Location: OKC Carbon Capture Type : Material 1 Carbon Capture Date: April 24, 2024 Ledger Creation Date : Mar 24, 2024 Prediction Date : Mar 24, 2024 Ledger Updated Date : April 30, 2024 Sequestration Location : Kansas City, MO Sequestration Date: April 30, 2024Carbon Captured Prediction Amount : 1 TONCarbon Captured Actual Amount : 1 TONCarbon Sequestered Amount : 0.75 TONDiscount Applied : 25%

[0092] FIG. 6 illustrates an example flowchart of a method 600 in accordance with one or more embodiments of the present disclosure. The method 600 is an example computer- implemented method that may be implemented by a system 100 (e.g., computing device 105, cloud network 110, blockchain based platform 120) as described herein.

[0093] At 605, the method 600 includes processing, by a computing device (e.g., a computing device 105 such as, for example, computing device 105-a, a computing device implementing the cloud network 110, or the like), sensor data corresponding to a reference process parameter associated with processing a gas by a processing facility (e.g., an industrial asset 101, for example, industrial asset 101 -a) with respect to a first temporal period.

[0094] In some aspects, the reference process parameter is included in a set of reference process parameters including: an amount of the gas received at the processing facility with respect to the first temporal period; a percentage of a target element (e.g., carbon, carbon dioxide) included in the gas received at the processing facility; and an amount of a product (e.g., clean air) output by the processing facility based on processing the gas, where the product is substantially absent the target element.

[0095] At 610, the method 600 includes predicting, by the computing device based on processing the reference process parameter, a performance parameter (e.g., predicted performance parameter 335, predicted performance parameter 435) associated with processing the gas by the processing facility in association with a second temporal period.

[0096] In some aspects, predicting the performance parameter is further based on processing, by the computing device, an environmental parameter (e.g., environmental parameters 320, environmental parameters 420) associated with the processing facility with respect to the first temporal period.

[0097] At 615, the method 600 may include predicting, by the computing device, a degradation parameter (e.g., degradation parameter 370, degradation parameter 470) associated with processing the gas based on processing one or more variables associated with the gas with respect to the first temporal period. In some aspects, the one or more variables are included in a set of variables including: a pressure (e.g., pressure 350, pressure 450) associated with processing the gas; a temperature (e.g., temperature 355, temperature 455) associated with processing the gas; a material density (e.g., material density 360, material density 460) associated with processing the gas; and an amount (e.g., captured amount 365, captured amount 465) of a target element captured in association with processing the gas.

[0098] In some aspects, predicting the performance parameter at 610 is further based on processing, by the computing device, the degradation parameter associated with processing the gas by the processing facility with respect to at least the second temporal period.

[0099] At 620, the method 600 may include setting a profile associated with processing the gas by the processing facility with respect to at least the second temporal period based on: predicting the performance parameter; and a demand level for energy credits (e.g., by an entity, business, company, or the like) associated with processing the gas.

[0100] At 622, the method 600 may include controlling, by the computing device, one or more operations of the processing facility in association with processing thegas, based on the profile. For example, at 622, the method 600 may include controlling carbon capture operations of the processing facility based on the profile.

[0101] In an example, the method 600 may include determining a predicted output(s) by the processing facility based on a given profile(s). Using the predicted output(s) associated with the profile(s), the method 600 may include analyzing a downstream channel(s) and adjusting the profile to accommodate the expected capacity. Accordingly, for example, based on the analysis of the downstream channel(s), the method 600 may include adjusting the profile (or selecting a different profile) such that a performance parameter (e.g., carbon capture rate, amount of carbon captured) of the processing facility according to the profile satisfies the expected capacity.

[0102] At 625, the method 600 may include processing, by a second computing device (e.g., computing device 105-b, a computing device implementing the cloud network 110, or the like), a second reference process parameter associated with processing the gas by a second processing facility (e.g., another industrial asset 101, for example, industrial asset 101-b) with respect to the first temporal period, a third temporal period, or both. In some examples, the third temporal period may be the same as or may partially overlap the second temporal period.

[0103] At 630, the method 600 may include predicting, by the second computing device, based on processing the reference process parameter and the second reference process parameter by the second computing device, at least one of: the performance parameter associated with processing the gas by the processing facility in association with the second temporal period; and the performance parameter associated with processing the gas by the second processing facility in association with the second temporal period.

[0104] At 635, the method 600 includes managing, by a computing device (e.g., computing device 105-a, computing device 105-b, a computing device implementing the cloud network 110, or the like), a transaction associated with selling, purchasing, or exchanging energy credits with respect to the processing facility and at least one second processing facility (e.g., industrial asset 101-b), where managing the transaction is based on predicting the performance parameter.

[0105] In the descriptions of the flowcharts herein, the operations may be performed in a different order than the order shown, or the operations may be performed in different orders or at different times. Certain operations may also be left out of the flowcharts, one or more operations may be repeated, or other operations may be added to the flowcharts.

[0106] In the descriptions of the flowcharts herein, the operations may be performed in a different order than the order shown, or the operations may be performed in different orders or at different times. Certain operations may also be left out of the flowcharts, one or more operations may be repeated, or other operations may be added to the flowcharts.

[0107] FIG. 7 illustrates an example system 700 in accordance with one or more embodiments of the present disclosure. In some aspects, the system 700 supports the tracking of equipment that actively removes carbon from a process, system, and / or environment as described herein.

[0108] The system 700 illustrates an example of an industrial asset 101 described herein. The system 700 includes computing devices 705 (e.g., computing device 705-a, device 705-b), direct air capture equipment 710, sensor 755 (or multiple sensors 755), sensor 760 (or multiple sensors 760), and a database 780. The system 700 supports data management as described herein.

[0109] A computing device 705 (e.g., computing device 705-a) may be disposed in operable communication with direct air capture equipment 710 and / or sensors (e.g., sensor 755) associated with the direct air capture equipment 710. The computing device 705-a may be, for example, a programmable logic controller 103 or a computing device 105 (e.g., edge device, loT device) described herein.

[0110] The direct air capture equipment 710 supports features for pulling in atmospheric air and, through a series of reactions (e.g., chemical reactions), extracting carbon dioxide (CO2) and returning the rest of the air to the environment.

[0111] The system 700 supports communication between the computing device 705 and other devices of the system 700 via wired communication protocols, wireless communication protocols (e.g., electromagnetic (EM) signals, WiFi, Bluetooth™, ZigBee™, Ubiquiti™, 3G, 4G, LTE, and the like), and / or combinations including one or more of the foregoing.

[0112] The computing device 705 is configured to receive, store and / or transmit data generated from components included in the direct air capture equipment 710. The computing device 705 includes processing components configured to analyze received data. The computing device 705 includes processing components configured to provide data (and / or control signals) to other components of the system 700. The computing device 705 includes any number of suitable components, such as processors, memory, communication devices and power sources.

[0113] The system 700 may include a database 780 configured to store data (e.g., sensor data, processed data, machine learning models) associated with the system 700. The database 780 may include a relational database, a centralized database, a distributed database, an operational database, a hierarchical database, a network database, an object oriented database, a graph database, a NoSQL (non-relational) database, etc. In some aspects, the database 780 may store and provide access to, for example, any of the stored data described herein.

[0114] Set forth below are some embodiments of the foregoing disclosure:

[0115] Embodiment 1. A computer-implemented method characterized by: processing, by a computing device, sensor data corresponding to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, by the computing device based on processing the reference process parameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period.

[0116] Embodiment 2. A computer- implemented method as in any prior embodiment, further comprising: setting a profile associated with processing the gas by the processing facility with respect to at least the second temporal period based on: predicting the performance parameter; and a demand level for energy credits associated with processing the gas.

[0117] Embodiment 3. A computer-implemented method as in any prior embodiment, wherein the reference process parameter is comprised in a set of reference process parameters comprising: an amount of the gas received at the processing facility with respect to the first temporal period; a percentage of a target element comprised in the gas received at the processing facility; and an amount of a product output by the processing facility based at least in part on processing the gas, wherein the product is substantially absent the target element.

[0118] Embodiment 4. A computer-implemented method as in any prior embodiment, wherein predicting the performance parameter is further based on processing, by the computing device, an environmental parameter associated with the processing facility with respect to the first temporal period.

[0119] Embodiment 5. A computer-implemented method as in any prior embodiment, wherein predicting the performance parameter is further based on processing, by the computing device, a degradation parameter associated with processing the gas by the processing facility with respect to at least the second temporal period.

[0120] Embodiment 6. A computer-implemented method as in any prior embodiment, further comprising: predicting, by the computing device, the degradation parameter based on processing one or more variables associated with the gas with respect to the first temporal period, wherein the one or more variables are comprised in a set of variables comprising: a pressure associated with processing the gas; a temperature associated with processing the gas; a material density associated with processing the gas; and an amount of a target element captured in association with processing the gas.

[0121] Embodiment 7. A computer-implemented method as in any prior embodiment, further comprising: processing, by a second computing device, a second reference process parameter associated with processing the gas by a second processing facility with respect to the first temporal period, a third temporal period, or both; and predicting, by the second computing device, based on processing the reference process parameter and the second reference process parameter by the second computing device, at least one of: the performance parameter associated with processing the gas by the processing facility in association with the second temporal period; and the performance parameter associated with processing the gas by the second processing facility in association with the second temporal period.

[0122] Embodiment 8. A computer-implemented method as in any prior embodiment, further comprising: managing, by the computing device, a transaction associated with selling, purchasing, or exchanging energy credits with respect to the processing facility and at least one second processing facility, wherein managing the transaction is based at least in part on predicting the performance parameter.

[0123] Embodiment 9. A system comprising: one or more sensors; and a computing device comprising a processor and a memory, wherein the memory comprises instructions stored thereon that, when executed by the processor, cause the processor to perform operations comprising: processing sensor data provided by the one or more sensors, wherein the sensor data corresponds to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, based on processing the reference process parameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period.

[0124] Embodiment 10. A system as in any prior embodiment, wherein the instructions, when executed by the processor, further cause the processor to perform operations comprising: setting a profile associated with processing the gas by the processingfacility with respect to at least the second temporal period based on: predicting the performance parameter; and a demand level for energy credits associated with processing the gas.

[0125] Embodiment 11. A system as in any prior embodiment, wherein the reference process parameter is comprised in a set of reference process parameters comprising: an amount of the gas received at the processing facility with respect to the first temporal period; a percentage of a target element comprised in the gas received at the processing facility; and an amount of a product output by the processing facility based at least in part on processing the gas, wherein the product is substantially absent the target element.

[0126] Embodiment 12. A system as in any prior embodiment, wherein predicting the performance parameter is further based on processing, by the processor, an environmental parameter associated with the processing facility with respect to the first temporal period.

[0127] Embodiment 13. A system as in any prior embodiment, wherein predicting the performance parameter is further based on processing, by the processor, a degradation parameter associated with processing the gas by the processing facility with respect to at least the second temporal period.

[0128] Embodiment 14. A system as in any prior embodiment, wherein the instructions, when executed by the processor, further cause the processor to perform operations comprising: predicting, by the computing device, the degradation parameter based on processing one or more variables associated with the gas with respect to the first temporal period, wherein the one or more variables are comprised in a set of variables comprising: a pressure associated with processing the gas; a temperature associated with processing the gas; a material density associated with processing the gas; and an amount of a target element captured in association with processing the gas.

[0129] Embodiment 15. A system as in any prior embodiment, further comprising: a second computing device comprising a second processor and a second memory, wherein the second computing device is comprised in a cloud network, wherein the second memory comprises instructions stored thereon that, when executed by the second processor, cause the second processor to perform operations comprising: processing one or more second reference parameters associated with processing the gas by a second processing facility with respect to the first temporal period, a third temporal period, or both; and predicting, based on processing the reference process parameter and the second reference process parameter, at least one of: the performance parameter associated with processing thegas by the processing facility in association with the second temporal period; and the performance parameter associated with processing the gas by the second processing facility in association with the second temporal period.

[0130] Embodiment 16. A system as in any prior embodiment, further comprising: a third computing device comprising a third processor and a third memory, wherein the third computing device is comprised in the cloud network, wherein the third memory comprises instructions stored thereon that, when executed by the third processor, cause the third processor to perform operations comprising: managing, by the third computing device, a transaction associated with selling, purchasing, or exchanging energy credits with respect to the processing facility and at least one second processing facility, wherein managing the transaction is based at least in part on the predicted performance parameter.

[0131] Embodiment 17. A system as in any prior embodiment, wherein the computing device is at a network edge of a network associated with the processing facility.

[0132] Embodiment 18. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising: processing sensor data corresponding to a reference process parameter associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, based on processing the reference process parameter, a performance parameter associated with processing the gas by the processing facility in association with a second temporal period.

[0133] Embodiment 19. A computer program product as in any prior embodiment, wherein the program instructions, when executed by the processor, further cause the processor to perform operations comprising: setting a profile associated with processing the gas by the processing facility with respect to at least the second temporal period based on: predicting the performance parameter; and a demand level for energy credits associated with processing the gas.

[0134] Embodiment 20. A computer program product as in any prior embodiment, wherein predicting the performance parameter is further based on processing, by the processor, a degradation parameter associated with processing the gas by the processing facility with respect to at least the second temporal period.

[0135] The use of the terms “a” and “an” and “the” and similar referents in the context of describing the invention (especially in the context of the following claims) are tobe construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. Further, it should be noted that the terms “first,” “second,” and the like herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The terms “about”, “substantially” and “generally” are intended to include the degree of error associated with measurement of the particular quantity based upon the equipment available at the time of filing the application. For example, “about” and / or “substantially” and / or “generally” can include a range of ± 8% of a given value.

[0136] The teachings of the present disclosure may be used in a variety of well operations. These operations may involve using one or more treatment agents to treat a formation, the fluids resident in a formation, a borehole, and I or equipment in the borehole, such as production tubing. The treatment agents may be in the form of liquids, gases, solids, semi-solids, and mixtures thereof. Illustrative treatment agents include, but are not limited to, fracturing fluids, acids, steam, water, brine, anti-corrosion agents, cement, permeability modifiers, drilling muds, emulsifiers, demulsifiers, tracers, flow improvers etc. Illustrative well operations include, but are not limited to, hydraulic fracturing, stimulation, tracer injection, cleaning, acidizing, steam injection, water flooding, cementing, etc.

[0137] While the invention has been described with reference to an exemplary embodiment or embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed as the best mode contemplated for carrying out this invention, but that the invention will include all embodiments falling within the scope of the claims. Also, in the drawings and the description, there have been disclosed exemplary embodiments of the invention and, although specific terms may have been employed, they are unless otherwise stated used in a generic and descriptive sense only and not for purposes of limitation, the scope of the invention therefore not being so limited.

Claims

CLAIMS1. A computer- implemented method (600) characterized by: processing, by a computing device (105-a), sensor data corresponding to a reference process parameter (315) associated with processing a gas by a processing facility (101-a) with respect to a first temporal period; and predicting, by the computing device (105-a) based on processing the reference process parameter (315), a performance parameter (325) associated with processing the gas by the processing facility (101-a) in association with a second temporal period.

2. The computer-implemented method (600) of claim 1, further comprising: setting a profile associated with processing the gas by the processing facility (101-a) with respect to at least the second temporal period based on: predicting the performance parameter (325); and a demand level for energy credits associated with processing the gas.

3. The computer-implemented method (600) of claim 1, wherein the reference process parameter (315) is comprised in a set of reference process parameters (315) comprising: an amount of the gas received at the processing facility (101-a) with respect to the first temporal period; a percentage of a target element comprised in the gas received at the processing facility (101-a); and an amount of a product output by the processing facility (101-a) based at least in part on processing the gas, wherein the product is substantially absent the target element.

4. The computer-implemented method (600) of claim 1, wherein predicting the performance parameter (325) is further based on processing, by the computing device (105- a), environmental parameter (320) associated with the processing facility (101-a) with respect to the first temporal period.

5. The computer-implemented method (600) of claim 1, wherein predicting the performance parameter (325) is further based on processing, by the computing device (105- a), a degradation parameter (370) associated with processing the gas by the processing facility (101-a) with respect to at least the second temporal period.

6. The computer-implemented method (600) of claim 5, further comprising: predicting, by the computing device (105-a), the degradation parameter (370) based on processing one or more variables associated with the gas with respect to the first temporal period, wherein the one or more variables are comprised in a set of variables comprising:a pressure associated with processing the gas; a temperature associated with processing the gas; a material density associated with processing the gas; and an amount of a target element captured in association with processing the gas.

7. The computer-implemented method (600) of claim 1, further comprising: processing, by a second computing device, a second reference process parameter(315) associated with processing the gas by a second processing facility (101-b) with respect to the first temporal period, a third temporal period, or both; and predicting, by the second computing device, based on processing the reference process parameter (315) and the second reference process parameter (315) by the second computing device (105-b), at least one of: the performance parameter (325) associated with processing the gas by the processing facility (101-a) in association with the second temporal period; and the performance parameter (325) associated with processing the gas by the second processing facility (101-b) in association with the second temporal period.

8. The computer-implemented method (600) of claim 1, further comprising: managing, by the computing device (105-a), a transaction associated with selling, purchasing, or exchanging energy credits with respect to the processing facility (101-a) and at least one second processing facility (101-b), wherein managing the transaction is based at least in part on predicting the performance parameter (325).

9. A system (100) characterized by: one or more sensors (102); and a computing device (105-a) characterized by a processor and a memory, wherein the memory comprises instructions stored thereon that, when executed by the processor, cause the processor to perform operations characterized by: processing sensor data provided by the one or more sensors (102), wherein the sensor data corresponds to a reference process parameter (315) associated with processing a gas by a processing facility with respect to a first temporal period; and predicting, based on processing the reference process parameter (315), a performance parameter (325) associated with processing the gas by the processing facility (101-a) in association with a second temporal period.

10. The system (100) of claim 9, wherein the instructions, when executed by the processor, further cause the processor to perform operations comprising: setting a profile associated with processing the gas by the processing facility (101-a) with respect to at least the second temporal period based on: predicting the performance parameter (325); and a demand level for energy credits associated with processing the gas.

11. The system (100) of claim 9, wherein the reference process parameter (315) is comprised in a set of reference process parameters (315) comprising: an amount of the gas received at the processing facility (101-a) with respect to the first temporal period; a percentage of a target element comprised in the gas received at the processing facility (101-a); and an amount of a product output by the processing facility (101-a) based at least in part on processing the gas, wherein the product is substantially absent the target element.

12. The system (100) of claim 9, wherein predicting the performance parameter (325) is further based on processing, by the processor, an environmental parameter (320) associated with the processing facility (101-a) with respect to the first temporal period.

13. The system (100) of claim 9, wherein predicting the performance parameter (325) is further based on processing, by the processor, a degradation parameter (370) associated with processing the gas by the processing facility (101-a) with respect to at least the second temporal period.

14. The system (100) of claim 9, further comprising: a second computing device comprising a second processor and a second memory, wherein the second computing device is comprised in a cloud network, wherein the second memory comprises instructions stored thereon that, when executed by the second processor, cause the second processor to perform operations comprising: processing one or more second reference parameters associated with processing the gas by a second processing facility (101-b) with respect to the first temporal period, a third temporal period, or both; and predicting, based on processing the reference process parameter (315) and the second reference process parameter (315), at least one of: the performance parameter (325) associated with processing the gas by the processing facility (101-a) in association with the second temporal period; andthe performance parameter (325) associated with processing the gas by the second processing facility (101-b) in association with the second temporal period; and a third computing device (105-c) comprising a third processor and a third memory, wherein the third computing device is comprised in the cloud network, wherein the third memory comprises instructions stored thereon that, when executed by the third processor, cause the third processor to perform operations comprising: managing, by the third computing device (105-c), a transaction associated with selling, purchasing, or exchanging energy credits with respect to the processing facility (101- a) and at least one second processing facility (101-b), wherein managing the transaction is based at least in part on the predicted performance parameter (325), and wherein the computing device (105-a) is at a network edge of a network associated with the processing facility (101-a).

15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising: processing sensor data corresponding to a reference process parameter (315) associated with processing a gas by a processing facility (101-a) with respect to a first temporal period; and predicting, based on processing the reference process parameter (315), a performance parameter (325) associated with processing the gas by the processing facility (101-a) in association with a second temporal period.

Images