ML driven automated screening and ranking of potential CCS sites

Abstract

Disclosed are methods, systems, and computer programs that determine an optimal location for fluid storage operations at a first site (e.g., a carbon capture and storage (CCS) site). The methods include: determining first data for the first site; generating a trained first ML model using the first data; generating preliminary location data associated with the first site using the trained first model; receiving second data associated with the first site; generating a trained second ML model based on the second data; and determining optimal locations at the first site where fluid can be stored by applying to the trained second ML model, the preliminary location data associated with the first site.

Description

ML DRIVEN AUTOMATED SCREENING AND RANKING OF POTENTIAL CCS SITESCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to US Provisional Application No. 63 / 595,597, filed on November 2, 2023, titled "ML Driven Automated Screening And Ranking Of Potential CCS Sites," which is incorporated herein by reference in its entirety for all purposes.TECHNICAL FIELD

[0002] This disclosure is directed to methods and systems for selecting optimal fluid storage locations associated with carbon capture and storage operations.BACKGROUND

[0003] Carbon capture and storage (CCS) operations provide mechanisms for achieving net zero carbon emissions goals. A CCS project may start with identifying suitable sites for greenhouse gas storage. This process can be regarded as a screening process which forms part of the initial steps for most CCS projects.

[0004] At the screening stage, feasibility data may be collected for a site (e.g., a resource site) under consideration for CCS operations. In some cases, this collected feasibility data may comprise limited and non-representative site maps or other geological data that are insufficient, and sometimes inadequate for creating or parameterizing geological computing models for the CCS operations. Furthermore, the feasibility data with attendant maps and / or geological computing models may rely on “chance of success” (COS) mapping operations which can be problematic in generating reports and / or analysis information for CCS operations.

[0005] Moreover, the screening processes referenced above can be plagued with: lack of current, real-time or near real-time data; human errors; inefficient and slow workflows and process stages; resource intensive computing operations or non-computing operations; and inaccuracies associated with uncertainty analysis for prospective sites under consideration for CCS operations.

[0006] There is therefore the need to address the aforementioned challenges associated with developing and implementing CCS operations.SUMMARY

[0007] Disclosed are methods, systems, and computer programs that determine an optimal location for fluid storage operations. According to an embodiment, a method for determining an optimal location for fluid storage operations comprises: determining first data for a first site, the first data comprising one or more of: sensor data indicating surface or subsurface conditions of a second site that is similar to or distinct from the first site, regulatory data associated with storing fluid at the first site, and infrastructure data associated with surface or subsurface infrastructure proximally located relative to the first site; generating a training dataset and a validation dataset based on the first data; generating a trained first machine learning (ML) model based on the training dataset and the validation dataset; generating, based on the trained first ML model, preliminary location data associated with two or more locations at the first site where fluid can be stored; receiving second data associated with the first site, the second data comprising one or more of: geological data indicating geological information associated with the two or more locations at the first site where fluid can be stored, and constraint data imposing boundary conditions or filter conditions on the geological data; generating a trained second ML model based on the second data; applying to the trained second ML model, the preliminary location data associated with the two or more locations at the first site where fluid can be stored and thereby generate parametric data for each of the two or more locations at the first site where fluid can be stored; determining, based on the parametric data, fluid storage optimality data for each of the two or more locations at the first site where fluid can be stored, the fluid storage optimality data comprising one or more of qualitative data or quantitative data that establish fluid storage efficiency information of at least a first location comprised in the two or more locations at the first site where fluid can be stored relative to a second location comprised in the two or more locations at the first site where fluid can be stored; classifying, based on the fluid storage optimality data, the two or more locations at the first site where fluid can be stored to indicate at least a ranking of the first location relative to the second location; generating, based on the classifying, a multi-dimensional visualization for: the first location, the multi-dimensional visualization indicating a first parameter set comprised in the parametric data, and the second location, the multi-dimensional visualization indicating a second parameter set comprised in the parametric data.

[0008] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0009] A first learning data structure associated with the first ML model includes a neural network data structure; and a second learning data structure associated with the first ML model includes a decision tree data structure, the second learning data structure being overlayed on the first learning data structure to generate the trained first ML model.

[0010] In one embodiment, the geological data comprises one or more of: rock property data including porosity data, permeability data, net-to-gross (NTG) data associated with subsurface structures of the second site that is similar to or distinct from the first site; relative permeability data associated with subsurface structures of the second site that is similar to or distinct from the first site; geological boundary condition data or facies data associated with subsurface structures of the second site that is similar to or distinct from the first site; injection rate data associated with subsurface structures of the second site that is similar to or distinct from the first site; injector number data associated with subsurface structures of the second site that is similar to or distinct from the first site; and producer number data associated with subsurface structures of the second site that is similar to or distinct from the first site.

[0011] Furthermore, the infrastructure data comprises data associated with one or more surface or subsurface structures including buildings, roads, and tunnels associated with the first site.

[0012] In one embodiment, the first parameter set or the second parameter set comprises one or more of: fluid storage capacity data associated with each of the two or more locations at the first site where fluid can be stored; fluid storage efficiency factor data associated with each of the two or more locations at the first site where fluid can be stored; fluid plume size data associated with each of the two or more locations at the first site where fluid can be stored; average fluid injection rate data associated with each of the two or more locations at the first site where fluid can be stored; storage site development cost data associated with each of the two or more locations at the first site where fluid can be stored; and carbon footprint rating data associated with each of the two or more locations at the first site where fluid can be stored.

[0013] In exemplary implementations, the fluid storage optimality data is generated or determined based on a combination of one or more parameters comprised in the parametric data for each of the two or more locations at the first site where fluid can be stored.

[0014] Moreover, the first site comprises a fluid storage site including one or more of: an aquifer, a saline aquifer, an oil reservoir, a depleted oil reservoir, a gas reservoir, or a depleted gas reservoir.

[0015] In some cases, the multi-dimensional visualization comprises a risk matrix quantitatively or qualitatively characterizing one or more of: an amount of stored fluid leakage that is allowable at the first site; an amount of stored fluid that is allowed to leak from a primary aquifer into a secondary aquifer at the first site; an amount of stored fluid that is allowed to leak into legacy wells at the first site; an amount of stored fluid that is allowed to leak from one well into a neighboring well at the first site; resolution data of one or more monitoring system associated with the first site; or risk profile data associated with the first site imposed by regulatory bodies.

[0016] In one embodiment, the fluid comprises one or more of: carbon dioxide gas, hydrogen gas, or methane gas.

[0017] Furthermore, the multi-dimensional visualization can indicate: a first shape that visually characterizes fluid storage at the first location; and a second shape that visually characterizes fluid storage at the second location.

[0018] It is appreciated that the first shape or the second shape comprises one of a polygonal shape or a polyhedral shape.BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The disclosure is illustrated by way of example, and not by way of limitation in the figures of the accompanying drawings in which like reference numerals are used to refer to similar elements. It is emphasized that various features may not be drawn to scale and the dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0020] FIG. 1 provides an exemplary high-level workflow for methods, systems, and computer programs that determine an optimal location for fluid storage operations at a CCS site.

[0021] FIG. 2 shows a cross-sectional view of a resource site for which the process of FIG. 1 may be executed.

[0022] FIG. 3 shows a network system illustrating a communicative coupling of devices or systems associated with the resource site of FIG. 2.

[0023] FIG. 4 provides an exemplary workflow for screening one or more CCS storage sites or resource sites.

[0024] FIG. 5 depicts an exemplary workflow for ranking or classifying a plurality of potential CCS locations.

[0025] FIGS. 6A and 6B provide exemplary detailed workflows for methods, systems, and computer programs that determine an optimal location for fluid storage operations.DETAILED DESCRIPTION

[0026] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the disclosure. However, it will be apparent to one of ordinary skill in the art that this disclosure may be practiced without these specific details. In other instances, some methods, procedures, components, circuits and networks have not been described in detail so as not to unnecessarily obscure aspects of the disclosed embodiments.

[0027] In some embodiments, the systems and methods disclosed may be accomplished using interconnected devices and systems that obtain a plurality of parameters of interest associated with a resource site. The workfl ows / flowcharts described in this disclosure, according to some embodiments, implicate a new processing approach (e.g., hardware, special purpose processors, and specially programmed general-purpose processors) because such analyses are too complex and cannot be mentally performed by a person in the time available or at all. Thus, the described systems and methods are directed to tangible computing implementations that solve specific technological problems in developing natural resources such as oil, gas, water well industries, and other mineral exploration operations. More specifically, the systems and methods disclosed may be applicable to operations associated with gas storage at a resource site (e.g., oil field, saline aquifers, etc.).

[0028] Attention is now directed to methods, techniques, infrastructure, and workflows for operations that may be carried out at a resource site. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined while the order of some operations may be changed. Some embodiments include an iterative refinement of one or more data or computing models associated with a resource site via feedback loops executed by one or more computing device processors and / or through other control devices / mechanisms that make determinations regarding whether a given action, template, model, resource data, etc., is sufficiently accurate.Overview

[0029] This disclosure provides methods, systems, and computer programs that enhance or otherwise optimize CCS operations including CCS screening operations. In particular, the disclosed methods and systems beneficially facilitate identifying suitable CCS sites with considerations including: gas / fluid storage capacity data; gas / fluid injectivity data; gas / fluid containment data; and social requirements data. Additionally, the disclosed approach beneficially ranks CCS sites to enable executing comparison computing operations between multiple CCS sites and thereby facilitate the selection of optimal or suitable CCS sites for gas storage with attendant uncertainty data.

[0030] According to one embodiment, the disclosed CCS screening operations for fluids (e.g., gases such as carbon dioxide, hydrogen gas, and methane gas) involve multiple screening stages. For example, the multiple screening stages include a first screening stage where a plurality of sites including reservoirs (e.g., depleted oil or gas reservoirs) are filtered dependently or independently or in conjunction with potential areal sites based on one or more minimum site selection criteria. The one or more minimum site selection criteria, according to one embodiment, comprise fundamental or basic criteria that indicate necessary requirements for CCS operations for a given CCS storage site. Furthermore, the plurality of sites and / or potential areal locations which filter through a first pass of the first screening stage are selected for a more detailed second screening stage. The potential sites and areal locations that are generated based on the first pass are filtered through several surface and subsurface site screening criteria to identify potential risks and benefits associated with each location during the second pass.

[0031] The forgoing screening processes may be executed, using machine learning (ML) models that accurately, quickly, and efficiently filter out CCS storage sites that do not meet CCS objectives and thereby enable identification of optimal CCS storage sites. In particular, the disclosed ML-based approach speeds-up CCS storage site selection processes by several orders of magnitude (e.g., over 10 times faster than human or sub-optimal filtering systems, or over 50 times faster than human or other sub-optimal filtering systems, or over a 100 times faster than human or sub-optimal filtering systems, or over 1000 times faster than human or other sub-optimal filtering systems, etc.).

[0032] According to one embodiment, a training dataset, for a first ML model, may be used to train or otherwise configure the first ML model to identify potential fluid storage sites. For example, the training dataset may be compiled using metadata from one or more resource sites under consideration for fluid (e.g., liquid and / or gas) storage. It is appreciated that during the training phase, the first ML model may be trained based on a first intelligent data learning structure (e.g., decision tree structure) associated with the first ML model such that the first intelligent data learning structure is overlayed with an underlying second intelligent learning data structure (e.g., a neural network structure) associated with the first ML model.

[0033] Once a potential fluid storage site (e.g., reservoirs and / or areal locations) are identified, said identified sites may be ranked against each other, for example, based on a second ML model, to determine data indicating an optimal set of initial sites. The ranking, categorizing, grouping, or sorting of sites may be achieved using, for example: qualitative and / or quantitative identifiers that are based on a weighted a relationship; and / or a weighted correlation; and / or a weighted combination of fluid capacity data associated with the site(s) under consideration; and / or fluid storage efficiency factor data associated with the site(s) under consideration; and / or fluid plume size data associated with the site(s) under consideration; and / or average fluid injection rate data associated with the site(s) under consideration; and / or storage site development cost data associated with the site(s) under consideration; and / or carbon footprint rating data associated with the site(s) under consideration.

[0034] The ML-based approach described herein enables performance of computations in a fraction of time relative to physics-based simulation systems. For example, the disclosed approach provides optimal CCS site detection at a rate of over 10 times faster than physics based simulation systems, or over 50 times faster than physics based simulation systems, orover a 100 times faster than physics based simulation systems, or over 1000 times faster than physics based simulation systems.High-Level Workflow

[0035] FIG. 1 provides an exemplary high-level workflow 100 for methods, systems, and computer programs that determine an optimal location for fluid storage operations at a CCS site.

[0036] At block 102, a signal processing engine may determine first data for the CCS site. The first data, for example, can include sensor information from a resource site, regulatory requirements from agencies that control or otherwise ensure that CCS compliance is met, and infrastructure associated with subsurface structures that are proximal and / or distal relative to CCS sites under consideration at the resource site.

[0037] At block 104, a trained first ML model is generated based on the first data. This can comprise customizing or parameterizing a first computing model (e.g., a first ML model) using the first data and thereby generate the trained first ML model.

[0038] At block 106, the signal processing engine may generate preliminary location data associated with the CCS site using the trained first ML model. In one embodiment, the preliminary location data associated with the CCS site is generated based on a first simulation using or involving the trained first ML model.

[0039] Turning to block 108, the signal processing engine may receive second data associated with the CCS site. In other embodiments, the second data comprises one or more of geological data associated with the resource site, and / or constraint or boundary condition data associated with the resource site.

[0040] At block 110, the signal processing engine may generate a trained second ML model based on, or in association with, the second data and / or the first data.

[0041] The signal processing engine may determine, at block 112, optimal locations at the CCS site where fluid can be stored based on at least the preliminary location data generated at block 106. According to one embodiment, determining the optimal locations at the CCS site where fluid can be stored comprises applying the preliminary location data associated with the CCS sit to, for example, parameterize and / or configure the trained second ML model and thereby generate the optimal locations at the CCS site where fluid can be stored. It isappreciated that the optimal locations, for example, may be determined based on a second simulation involving the trained second ML model such that the preliminary location data associated with the CCS site is ingested, analyzed, or otherwise processed further using the trained second ML model to generate data indicating the optimal locations.Resource Site

[0042] FIG. 2 shows a cross-sectional view of a resource site 200 for which the process of FIG. 1 may be executed. While the illustrated resource site 200 represents a subterranean formation, the resource site, according to some embodiments, may be below water bodies such as oceans, seas, lakes, ponds, wetlands, rivers, etc.

[0043] According to one embodiment, various measurement tools capable of sensing one or more parameters such as seismic two-way travel time, density, resistivity, production rate, etc., of a subterranean formation and / or geological formations may be provided at the resource site. As an example, wireline tools may be used to obtain measurement information related to geological attributes (e.g., geological attributes of a wellbore and / or reservoir) including geophysical and / or chemical information. For example, the chemical information may include chemical information associated with the subsurface and / or chemical information associated with the surface / above ground areas of the resource site 200.

[0044] In some embodiments, various sensors may be located at various locations around the resource site 200 to monitor and collect data for executing the process outlined in FIGS. 6A and 6B. In other embodiments, the techniques disclosed herein may be applied to surface seismic monitoring applications, surface gravity applications, surface electromagnetic applications, surface ground heave applications, and surface measurement of induced seismicity applications. According to some embodiments, the disclosed methods and systems may be applied to remote sensing applications (e.g., satellite-based measurements), subsea applications associated with permanent sensors, temporary sensor applications, remotely operated vehicles applications, and aerial-based measurement (e.g., performed from planes, helicopters, and / or drones) applications. The aerial-based measurements may include Synthetic Aperture Radar data measurements, atmospheric concentration data measurements associated with molecules such as CCh, CFL, and / or gas concentration data measurements associated with gases within the seabed.

[0045] Part, or all, of the resource site 200 may be on land, on water, or below water. In addition, while a resource site 200 is depicted, the disclosed methods and systems may be used with any combination of one or more resource sites (e.g., multiple oil fields or multiple wellsites, one or more saline aquifers, one or more depleted oil / gas fields, etc.), one or more processing facilities, etc.

[0046] Furthermore, the resource site 200 of FIG. 2 may have data acquisition tools 202a, 202b, 202c, and 202d positioned at various locations within the resource site 200. The subterranean structure 204 may have a plurality of geological formations 206a-206d. As shown, this structure may have several formations or layers, including a shale layer 206a, a carbonate layer 206b, a shale layer 206c, and a sand layer 206d. A fault 207 within the subterranean formation of the resource site 200 may extend through the shale layer 206a and the carbonate layer 206b. In addition, the data acquisition tools, for example, may be adapted to take measurements and detect geophysical and / or chemical characteristics of the various formations shown.

[0047] While a specific subterranean formation with specific geological structures is depicted, it is appreciated that the oil field 200 may contain a variety of geological structures and / or formations, sometimes having extreme complexity. In some locations of a given geological structure, for example below a water line (e.g., aquifer) relative to the given geological structure, fluid may occupy pore spaces of the formations. Each of the measurement devices may be used to measure properties of the formations and / or other geological features. While each data acquisition tool is shown as being in specific locations in FIG. 2, it is appreciated that one or more types of measurement may be taken at one or more locations across one or more sources of the resource site 200 or other locations for comparison and / or analysis. The data collected from various sources at the resource site 200 may be processed and / or evaluated and / or used as training data, and or used to generate high resolution result sets for characterizing a resource at the resource site, and / or used for generating resource models, etc. In one embodiment, the data collected by a set of sensors at the resource site may include data associated with the number of wells of a first reservoir or second reservoir at the resource site, data associated with the number of grid cells of the first or second reservoir, data associated with the average permeability of the first or second reservoir, data associated with theproduction duration history (e.g., number of years of production) of the first reservoir or second, etc.

[0048] Turning back to FIG. 2, data acquisition tool 202a is illustrated as a measurement truck, which may comprise devices or sensors that take measurements of the subsurface through sound vibrations such as, but not limited to, seismic measurements. Drilling tool 202b may include a downhole sensor adapted to perform logging while drilling (LWD) data collection. The wireline tool 202c may include a downhole sensor deployed in a wellbore or borehole. Production tool 202d may be deployed from a production unit or Christmas tree into a completed wellbore. Examples of parameters that may be measured include weight on bit, torque on bit, subterranean pressures (e.g., underground fluid pressure), temperatures, flow rates, compositions, rotary speed, particle count, voltages, currents, and / or other parameters of operations as further discussed below.

[0049] In some cases, sensors may be positioned about the resource site to collect data relating to various resource site operations, such as sensors deployed by the data acquisition tools 202. The sensors may include any type of sensor such as a metrology sensor (e.g., temperature, humidity), an automation enabling sensor, an operational sensor (e.g., pressure sensor, H2S sensor, thermometer, depth, tension), evaluation sensors, that can be used for acquiring data regarding a subsurface formation, wellbore, formation fluid / gas, wellbore fluid, gas / oil / water comprised in the formation / wellbore fluid, or any other suitable sensor. For example, the sensors may include accelerometers, flow rate sensors, pressure transducers, electromagnetic sensors, acoustic sensors, temperature sensors, chemical agent detection sensors, nuclear sensors, and / or any additional suitable sensors.

[0050] In one embodiment, the data captured by the one or sensors may be used to characterize, or otherwise generate one or more parameter values for a high resolution result set used to, for example, label or configure a machine learning (ML) engine or a resource model as the case may require. In other embodiments, test data or synthetic data may also be used in developing the ML engine or the resource model via one or more parameterization / labeling operations such as those discussed in association with the workflows presented herein.

[0051] Evaluation sensors may be featured in downhole tools such as tools 202b-202d and may include for instance electromagnetic sensors, acoustic sensors, nuclear sensors, and optic sensors. Examples of tools including evaluation sensors that can be used in the frameworkof the current method include electromagnetic tools such as imaging sensors. In one embodiment, the imaging sensors comprise one or more of: FMI™ or QuantaGeo™ (mark of SLB, Houston, TX) sensors; induction sensors including Rt Scanner™ (mark of SLB, Houston, TX) sensors; multifrequency dielectric dispersion sensors including Dielectric Scanner™ (mark of SLB, Houston, TX) sensors; acoustic tools including sonic sensors such as Sonic Scanner™ (mark of SLB, Houston, TX); ultrasonic sensors including pulse-echo sensors as in UBI™ or PowerEcho™ (marks of SLB, Houston, TX) or flexural sensors or PowerFlex™ (mark of SLB, Houston, TX) sensors; nuclear sensors such as Litho Scanner™ (mark of SLB, Houston, TX) sensors or nuclear magnetic resonance sensors; fluid sampling tools including fluid analysis sensors such as InSitu Fluid Analyzer™ (mark of SLB, Houston, TX) sensors; and distributed sensors including fiber optic sensors. According to one embodiment, the disclosed evaluation sensors are used for: evaluating or determining formation data associated with a well at the resource site (i.e., determining petrophysical or geological properties of the formation); verifying or determining integrity data (e.g., integrity data such as casing data or cement properties data)for the well; and / or analyzing or determining fluid data associated with produced fluid (e.g., hydrocarbons) at the resource site. It is appreciated that the fluid data can comprise flowrate data, and fluid type data (e.g., whether the fluid is liquid or gaseous or a combination thereof).

[0052] As shown, data acquisition tools 202a-202d may generate data plots or measurements 208a-208d, respectively. These data plots are depicted within the resource site 200 to demonstrate or indicate data generated by some of the operations executed at the resource site 200. Data plots 208a-208c are examples of static data plots that may be generated by data acquisition tools 202a-202c, respectively. However, it is herein contemplated that data plots 208a-208c may also be data plots generated and updated in real time. These measurements may be analyzed to better define properties of the formation(s) and / or determine the accuracy of the measurements and / or check for and compensate for measurement errors. The plots of each of the respective measurements may be aligned and / or scaled for comparison and verification purposes. In some embodiments, base data associated with the plots may be incorporated into site planning, modeling a test at the resource site 200. The respective measurements that can be taken may be any of the above.

[0053] Other data may also be collected, such as historical data of the resource site 200 and / or sites similar to the resource site 200, user inputs, information (e.g., economic information) associated with the resource site 200 and / or sites similar to the resource site 200, and / or other measurement data and other parameters of interest. Similar measurements may also be used to measure changes in formation aspects over time.

[0054] In one embodiment, computer facilities such as those discussed in association with FIG. 3 may be positioned at various locations about the resource site 200 e.g., a surface unit) and / or at remote locations. A surface unit (e.g., one or more terminals 320) may be used to communicate with the onsite tools and / or offsite operations, as well as with other surface or subsurface / downhole sensors. The surface unit may be capable of sending commands to the resource site (e.g., oil / gas field) equipment / sy stems, and / or receiving data therefrom. In some cases, the surface unit may also collect data generated during production operations and can produce output data, which may be stored or transmitted for further processing at the resource site or to an offsite location relative to the resource site.

[0055] It is appreciated that the data collected by sensors associated with the resource site may be used alone or in combination with other data for energy development operations (e.g., computing operations or otherwise). It is further appreciated that the data aggregated using the sensors may be collected in one or more databases and / or transmitted to one or more computing systems at the resource site or to the offsite location. In one embodiment, the data associated with the sensors may be historical data, real-time data, or combinations thereof. The real-time data may be used in real-time or stored for later use. The data may also be combined with historical data or other inputs for further analysis or for modeling purposes to optimize production processes at the resource site 200. In one embodiment, the data is stored in separate databases, or combined into a single database.High-Level Network System

[0056] FIG. 3 shows a high-level networked system 300 illustrating a communicative coupling of devices or systems associated with the resource site 200 of FIG. 2. The system 300 shown in the figure may include a set of processors 302a, 302b, and 302c for executing one or more processes discussed herein. The set of processors 302 may be electrically coupled to one or more servers (e.g., computing systems) including memory 306a, 306b, and 306c thatmay store for example, program data, databases, and other forms of data. Each server of the one or more servers may also include one or more communication devices 308a, 308b, and 308c. The set of servers may provide a cloud-computing platform 310. In one embodiment, the set of servers includes different computing devices that are situated in different locations and may be scalable based on the needs and workflows associated with the oil field 200. The communication devices of each server may enable the servers to communicate with each other through a local or global network such as an Internet network. In some embodiments, the servers may be arranged as a town 312, which may provide a private or local cloud service for users. A town may be advantageous in remote locations with poor connectivity. Additionally, a town may be beneficial in scenarios with large networks where security may be of concern. A town in such large network embodiments can facilitate implementation of a private network within such large networks. The town may interface with other towns or a larger cloud network, which may also communicate over public communication links. Note that cloud-computing platform 310 may include a private network and / or portions of public networks. In some cases, a cloud-computing platform 310 may include remote storage and / or other application processing capabilities.

[0057] In some embodiments, the system 300 of FIG. 3 may also include one or more user terminals 314a and 314b each including at least a processor to execute programs, a memory (e.g., 316a and 316b) for storing data, a communication device and one or more user interfaces and devices that enable a user to receive, view, and transmit information. In one embodiment, the user terminals 314a and 314b is a computing system having interfaces and devices including keyboards, touchscreens, display screens, speakers, microphones, a mouse, styluses, etc. Furthermore, the user terminals 314 may be communicatively coupled to the one or more servers of the cloud-computing platform 310. In particular, the user terminals 314 may be client terminals or expert terminals, enabling collaboration between clients and experts through the system 300 of FIG. 3.

[0058] The system 300 of FIG. 3 may also include computing systems associated with at least one or more resource sites 200, such that the computing systems may have, for example, a set of terminals 320, each including at least a processor, a memory, and a communication device for communicating with other devices communicatively coupled to the cloud-computing platform 310. In addition, the at least one or more resource sites 200 may have associated setsof sensors (e g., one or more sensors described in association with FIG. 2) or sensor interfaces 322a and 322b communicatively coupled to the set of terminals 320 and / or directly coupled to the cloud-computing platform 310. In some embodiments, data collected by the sets of sensors / sensor interfaces 322a and 322b may be processed to generate one or more resource models (e.g., reservoir models) or one or more resolved data sets used to generate the one or more resource models which may be displayed on a user interface associated with the set of terminals 320, and / or displayed on user interfaces associated with the set of servers of the cloud computing platform 310, and / or displayed on user interfaces of the user terminals 314. Furthermore, various equipment / devices discussed in association with the resource site 200 may also be communicatively coupled to the set of terminals 320 and or communicatively coupled directly to the cloud-computing platform 310. The equipment and sensors may also include one or more communication device(s) that may communicate with the set of terminals 320 to receive orders / instructions locally and / or remotely from the resource site 200 and also send statuses / updates to other terminals such as the user terminals 314.

[0059] The system 300 of FIG. 3 may also include one or more client servers 324 including a processor, memory and communication device. For communication purposes, the client servers 324 may be communicatively coupled to the cloud-computing platform 310, and / or to the user terminals 314a and 314b, and / or to the set of terminals 320 at the resource site 200 and / or to sensors at the oil field, and / or to other equipment at the resource site 200.

[0060] A processor, as discussed with reference to the system 300 of FIG. 3, may include a microprocessor, a graphical processing unit (GPU), a microcontroller, a processor module or subsystem, a programmable integrated circuit, a programmable gate array, or another control or computing device.

[0061] The memory / storage media discussed above in association with FIG. 3 can be implemented as one or more computer-readable or machine-readable storage media that are non-transitory. In some embodiments, storage media may be distributed within and / or across multiple internal and / or external enclosures of a computing system and / or additional computing systems. Storage media may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories; magnetic disks suchas fixed, floppy and removable disks; other magnetic media including tape; optical media such as compact disks (CDs) or digital video disks (DVDs), BluRays or any other type of optical media; or other types of storage devices. “Non-transitory” computer readable medium refers to the medium itself (i.e., tangible, not a signal) and not data storage persistency (e.g., RAM vs. ROM).

[0062] Note that instructions can be provided on one or more computer-readable or machine-readable storage media, or alternatively, can be provided on multiple computer- readable or machine-readable storage media distributed in a large system having possibly plural nodes and / or non-transitory storage means. Such computer-readable or machine-readable storage medium or media is (are) considered to be part of an article (or article of manufacture). The storage medium or media can be located either in a computer system running the machine- readable instructions, or located at a remote site from which machine-readable instructions can be downloaded over a network for execution.

[0063] It is appreciated that the described system 300 of FIG. 3 is an example that may have more or fewer components than shown; may combine additional components; and / or may have a different configuration or arrangement of the components than those shown in FIG. 3. The various components shown may be implemented in hardware, software, or a combination of both, hardware and software, including one or more signal processing engine and / or application specific integrated circuits.

[0064] Further, the steps in the flowcharts described below may be implemented by running one or more functional modules in an information processing apparatus such as general-purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, GPUs or other appropriate devices associated with the system 300 of FIG. 3. For example, the flowchart of FIG. 1 as well as the flowcharts below may be executed using a signal processing engine or a data processing module (e.g., computing module) stored in memory 306a, 306b, or 306c such that the signal processing engine or the data processing module includes instructions that are executed by the one or more processors such as processors 302a, 302b, or 302c as the case may require. The various modules of the system 300 of FIG. 3, combinations of these modules, and / or their combination with general hardware are included within the scope of protection of the disclosure. While one or more computing processors (e.g., processors 302a, 302b, or 302c) may be described as executing steps associated with one or more of theflowcharts described in this disclosure, the one or more computing device processors may be associated with the cloud-based computing platform 310 and may be located at one location or distributed across multiple locations. In one embodiment, the one or more computing device processors may also be associated with other systems of FIG. 3 other than the cloud-computing platform 310.

[0065] In some embodiments, a computing system associated with the system 300 is provided that includes at least one processor, at least one memory, and one or more programs stored in the at least one memory, such that the programs comprise instructions, which when executed by the at least one processor, are configured to perform any method disclosed herein.

[0066] In some embodiments, a computer readable storage medium associated with the system 300 is provided, which has stored therein one or more programs, the one or more programs including instructions, which when executed by a processor, cause the processor to perform any method disclosed herein. In some embodiments, a computing system is provided that includes at least one processor, at least one memory, and one or more programs stored in the at least one memory for performing any method disclosed herein. In some embodiments, an information processing apparatus for use in a computing system is provided for performing any method disclosed herein.Embodiments

[0067] According to one embodiment, the disclosed methods and systems have the following attendant workflows:First Workflow: Site Screening Workflow

[0068] FIG. 4 provides an exemplary workflow 400 for screening one or more CCS storage sites according to some embodiments. In particular, a first ML model (e.g., an intelligent CCS computing model) may be used to implement the operations outlined in FIG. 4. For example, the various criteria discussed in association with FIG. 4 may comprise parameter configurations for a first set of parameters of the first ML model.

[0069] In this first workflow, a plurality of potential CCS storage sites (e.g., depleted or non-depleted reservoirs at a resource site) and potential areal zones are filtered based on a minimum site selection criteria. The minimum site selection criteria, according to oneembodiment, comprises: basic or fundamental fluid storage conditions and / or fluid storage requirements data associated with storing fluid at the plurality of potential CCS storage sites and / or potential areal zones, for example, at a resource site under consideration; and / or bounded constraints data associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and / or regulatory or CCS risk requirements data that the plurality of CCS storage sites and / or potential areal zones must satisfy. In one embodiment, the minimum site selection criteria include: preliminary assessment data and / or fluid storage capacity data 402a associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and / or fluid containment data 402b together with environmental safety data 402c associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and legal and / or regulatory restrictions data 402d that constrain the CCS storage project under consideration to one or more of the plurality of potential CCS storage sites and / or potential areal zones.

[0070] Moreover, the sites and areal locations under consideration and which filter through the first screening or filtering operation may be selected for a more detailed second screening operation. In particular, the potential sites and areal locations that are generated based on the first screening operation may be filtered or otherwise subjected to a selection or secondary screening operation based on several surface screening criteria data 406a and subsurface screening criteria data 406b to determine or otherwise identify potential risks data and / or benefits data associated with each location. Some of the surface screening criteria data 406a and / or subsurface screening criteria data 406b with their attendant data derivative data infrastructure data 404a, protected areas data 404b, additional surface screening criteria data 404c, structural depth data 404d, seal thickness data 404e, reservoir quality data 404f, additional subsurface data 404g are outlined in FIG. 4.

[0071] According to one embodiment, data from one or more of the following sources may be used to train, configure, or otherwise initialize the first ML model described in FIG. 4 using one or more of: the surface screening criteria data 406a or sources from which said surface screening criteria data 406a are derived; subsurface screening criteria data 406b or sources from which said subsurface screening criteria data 406b are derived; and legal and / or regulatory restrictions data 402d or data derived from regulatory requirements data sources. It is appreciated that one or more of the surface criteria data sources, the subsurface criteria datasources, and regulatory requirements data sources may be comprised in a database or a data server. In one embodiment, the database includes custom requirement data designated as such to comply with specific goals or objectives associated with a CCS storage project. In other embodiments, the data from the data sources may be derived from historical CCS site data that are similar to, or distinct from, a CCS sites under consideration. In one embodiment, the surface criteria data sources and / or subsurface criteria data sources may rely on sensor measurements that capture surface and / or subsurface conditions associated with the CCS site(s) under consideration. In exemplary implementations, the data (e.g., preliminary assessment data and / or fluid storage capacity data 402a associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and / or fluid containment data 402b together with environmental safety data 402c associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and legal and / or regulatory restrictions data 402d; and / or surface screening criteria data 406a and / or subsurface screening criteria data 406b) from the data sources including metadata associated with the CCS sites under considerations may be formatted into a data matrix prior to the first ML model being applied to said data.

[0072] According to one embodiment, the first ML model is trained after the relevant data (e.g., preliminary assessment data and / or fluid storage capacity data 402a associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and / or fluid containment data 402b together with environmental safety data 402c associated with storing fluid at one or more of the plurality of potential CCS storage sites and / or potential areal zones; and legal and / or regulatory restrictions data 402d; and / or surface screening criteria data 406a and / or subsurface screening criteria data 406b) is received or extracted from one or more databases associated with the CCS storage project. It is appreciated that once the data within the one or more databases are compiled, the data within the database may be randomly split into a training dataset and a validation dataset using a randomized approach. The training dataset may then be used to train 403a the first ML model given one or more of the criteria discussed above in association with the filtering operations. In one embodiment, the criteria may include new or updated criteria or inputs that stipulate conditions or requirements for the CCS storage operation. In other embodiments, the criteria may be based on static or dynamic geological models associated with the CCS site under consideration. Thestatic or dynamic models may include subsurface models indicating geological structures of the subsurface which is being considered for CCS storage operations. In some cases, the static or dynamic models include surface or above-surface models indicating aerial models or aboveground models, or surface environment models associated with the CCS site under consideration.

[0073] As previously noted, training of the first ML model may include overlying a first intelligent learning data structure (e.g., a decision tree learning structure) over an underlying second intelligent learning data structure (e.g., a neural network learning structure) to form an integration, an aggregation, or a combination of two intelligent learning data models (e.g., decision tree learning model and a neural network learning model). The two intelligent learning data models (e.g., trained first ML model), according to one embodiment, may work together in tandem to filter, analyze, and / or otherwise process inputs or received data and thereby select or filter appropriate CCS sites under consideration for fluid storage.

[0074] Once the first ML model is trained, a labeled dataset may be used to validate 403b the trained first ML model. In some cases, this involves validating the trained first ML model using the labeled dataset such that the labeled dataset comprises new surface or subsurface data which the first ML model has not seen before or which the first ML model has not yet encountered from a data perspective. For example, the trained first ML model may be subjected to, or used to operate on a dataset that is distinct from the training dataset to confirm that the first ML model is operating as intended and thereby generate a validated first ML model. According to one embodiment, the distinct dataset may have already established outputs or constraints which confirm, inform, or otherwise validate the trained first ML model and thereby generate the validated first ML model that ensures that the parameters of the trained first ML model are accurately or correctly configured. If the trained first ML model (e.g., the validated first ML model) correctly predicts the potential CCS sites under consideration based on the distinct data and / or the training data, then said trained first ML model is deemed ready for predicting CCS storage sites. If the first ML model fails to predict the potential CCS sites under consideration, then it is looped back for another training cycle.

[0075] According to one embodiment, data inputs such as those discussed herein may be formatted into a multi-dimensional matrix which the ML model or the trained ML model (e.g., validated first ML model) can operate on.

[0076] After training and validating the first ML model to generated the validated first ML model, the validated first ML model may receive or otherwise ingest CCS data 408a and / or 408b associated with a CCS site under consideration. The CCS data 408a and / or 408b, according to one embodiment, comprises data that is similar to or distinct from the training data and / or validation data. Furthermore, the CCS data 408a and / or 408b may be similarly stored in the database associated with the CCS site under consideration. In addition, the CCS data may include surface and / or subsurface data or criteria data associated with the CCS site under consideration. For example, the subsurface data may include data associated with subsurface or geological structures such as reservoirs (e.g., depleted or non-depleted reservoirs) while the surface data may include areal data including climate data and / or structural data associated with surface structures (e.g., buildings, roadways, or other infrastructure on the surface). Furthermore, the validated ML model may receive CCS data such that the validated ML model predicts 403c a plurality of CCS locations 410 (e.g., a plurality of preliminary screened CCS storage sites) for a given CCS site under consideration at a resource site. The plurality of CCS locations 410 may be ranked or otherwise prioritized based on storage efficiencies or storage optimality of individual CCS storage locations comprised in the plurality of CCS locations 410. The number of features can be kept flexible, such that a confidence ranking value may be provided to indirectly or directly relate the number of site features provided as input to the size of the training and validation datasets.

[0077] According to one embodiment, the output (e.g., CCS location data) or the CCS locations 410 generated by the trained first ML model may be automatically rendered as multidimensional visualizations indicating various shapes (e.g., polygons and / or polyhedrons) visually characterizing each of the plurality of storage locations at the resource site. In one embodiment, the multi-dimensional visualizations further include: storage volume data associated with storing fluid within one or more of the plurality of the CCS locations 410; and / or storage risk data associated with storing fluid within one or more of the plurality of CCS locations 410; and / or storage efficiency data for the plurality of CCS locations 410. The predictions may also include targeted subsurface structures such as specific reservoirs associated with the CCS site under consideration.

[0078] It is appreciated that the first workflow may be used to generate data outputs (e.g., CCS locations 410 or preliminary CCS locations at a resource site) based on the firsttrained ML model. For example, the data outputs can comprise data indicating a set of preliminary screened CCS storage sites or CCS locations associated with a CCS site under consideration. These aspects are discussed in association with FIG. 4.Second Workflow: CCS Location Ranking Workflow

[0079] Once the plurality of CCS locations 410 (e.g., reservoirs and areal locations) are determined, the plurality of CCS locations 410 are ranked against each other to identify optimal CCS locations. The overall workflow to achieve this is shown in FIG. 5Error! Reference source not found.. The ranking of the plurality of CCS locations may be done based on one or more of the following parameters (e.g., location parameters):• fluid storage capacity data associated with the plurality of CCS locations;• fluid storage efficiency factor data associated with the plurality of CCS locations;• fluid plume size data associated with the plurality of CCS locations;• average fluid injection rate data associated with the plurality of CCS locations;• storage site development cost data associated with the plurality of CCS locations; and• carbon footprint rating data associated with the plurality of CCS locations.In some embodiments, the ranking or classifying may be based on a weighted combination of one or more of the above parameters. To do this, a second ML model that is different from the first ML model is trained using one or more configuration data selected from:• model data 502a (e.g., a static geological model data) associated with one or more CCS sites under consideration;• rock property data 502b (e.g., porosity data, permeability data, etc.) associated with the one or more CCS sites under consideration;• relative permeability data 502c associated with the one or more CCS sites under consideration;• boundary condition data 502d associated with the one or more CCS sites under consideration;• injection rate 502e and / or production rate data associated with the one or more CCS sites under consideration; and / or• injector well number data 502f and / or producer well number data associated with the one or more CCS sites under considerations.

[0080] It is appreciated that two or more of the configuration data may be combined and / or otherwise leveraged or used to create 503a a plurality of scenarios or implementation cases 504a. . .504d that may be further refined 503b and / or used in additional quantitative and / or qualitative computations 503c prior to, and / or during, and / or after training 505a and / or validating 505b the second ML model to generate a validated second ML model.

[0081] Once the second ML model is trained to generate the validated second ML model, the output data (e.g., the plurality of CCS locations 410) generated from the workflow of FIG. 4 or data indicating a set of preliminary screened CCS storage sites or CCS locations associated with a CCS site under consideration may be ingested or otherwise applied to the second ML model. The second ML model then computes or generates 505c data values for the location parameters used for classifying and / or ranking the one or more CCS locations comprised in the CCS locations (e.g., the plurality of CCS locations 410) associated with the CCS site under consideration. The CCS locations associated with the CCS site under consideration may then be ranked based on the computed or generated data values.

[0082] The ML-based approach described herein can enable the performance of the aforementioned workflows in a fraction of time as compared to some existing physics-based simulation approaches.

[0083] In one embodiment, the second ML model of FIG. 5 can be trained by creating a training dataset and validation dataset. For example, the training dataset and the validation dataset can be created using numerical reservoir simulations. In such cases, a large number of subsurface scenarios (e.g., a plurality of scenarios or implementation cases 504a. , .504d) can be simulated that cover a plurality of subsurface uncertainty data or scenario data, including: rock properties (e.g., porosity, permeability, NTG, thickness, depth of reservoir, etc.); relative permeability data; boundary condition data; injection rate data; number of injectors data; number of producers data, etc. In some embodiments, the subsurface uncertainty data or scenario data may be derived from one or more of: user inputs; pre-configured model templates; custom profile data for the second ML model that are automatically deployed to train the second ML model; etc. Furthermore, the subsurface uncertainty data or scenario data may be associated with the CCS site under consideration and may be formatted into a data matrix to indicate a plurality of cases or model configurations prior to being applied to the second ML model during the training phase of the second ML model.

[0084] As part of training the second ML model, once the database is compiled, training and validation datasets can be determined. For example, the training and validation datasets can be identified from the database based on a randomized approach. The training dataset can be used to train the second ML model to rank the potential fluid storage sites, based on one or more data inputs, such that the data inputs comprise the final output (e.g., the plurality of CCS locations 410) of the site screening workflow described above in FIG. 4. In some cases, a neural network-based approach can be used to train the second ML model. Once the second ML model is trained, the second ML model can be validated using a labeled dataset. Furthermore, the validation process of the second ML model can include executing the second ML model to correctly compute capacity data 508a (e.g., fluid capacity data), and / or efficiency factor data 508b (e.g., fluid efficiency factor data), and / or plume size data 508c (e.g., fluid plume size data), and / or average injection rate data 508d, and / or cost of development data 508e, and / or carbon footprint rating data 508f for CCS sites for which the same values have been calculated using physics-based approaches. If the second ML model can correctly predict the various parameters, then it is deemed ready for predictions. If the second ML model fails to predict the parameters correctly, it is looped back for another training cycle.

[0085] Upon validation, the second ML model discussed in association with FIG. 5 can be implemented to identify an optimal CCS site by raking the potential fluid (e.g., CCh, CFL, and / or some other fluid- hydrocarbon or otherwise) storage sites predicted from the site screening workflow described in FIG. 4. For example, inputs to the second ML model can include site features that are used in the site screening workflow of FIG. 4. From these inputs, the second ML model can estimate capacity data, efficiency factor data, plume size data, average injection rate data, cost of development data and carbon footprint rating data for each of the potential storage sites determined using the workflow of FIG. 4. Furthermore, a site ranking value can also be provided to rank or otherwise categorize the potential storage sites generated using the workflow of FIG. 4 against each other.Consolidated Workflow: Methods and Systems For Determining Optimal Fluid Storage Locations

[0086] FIGS. 6A and 6B provide exemplary detailed workflows 600a and 600b for methods, systems, and computer programs that determine an optimal location for fluid storageoperations. It is appreciated that a data managing module (e.g., a data manager or data engine or a signal processing engine) stored in a memory device may cause a computer processor to execute the various processing stages of the workflows discussed in association with FIGS. 4, 5, 6A and 6B. For example, the disclosed techniques may be implemented as a data manager or signal processing engine within a geological software tool such that the data manager or signal processing engine enables modeling or determining optimal location for fluid storage operations at a resource site.

[0087] At block 602, the signal processing engine may determine first data for a first site. The first data can comprise one or more of: sensor data indicating surface or subsurface conditions of a second site that is similar to or distinct from the first site; regulatory data associated with storing fluid at the first site; and infrastructure data associated with surface or subsurface infrastructure proximally located relative to the first site. It is appreciated that the first site and / or the second site can comprise the same resource site. In other embodiments, the first site and the second site comprise distinct resource sites relative to each other. Furthermore, the first site or the second site may comprise a site designated for carbon capture and storage (CCS) operations and / or associated with CCS operations.

[0088] At block 604, the signal processing engine may generate a training dataset and a validation dataset based on the first data. In one embodiment, the training dataset and the validation dataset may be generated from randomly splitting initially aggregated data (e.g., the first data) associated with the first site.

[0089] At block 606, the signal processing engine may further generate a trained first machine learning (ML) model based on the training dataset and the validation dataset.

[0090] In addition, the signal processing engine may generate, based on the trained first ML model, preliminary location data associated with two or more locations at the first site where fluid can be stored at block 608.

[0091] In one embodiment, the signal processing engine may receive, at block 610, second data associated with the first site. The second data may comprise one or more: geological data indicating geological information associated with the two or more locations at the first site where fluid can be stored; and constraint data imposing boundary or filter conditions on the geological data;

[0092] At block 612, the signal processing engine may also generate a trained second ML model based on the second. In particular, the second trained ML model may be based on or associated with the received second data.

[0093] The signal processing engine may also apply to the trained second ML model, at block 614, the preliminary location data associated with the two or more locations at the first site where fluid can be stored to generate parametric data for each of the two or more locations at the first site where fluid can be stored.

[0094] At block 616, the signal processing may determine, based on the parametric data, fluid storage optimality data for each of the two or more locations at the first site where fluid can be stored. The fluid storage optimality data comprises, according to one embodiment, one or more of qualitative data or quantitative data that establish fluid storage efficiency information of at least a first location comprised in the two or more locations at the first site where fluid can be stored relative to a second location comprised in the two or more locations at the first site where fluid can be stored.

[0095] Turning to block 618, the signal processing engine may classify, based on the fluid storage optimality data, the two or more locations at the first site where fluid can be stored to indicate at least a ranking of the first location relative to the second location.

[0096] At block 620, the signal processing engine may generate, based on the classifying, a multi-dimensional visualization for: the first location, the multi-dimensional visualization indicating a first parameter set comprised in the parametric data; and the second location, the multi-dimensional visualization indicating a second parameter set comprised in the parametric data.

[0097] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0098] A first learning data structure associated with the first ML model includes a neural network data structure; and a second learning data structure associated with the first ML model includes a decision tree data structure, the second learning data structure being overlayed on the first learning data structure to generate the trained first ML model.

[0099] In one embodiment, the geological data comprises one or more of: rock property data including porosity data, permeability data, net-to-gross (NTG) data associated withsubsurface structures of the second site that is similar to or distinct from the first site; relative permeability data associated with subsurface structures of the second site that is similar to or distinct from the first site; geological boundary condition data or facies data associated with subsurface structures of the second site that is similar to or distinct from the first site; injection rate data associated with subsurface structures of the second site that is similar to or distinct from the first site; injector number data associated with subsurface structures of the second site that is similar to or distinct from the first site; and producer number data associated with subsurface structures of the second site that is similar to or distinct from the first site.

[0100] Furthermore, the infrastructure data comprises data associated with one or more surface or subsurface structures including buildings, roads, and tunnels associated with the first site.

[0101] In one embodiment, the first parameter set or the second parameter set comprises one or more of: fluid storage capacity data associated with each of the two or more locations at the first site where fluid can be stored; fluid storage efficiency factor data associated with each of the two or more locations at the first site where fluid can be stored; fluid plume size data associated with each of the two or more locations at the first site where fluid can be stored; average fluid injection rate data associated with each of the two or more locations at the first site where fluid can be stored; storage site development cost data associated with each of the two or more locations at the first site where fluid can be stored; and carbon footprint rating data associated with each of the two or more locations at the first site where fluid can be stored.

[0102] In exemplary implementations, the fluid storage optimality data is generated or determined based on a combination of one or more parameters comprised in the parametric data for each of the two or more locations at the first site where fluid can be stored.

[0103] Moreover, the first site comprises a fluid storage site including one or more of: an aquifer, a saline aquifer, an oil reservoir, a depleted oil reservoir, a gas reservoir, or a depleted gas reservoir.

[0104] In some cases, the multi-dimensional visualization comprises a risk matrix indicating risk data for implementing fluid storage for each of the two or more locations at the first site where fluid can be stored. The risk matrix, for example, quantitatively or qualitatively characterizes one or more of: an amount of stored fluid leakage that is allowable at the first site; an amount of stored fluid that is allowed to leak from a primary aquifer into a secondary aquiferat the first site; an amount of stored fluid that is allowed to leak into legacy wells at the first site; an amount of stored fluid that is allowed to leak from one well into a neighboring well at the first site; resolution data of one or more monitoring system associated with the first site; or risk profile data associated with the first site imposed by regulatory bodies.

[0105] In one embodiment, the fluid comprises one or more of: carbon dioxide gas, hydrogen gas, or methane gas.

[0106] Furthermore, the multi-dimensional visualization can indicate: a first shape that visually characterizes fluid storage at the first location; and a second shape that visually characterizes fluid storage at the second location.

[0107] It is appreciated that the first shape or the second shape comprises one of a polygonal shape or a polyhedral shape.

[0108] The disclosed approach beneficially provides:• accelerated and automated screening of potential fluid storage sites for CCS storage operations;• fully automated and robust determination of important fluid storage parameters including fluid storage capacity, fluid storage efficiency factor, etc.• storage location ranking for a plurality of fluid storage locations associated with one or more CCS sites.

[0109] Furthermore, the disclosed methods and systems enable intelligent identification of suitable CCS sites using one or more ML models. The CCS site screening operations may be based on different surface and subsurface criteria or parameters, which include reservoir property data, geomechanical property data, seismic activity data, population density data, data associated with sensitive areas proximal to the CCS site under consideration, etc. The disclosed methods and systems can further leverage surface data such as map data for surface criteria including road network data, rail line data, building or other infrastructural data for the operations disclosed. Furthermore, the generated reports, files, and multi-dimensional images associated with a CCS project can include a risk matrix information indicating risk data for implementing fluid storage for a plurality of fluid storage locations associated with a CCS site.

[0110] In some implementations, the gas storage determinations disclosed are associated with storing gas including at least one of: carbon dioxide gas, hydrogen gas, and methane gas. Furthermore, a phase (e.g., fluid states including liquid and gaseous states) of thestored gas may be based on one or more of: a depth within a subsurface (e.g., a gas storage complex or a predicted fluid storage location) of a resource site within which fluid can be stored, and / or pressure within the subsurface of the resource / CCS site within which the fluid is stored.

[0111] The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limited the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to explain the principles and practical applications, to thereby enable others skilled in the art to use the various embodiments described herein with various modifications as are suited to the particular use contemplated. It is appreciated that the term optimize / optimal and its variants (e.g., efficient or optimally) may simply indicate improving, rather than the ultimate form of 'perfection' or the like.

[0112] It will also be understood that, although the terms first, second, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a first object or step, without departing from the scope. The first object or step, and the second object or step, are both objects or steps, respectively, but they are not to be considered the same object or step.

[0113] The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in the description herein and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any possible combination of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0114] As used herein, the term “if’ may be construed to mean “when” or “upon” or“in response to determining” or “in response to detecting,” depending on the context.

[0115] Those with skill in the art will appreciate that while some terms in this disclosure may refer to absolutes, e.g, all source receiver traces, each of a plurality of objects, etc., the methods and techniques disclosed herein may also be performed on fewer than all of a given thing, e.g. , performed on one or more components and / or performed on one or more source receiver traces. Accordingly, in instances in the disclosure where an absolute is used, the disclosure may also be interpreted to be referring to a subset.

Claims

CLAIMSWhat is claimed is:

1. A method for determining an optimal location for fluid storage operations, the method comprising: receiving first data for a first site; determining a training dataset and a validation dataset based on the first data; generating a trained first ML model based on the training dataset and the validation dataset; determining, based on the trained first model, preliminary location data associated with two or more locations at the first site where fluid can be stored; receiving second data associated with the first site, the second data being configured to train a second ML model; applying to the trained second ML model, the preliminary location data associated with the two or more locations at the first site where fluid can be stored to generate parametric data; determining, based on the parametric data, fluid storage optimality data for the two or more locations at the first site where fluid can be stored; classifying, based on the fluid storage optimality data, the two or more locations at the first site where fluid can be stored to indicate at least a ranking of a first location comprised in the two or more locations relative to a second location comprised in the two or more locations; generating, based on the classifying, a multi-dimensional visualization for: the first location, the multi-dimensional visualization indicating a first parameter set comprised in the parametric data, and the second location, the multi-dimensional visualization indicating a second parameter set comprised in the parametric data.

2. The method of Claim 1, wherein: the first data comprises one or more of: sensor data indicating surface or subsurface conditions of a second site that is similar to or distinct from the first site,regulatory data associated with storing fluid at the first site, and infrastructure data associated with surface or subsurface infrastructure proximally located relative to the first site.

3. The method of Claim 2, wherein the infrastructure data comprises data associated with one or more surface or subsurface structures including buildings, roads, and tunnels associated with the first site.

4. The method of Claim 1, wherein the second data comprises: geological data indicating geological information associated with the two or more locations at the first site where fluid can be stored; and constraint data imposing boundary or filter conditions on the geological data.

5. The method of Claim 4, wherein the geological data comprises one or more of: rock property data including porosity data, permeability data, net-to-gross (NTG) data associated with subsurface structures of a second site that is similar to or distinct from the first site; relative permeability data associated with subsurface structures of the second site that is similar to or distinct from the first site; geological boundary condition data or facies data associated with subsurface structures of the second site that is similar to or distinct from the first site; injection rate data associated with subsurface structures of the second site that is similar to or distinct from the first site; injector number data associated with subsurface structures of the second site that is similar to or distinct from the first site; and producer number data associated with subsurface structures of the second site that is similar to or distinct from the first site.

6. The method of Claim 1 , wherein the fluid storage optimality data comprises one or more of qualitative data or quantitative data that establish fluid storage efficiency information of the first location comprised in the two or more locations at the first site where fluid can be storedrelative to a second location comprised in the two or more locations at the first site where fluid can be stored.

7. The method of Claim 1, wherein a first learning data structure associated with the first ML model includes a neural network data structure; and a second learning data structure associated with the first ML model includes a decision tree data structure, the second learning data structure being overlayed on the first learning data structure to generate the trained first ML model.

8. The method of Claim 1, wherein the first parameter set, or the second parameter set comprises one or more of: fluid storage capacity data associated with each of the two or more locations at the first site where fluid can be stored; fluid storage efficiency factor data associated with each of the two or more locations at the first site where fluid can be stored; fluid plume size data associated with each of the two or more locations at the first site where fluid can be stored; average fluid injection rate data associated with each of the two or more locations at the first site where fluid can be stored; storage site development cost data associated with each of the two or more locations at the first site where fluid can be stored; and carbon footprint rating data associated with each of the two or more locations at the first site where fluid can be stored.

9. The method of Claim 1, wherein the fluid storage optimality data is generated or determined based on a combination of one or more parameters comprised in the parametric data for each of the two or more locations at the first site where fluid can be stored.

10. The method of Claim 1, wherein the first site comprises a fluid storage site including one or more of:an aquifer, a saline aquifer, an oil reservoir, a depleted oil reservoir, a gas reservoir, or a depleted gas reservoir.

11. The method of Claim 1, wherein the multi-dimensional visualization comprises a risk matrix indicating risk data for implementing fluid storage for each of the two or more locations at the first site where fluid can be stored;12. The method of Claim 11, wherein the risk matrix quantitatively or qualitatively characterizes one or more of: an amount of stored fluid leakage that is allowable at the first site; an amount of stored fluid that is allowed to leak from a primary aquifer into a secondary aquifer at the first site; an amount of stored fluid that is allowed to leak into legacy wells at the first site; an amount of stored fluid that is allowed to leak from one well into a neighboring well at the first site; resolution data of one or more monitoring system associated with the first site; or risk profile data associated with the first site imposed by regulatory bodies.

13. The method of Claim 1, wherein the fluid comprises one or more of: carbon dioxide gas, hydrogen gas, or methane gas.

14. The method of Claim 1, wherein the multi-dimensional visualization indicates: a first shape that visually characterizes fluid storage at the first location; and a second shape that visually characterizes fluid storage at the second location.

15. The method of Claim 14, wherein the first shape or the second shape comprises one of a polygonal shape or a polyhedral shape.

16. A system for determining an optimal location for fluid storage operations, the system comprising: a computer processor, and memory storing a data processing engine that comprises instructions which are executable by the computer processor to: determine first data for a first site, the first data comprising one or more of: sensor data indicating surface or subsurface conditions of a second site that is similar to or distinct from the first site, regulatory data associated with storing fluid at the first site, and infrastructure data associated with surface or subsurface infrastructure proximally located relative to the first site; generate a training dataset and a validation dataset based on the first data; generate a trained first machine learning (ML) model based on the training dataset and the validation dataset; generate, based on the trained first ML model, preliminary location data associated with two or more locations at the first site where fluid can be stored; receive second data associated with the first site, the second data comprising one or more of: geological data indicating geological information associated with the two or more locations at the first site where fluid can be stored; and constraint data imposing boundary conditions or filter conditions on the geological data; generate a trained second ML model based on the second data; apply to the trained second ML model, the preliminary location data associated with the two or more locations at the first site where fluid can be stored and thereby generate parametric data for each of the two or more locations at the first site where fluid can be stored;determine, based on the parametric data, fluid storage optimality data for each of the two or more locations at the first site where fluid can be stored, the fluid storage optimality data comprising one or more of qualitative data or quantitative data that establish fluid storage efficiency information of at least a first location comprised in the two or more locations at the first site where fluid can be stored relative to a second location comprised in the two or more locations at the first site where fluid can be stored; classify, based on the fluid storage optimality data, the two or more locations at the first site where fluid can be stored to indicate at least a ranking of the first location relative to the second location; generate, based on the classifying, a multi-dimensional visualization for: the first location, the multi-dimensional visualization indicating a first parameter set comprised in the parametric data, and the second location, the multi-dimensional visualization indicating a second parameter set comprised in the parametric data.

17. The system of Claim 16, wherein a first learning data structure associated with the first ML model includes a neural network data structure; and a second learning data structure associated with the first ML model includes a decision tree data structure, the second learning data structure being overlayed on the first learning data structure to generate the trained first ML model.

18. The system of Claim 16, wherein the geological data comprises one or more of: rock property data including porosity data, permeability data, net-to-gross (NTG) data associated with subsurface structures of the second site that is similar to or distinct from the first site; relative permeability data associated with subsurface structures of the second site that is similar to or distinct from the first site; geological boundary condition data or facies data associated with subsurface structures of the second site that is similar to or distinct from the first site;injection rate data associated with subsurface structures of the second site that is similar to or distinct from the first site; injector number data associated with subsurface structures of the second site that is similar to or distinct from the first site; and producer number data associated with subsurface structures of the second site that is similar to or distinct from the first site.

19. The system of Claim 16, wherein the first parameter set, or the second parameter set comprises one or more of: fluid storage capacity data associated with each of the two or more locations at the first site where fluid can be stored; fluid storage efficiency factor data associated with each of the two or more locations at the first site where fluid can be stored; fluid plume size data associated with each of the two or more locations at the first site where fluid can be stored; average fluid injection rate data associated with each of the two or more locations at the first site where fluid can be stored; storage site development cost data associated with each of the two or more locations at the first site where fluid can be stored; and carbon footprint rating data associated with each of the two or more locations at the first site where fluid can be stored.

20. A computer program for determining an optimal location for fluid storage operations the computer program comprising a non-transitory computer-readable medium comprising code configured to: determine first data for a first site, the first data comprising one or more of: sensor data indicating surface or subsurface conditions of a second site that is similar to or distinct from the first site, regulatory data associated with storing fluid at the first site, and infrastructure data associated with surface or subsurface infrastructure proximally located relative to the first site;generate a training dataset and a validation dataset based on the first data; generate a trained first machine learning (ML) model based on the training dataset and the validation dataset; generate, based on the trained first ML model, preliminary location data associated with two or more locations at the first site where fluid can be stored; receive second data associated with the first site, the second data comprising one or more of: geological data indicating geological information associated with the two or more locations at the first site where fluid can be stored; and constraint data imposing boundary or filter conditions on the geological data; generate a trained second ML model based on the second data; apply to the trained second ML model, the preliminary location data associated with the two or more locations at the first site where fluid can be stored and thereby generate parametric data for each of the two or more locations at the first site where fluid can be stored; determine, based on the parametric data, fluid storage optimality data for each of the two or more locations at the first site where fluid can be stored, the fluid storage optimality data comprising one or more of qualitative data or quantitative data that establish fluid storage efficiency information of at least a first location comprised in the two or more locations at the first site where fluid can be stored relative to a second location comprised in the two or more locations at the first site where fluid can be stored; classify, based on the fluid storage optimality data, the two or more locations at the first site where fluid can be stored to indicate at least a ranking of the first location relative to the second location; generate, based on the classifying, a multi-dimensional visualization for: the first location, the multi-dimensional visualization indicating a first parameter set comprised in the parametric data, and the second location, the multi-dimensional visualization indicating a second parameter set comprised in the parametric data.

Images