Artificial intelligence (AI)-powered automation of feasibility modeling for geophysical monitoring tools

Abstract

Certain aspects of the disclosure provide a method of feasibility modeling for a plurality of geophysical monitoring tools. The method generally includes processing, using a flow simulation model configured to simulate carbon dioxide flow at a carbon capture and storage (CCS) site, model input parameters associated with the CCS site to generate flow simulation output data; extracting the flow simulation output data; processing the flow simulation output data to simulate a use of geophysical monitoring tools at the CCS site; for each geophysical monitoring tool: simulating a monitoring response; and determining a uncertainty level associated with the generated monitoring response; determining, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site based on the monitoring response and the uncertainty level associated with each of the geophysical monitoring tools and thereby generate a feasibility score for each tool.

Description

ARTIFICIAL INTELLIGENCE (AI)-POWERED AUTOMATION OF FEASIBILITY MODELING FOR GEOPHYSICAL MONITORING TOOLSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This Application claims the benefit of and priority to U.S. Provisional Patent Application No. 63 / 516,553, filed on July 31, 2023, the entire contents of which are hereby incorporated by reference.INTRODUCTIONField

[0002] Aspects of the present disclosure relate to geophysical monitoring, and in particular to artificial intelligence (Al)-powered automation of feasibility modelingDescription of Related Art

[0003] The stabilization and / or the reduction of atmospheric concentrations of greenhouse gases, particularly carbon dioxide (CO2), represent a key challenge in the attempt to mitigate climate change. In particular, carbon dioxide and other heat-trapping gases have molecular structures that enable them to absorb infrared radiation and re-radiate the infrared waves out in all directions - some into space and some back to Earth. The infrared radiation that is radiated back to Earth causes further warming at the surface and lower atmosphere.

[0004] Concern over environmental effects, including global warming, of carbon dioxide has resulted in significant efforts to reduce overall atmospheric carbon dioxide including, for example, through reforesting, increasing use of renewable energy sources, and the use of carbon capture and storage (CCS) (also referred to as “carbon capture and sequestration”) processes. CCS involves the separation and capture of carbon dioxide from the emissions of industrial processes prior to release into the atmosphere, transportation of the captured carbon dioxide to a sequestration site, and storage of the carbon dioxide in deep underground geologic formations for safe, secure, and permanent storage. This helps to prevent the carbon dioxide from entering the atmosphere, mitigating against carbon emissions from industry and heating and thereby reducing the contribution to global warming, ocean acidification, and other environmental effects.

[0005] Effective CCS implementation projects rely on accurate monitoring methods. Specifically, monitoring is an important part of making storage of carbon dioxide safe, effective,and permanent in all types of geologic formations. Monitoring may occur during and / or after the injection phase of a carbon dioxide storage project. Monitoring helps to confirm that the carbon dioxide is being injected into geological formations intended for CCS, that injected carbon dioxide is not leaking into other geological formations, along faults, and / or through well bores, as well as improves the storage capacity utilization of a storage reservoir. In some cases, monitoring of CCS sites further helps to satisfy regulatory requirements to ensure that potable groundwater and / or ecosystems proximate to CCS sites are protected throughout a CCS project’s lifecycle.

[0006] Many technologies exist for monitoring CCS projects. One type of monitoring uses subsurface monitoring tools, which are tools used to detect and monitor the migration of carbon dioxide that has been injected into a geological formation (e.g., a CCS site), characterize faults, characterize fractures, and / or monitor for any potential micro-seismic activity that may be present near the location of the CCS site. Examples of conventional subsurface monitoring tools include well logging tools, downhole monitoring tools, subsurface fluid sampling, tracer analysis, seismic- imaging methods, high-precision gravity methods, electrical techniques, and / or the like.

[0007] For example, at some CCS sites, four-dimensional (4D) seismic modeling (also referred to as “4D seismic monitoring” or “time-lapse seismic monitoring”) is used for CCS monitoring. The basic concept of 4D seismic technology consists of the acquisition, processing, and interpretation of multiple 3D seismic surveys on a field subjected to dynamic changes due to fluid injection, production, and carbon dioxide sequestration. In the context of CCS, 4D seismic modeling is used to compare seismic data before and after carbon dioxide injection at a storage site. Specifically, carbon dioxide has different physical properties from the surrounding saturated rock, resulting in a difference in seismic impedance. As such, seismic data may be used to investigate the behavior of stored carbon dioxide and / or any leakage occurring. An effective way to compare the state between pre- and post-injection of carbon dioxide at a CCS site is to analyze the seismic, high-resolution images pre- and post-injection.

[0008] As another example, at some CCS sites, time-lapse gravity modeling (e.g., measurements of gravity change over time) is used to detect and evaluate carbon dioxide leakage from a carbon dioxide storage site. Because carbon dioxide has a different density compared with native reservoir fluids, its injection leads to measurable shifts in the gravitational field, which may be used to assess the migration of carbon dioxide in the subsurface following its injection. Thegravity modeling technique consists of measuring the downward acceleration of gravity at a series of specific locations using high precision gravimeters and repeating the measurements at defined times, with the aim of assessing the changes in gravity between measurements. Gravity measurements are made either at the ground surface or in boreholes.

[0009] Further, at some storage sites, controlled source electromagnetic (CSEM) modeling is used for monitoring carbon dioxide injection and migration. Specifically, CSEM is a geophysical monitoring tool employing electromagnetic remote-sensing technology to map the electric resistivity distribution of the subsurface.

[0010] In some cases, using gravity modeling and / or CSEM modeling in tandem with other geophysical techniques, such as 4D seismic modeling, may be beneficial. For example, using multiple of these monitoring techniques together may help to enhance data interpretation. Further, monitoring changes over time, using one or more of these techniques (e.g., by repeating seismic surveys), may also be beneficial in detecting carbon dioxide migration and / or leakage.SUMMARY

[0011] Certain aspects provide a method of feasibility modeling for a plurality of geophysical monitoring methods, including processing, using a flow simulation model configured to simulate a flow of carbon dioxide at a carbon capture and storage (CCS) site, a plurality of model input parameters associated with the CCS site to generate flow simulation output data; extracting the flow simulation output data from the flow simulation model; processing the flow simulation output data to simulate a use of the plurality of geophysical monitoring tools at the CCS site; for each of the plurality of geophysical monitoring tools: simulating a monitoring response associated with the CCS site; and determining a level of uncertainty associated with the generated monitoring response; determining, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site based on, at least, the monitoring response and the level of uncertainty associated with each of the plurality of geophysical monitoring tools and thereby generate a feasibility score for each of the plurality of geophysical monitoring tools; and determining to implement at least one of the plurality of the geophysical monitoring tools at the CCS site based on the feasibility score for the at least one of the plurality of the geophysical monitoring tools.

[0012] Other aspects provide one or more apparatuses configured to perform the aforementioned method as well as those described herein; one or more processing systems configured to perform the aforementioned method as well as those described herein; one or more non-transitory, computer-readable media comprising instructions that, when executed by a processors of one or more apparatuses or one or more processing systems, cause the apparatus(es) processing system(s) to perform the aforementioned method as well as those described herein; a one or more computer program products embodied on a computer readable storage medium comprising code for performing the aforementioned method as well as those further described herein; one or more apparatus comprising means for performing the aforementioned method as well as those further described herein; and one or more processing systems comprising means for performing the aforementioned method as well as those further described herein.

[0013] The following description and the related drawings set forth in detail certain illustrative features of one or more aspects.DESCRIPTION OF THE DRAWINGS

[0014] The appended figures depict certain aspects and are therefore not to be considered limiting of the scope of this disclosure.

[0015] FIG. 1 depicts an example system for feasibility modeling of geophysical monitoring tools.

[0016] FIG. 2 depicts example multi-physics modeling.

[0017] FIG. 3 depicts an example of a calculated acoustic impedance change that may be used to determine a feasibility of using four-dimensional (4D) seismic modeling for carbon capture and storage (CCS) monitoring.

[0018] FIG. 4 depicts an example method of feasibility modeling for a plurality of geophysical monitoring tools.

[0019] FIG. 5 depicts an example processing system on which aspects of the present disclosure can be performed.

[0020] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the drawings. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.DETAILED DESCRIPTION

[0021] A CCS monitoring plan may involve the use of one or more CCS monitoring tools (alternatively, techniques or methods), such as the subsurface monitoring tools described above. A CCS monitoring plan is used to demonstrate containment of carbon dioxide at a CCS site. For example, a CCS monitoring plan may be used to confirm that carbon dioxide distribution at a CCS site is monitored and understood to help ensure long term conformance, and / or assess the effectiveness of any corrective measures taken in case of a leakage and / or other adverse containment event at a CCS site. To this end, it is desirable for CCS monitoring tools to be scalable and cost efficient so that monitoring is widely deployed.

[0022] A technical problem exists, though, in that the feasibility of utilizing different CCS monitoring tools may be difficult at different CCS sites. Here, feasibility refers to the ability to use a particular CCS monitoring tool for effectively monitoring the state of a CCS site. For example, while 4D seismic modeling has proven to be a powerful tool for carbon dioxide monitoring, it is not without limitations. One of the main challenges when using 4D seismic modeling is ensuring the quality and consistency of the data acquired at different times and locations within a CCS site. Factors such as noise, acquisition geometry, processing parameters, CCS site conditions (e g., rock porosity at the CCS site), and / or environmental conditions can affect the consistency and accuracy of the 4D signals. For example, CCS sites having stiffer and lower porosity rocks may produce less changes in 4D seismic data as compared to CCS sites containing softer and higher porosity rocks. As another example, background noise in 4D seismic data caused by varying weather conditions, drilling (or other similar activity) near a CCS site, ship traffic (near underwater CCS sites), and / or other seismic vessels in the vicinity of a CCS site may affect the overall accuracy of the 4D seismic data.

[0023] Similarly, gravity modeling primarily relies on detecting density contrasts in the Earth's subsurface. As such, this method faces challenges when the density difference between the injectedcarbon dioxide and the surrounding rock and / or brine is minor. Additionally, as depth increases, the resolution of gravity data tends to decrease, thereby complicating the differentiation of small- scale subsurface features. Various noise sources, such as tidal effects and / or topographic variations, may also interfere with measurements. Moreover, gravity anomalies may originate from different geological sources, creating ambiguities in interpreting the data. When monitoring gravity changes over time, other temporal changes in the subsurface, such as water table fluctuations, for example, may affect the readings.

[0024] Additionally, CSEM modeling may be limited based on depth. For example, CSEM modeling has a resolution that may decrease with depth, and CSEM modeling resolution may be better used laterally than vertically. The penetration depth of CSEM signals varies based on the source frequency and subsurface resistivity. Accordingly, in highly conductive environments, the depth of effective investigation may be limited. CSEM may also be prone to interference from various noise sources, such as cultural noise and / or ionospheric changes, to name a few. Differentiating between carbon dioxide and other resistive features, including salt domes, may pose a challenge due to ambiguities in the CSEM response. Furthermore, the logistics and instrumentation needed for CSEM modeling, such as, for example, marine surveys, may be complex and costly.

[0025] Feasibility modeling may be performed to determine effective CCS monitoring tools for a given CCS site. The feasibility modeling may consider, for example, the varying sensitives and limitations of different CCS monitoring tools given characteristics of a CCS site. In some cases, feasibility modeling provides an independent assessment of a candidate CCS monitoring tool’s ability to (1) detect, at a single point in time, the presence of injected carbon dioxide within or near a geological formation where the carbon dioxide was injected, as well as (2) repeat similar detection at one or more other points in time (e.g., detectability and repeatability). This assessment may then be used to determine whether or not the candidate monitoring tool is a cost-effective investment at a particular storage site.

[0026] However, determining the feasibility of implementing candidate CCS monitoring tools at different sites, for purposes of detecting and monitoring the migration of carbon dioxide, is a technically challenging problem. In particular, conventional methodologies for conducting feasibility modeling for CCS monitoring tools present a range of challenges. For example, thesemethodologies often require intricate manual input and expert knowledge in multidisciplinary fields. These complexities can lead to significant utilization of physical (e.g., compute, memory, power) and financial resources.

[0027] For example, multiple tasks are involved in determining whether 4D seismic modeling is feasible for monitoring carbon dioxide migration and leakage at a particular CCS site. These tasks may include (1) modeling the flow of carbon dioxide injected at the storage site, (2) generating a rock physics model for quantitative seismic interpretation, (3) creating a thermodynamic model to assess the effects of temperature and / or pressure on seismic velocities, and / or (4) performing a geomechanical analysis to model reservoir deformation induced by changes in pressure, temperature, and / or saturation, as well as stresses in the surrounding geology of the CCS site when generating seismic data.

[0028] Traditionally, performance of each of these tasks has been performed individually by a specific subject-matter expert, for example, modeling the carbon dioxide flow is generally performed by a reservoir engineer, generating the rock physics model is generally the responsibility of a rock physicist, etc. Given execution of the process for determining the feasibility of using 4D seismic monitoring stretches across multiple domains and their corresponding experts, turnaround time for performing each task is often slow thereby resulting in extended times before a feasibility decision can be made. Further, in cases where characteristics of the CCS site change, then the process may need to be repeated to account for this change, even in cases where the change is minor. Needing to repeat the same process to account for various changes in CCS site characteristics is time consuming and resource intensive. Further many of these processes require significant compute processing power and are therefore impractical to perform in the human mind, even when considering domain experts.

[0029] These challenges make CCS inaccessible to organizations with fewer resources and / or limited technical expertise. As such, there is a need for a more efficient and accessible process for determining the feasibility of using various geophysical monitoring tools at different CCS sites.

[0030] Embodiments described herein overcome the aforementioned technical problems and improve upon the state of the art by providing an automated workflow for modeling feasibility of geophysical monitoring tools. In some embodiments described herein, an automated workflow combines techniques for (1) geophysical data ingestion, (2) flow simulation, (3) multi-physicsmodeling to simulate geophysical monitoring tools, (4) predictive analytics, and (5) automated decision-making to determine whether it would be beneficial to deploy one or more geophysical monitoring tools, and more specifically which technique(s), at a CCS site for monitoring carbon dioxide migration, and in some cases, leakage.

[0031] In some embodiments, automated workflows (e.g., such as automated workflow 100 described below with respect to FIG. 1) may include steps for obtaining geophysical data (e.g., properties) for a specific CCS site where carbon dioxide is stored and providing this data to a flow simulation model as an input data. The flow simulation model may be configured to use this input data to predict the flow of carbon dioxide through porous media at the CCS site. Output data (e.g., output properties) from the flow simulation, including information about saturation, pressure, temperature, and / or composition of injected carbon dioxide (e.g., referred to as “flow simulation parameters”), for example, are collected and used to perform multi-physics modeling.

[0032] Multi-physics modeling may involve the simultaneous modeling of different aspects of a physical system and the interactions among them. For example, in this context, multi-physics modeling may be used to simultaneously model thermodynamics, resistivity, density, rock physics, noise, and / or the like at the CCS site. Further, based on modeling one or more of the foregoing, the multi-physics modeling may be used to concurrently model various geophysical monitoring tools. These techniques may include seismic modeling, CSEM modeling, gravity modeling, vertical seismic profiling (VSP), distributed acoustic sensing (DAS) modelling, and / or the like.

[0033] Feasibility modeling of these geophysical monitoring tools indicates performance of these tools with respect to detecting and monitoring carbon dioxide present at the CCS sites. In particular, a monitoring response may be generated for each geophysical monitoring tool when performing feasibility modeling. A seismic response may include, for example, information about a change in seismic data collected for the CCS site over time where seismic modeling is carried out via multiple physics (multi-physics) modeling techniques. The monitoring responses may include data expected to be acquired at the CCS site should one or more of these geophysical monitoring tools be implemented at the CCS site.

[0034] In some embodiments, the automated workflow further performs an uncertainty assessment of monitoring responses generated for the modeled geophysical monitoring tools. The uncertainty assessment quantifies the uncertainty in the geophysical monitoring tools (e.g.,including their component mathematical models, and input parameters to flow simulation) used to produce the monitoring responses.

[0035] In embodiments described here, a machine learning model (referred to herein as a “feasibility model”) may be used to determine a feasibility of implementing one or more geophysical monitoring tools at a CCS site. For example, the feasibility model may process each of these monitoring responses (each associated with a different geophysical monitoring tool) along with the determined uncertainty associated with each of the monitoring responses to generate a feasibility score for each of the geophysical monitoring tools.

[0036] In some cases, the uncertainty quantification processes hundreds of models to calculate the feasibility score. The feasibility score may be a probability of observing the time-lapse changes with certain threshold. A high probability of feasibility (e.g., a high feasibility score) predicted for a geophysical monitoring tool may indicate that the technique / tool is well-suited and capable of performing effective monitoring at the CCS site, a low probability of feasibility (e.g., a low feasibility score) may indicate the opposite.

[0037] Embodiments described herein provide significant technical advantages over conventional systems, which rely on the expertise of various individuals to model the performance of geophysical monitoring tools for performing feasibility modeling. In particular, using machine learning models for performing geophysical feasibility modeling improves efficiency, costeffectiveness, and accessibility of monitoring CCS sites. Further, use of machine learning models helps to reduce the time required for data processing, thereby enabling faster decision making. For example, instead of waiting multiple months per modeling iteration, machine learning modelbased workflows described herein may be able to predict the feasibility of deploying one or more geophysical monitoring tools at a CCS site within minutes. Therefore, resource utilization may be reduced by orders of magnitude compared to conventional approaches.

[0038] Beneficially, the automated workflows described herein are designed to be iterative. Thus, the workflow allows users to easily adjust input geophysical data (e.g., model input parameters) and automatically reprocess the flow simulation and geophysical modeling needed to predict the feasibility of one or more geophysical monitoring tools based on this new input data. The iterative nature of the workflows described herein enables resource efficient and more accurate exploration of different carbon dioxide injection strategies and / or evaluating their impact ongeophysical responses (e.g., an area often identified as a bottleneck in traditional methodologies), as well as the feasibility of various geophysical monitoring tools.

[0039] Further, modeling multiple geophysical monitoring tools using a shared, multi-physics model in the above-described workflow helps to eliminate inefficiencies of running separate models for each technique. This helps to increase efficiency and ensure consistency for performing feasibility modeling because each geophysical monitoring tool is modeled based on the same underlying flow simulation model. More consistent modeling aids in producing more accurate feasibility predictions.

[0040] In some embodiments, the above-described workflow additionally includes the creation of proxy models. Specifically, modeling needed to assess the feasibility of multiple geophysical monitoring tools at a CCS site is complex and requires significant modeling time (however, less time than conventional methods) and / or resources. Proxy modeling provides an alternative to performing such complex modeling. In particular, machine learning algorithms may be used to generate simplified models (e.g., proxies) based on the results of previous, more complex models created for a particular CCS site. The proxy models may be trained on preexisting models such as those obtained in the uncertainty quantification process. The proxy models may be enabled to predict the monitoring response of geophysical monitoring tools deployed at future CCS sites. Notably, these proxies may be executed much faster than the original models from which they were created, thereby enabling the ability to perform large-scale simulations and / or provide realtime predictions.Example Workflow for Feasibility Modeling of Geophysical Monitoring Tools

[0041] FIG. 1 illustrates an example workflow 100 for feasibility modeling of geophysical monitoring tools. As illustrated, workflow 100 combines tasks, such as flow simulation modeling at 106, multi-physics modeling at 110, uncertainty quantification at 114, risk map generation at 118, and feasibility determination at 120 to determine the expected performance of multiple geophysical monitoring tools that may be deployed at a CCS site for purposes of detecting and monitoring the migration of carbon dioxide. Optionally, in some cases, workflow 100 further includes a task for proxy models creation at 122 that may be used in subsequent iterations to improve the speed of future feasibility modeling for the CCS site. Using workflow 100 to modelmultiple geophysical monitoring tools at a CCS site allows for an effective monitoring tool to be selected without needing to test each of these tools at the CCS site (and in some cases, determining that one or more of these tools are not effective for monitoring at the particular CCS site).

[0042] In some embodiments, workflow 100 is implemented via a cloud-based artificial intelligence (Al) platform. One example of a cloud-based Al platform is a Dataiku platform made commercially available by Dataiku of New York City, New York. An Al platform may include an integrated set of technologies that allow for the developing, testing, deploying, and / or refreshing of machine learning models. The Al platform used to implement workflow 100 may integrate data ingestion, pre-processing, modeling, and, in some cases, visualization in a single environment. Further, the Al platform may allow for real-time project sharing, thereby facilitating seamless collaboration among users when performing feasibility modeling of geophysical monitoring tools. As such, implementation of workflow 100 via the Al platform provides significant technical advantages that address the challenge of information silos in conventional systems used to perform geophysical monitoring tool feasibility modeling, as described above.

[0043] Although not meant to be limiting to this particular example, workflow 100 is described below for a scenario in which a user desires to determine the feasibility of implementing (1) 4D seismic modeling, (2) CSEM modeling, and / or (3) gravity modeling at a CCS site (e.g., a water aquifer used to store carbon dioxide). Workflow 100 may be used to efficiently determine the feasibility of implementing each of these geophysical monitoring tools at the CCS site, such that a user can determine the best type of modeling that should be applied to the CCS site (e.g., for purposes of detecting and monitoring the migration of carbon dioxide at the CCS site). In some other examples, workflow 100 may be similarly used to determine the feasibility of implementing one or more other techniques, methods, and / or tools for CCS monitoring at a CCS site.

[0044] As illustrated, workflow 100 begins, at 106, with performing flow simulation modeling (e.g., a form of computational fluid dynamics) for carbon dioxide at a CCS site. Specifically, a flow simulation model designed to simulate carbon dioxide flow within the subsurface, processes a plurality of model input parameters 104 associated with the CCS site. Example model input parameters 104 may include information about the reservoir being used to store the carbon dioxide below the surface, such as the structure of reservoir, rock permeability and porosity, reservoir initial pressure and temperature conditions, fluid compositional properties, and / or fluid injectionstrategy. Example flow simulators that may be used to perform the flow simulation modeling include the INTERSECT reservoir simulator and / or the Eclipse reservoir simulator made available by Schlumberger Ltd. of Houston, Texas.

[0045] Processing model input parameters 104 generates, via flow simulation modeling at 106, a digital replication of the flow of carbon dioxide at the CCS site. Flow simulation output data 108 is then extracted from this digital replication. Example flow simulation output data 108 includes saturation data, pressure data, temperature data, and / or composition data for injected carbon dioxide at the CCS site.

[0046] For the above-presented example, at 106 in workflow 100, information about the CCS site used to store the carbon dioxide (e.g., model input parameters 104) is used as input into the flow simulation model to model the flow of carbon dioxide within the water aquifer. Saturation data, pressure data, temperature data, and / or carbon dioxide composition data (e.g., flow simulation output data 108) modeled for the CCS site may be obtained via the simulation as outputs.

[0047] In some embodiments, the workflow 100 additionally includes the performance of automated quality control checks (although not shown in FIG. 1). For example, in some cases, prior to processing the model input parameters 104 at 106, workflow 100 includes steps for reviewing model input parameters 104 for inconsistencies, missing values, and / or anomalies. In some cases, an ML model is used to review model input parameters 106 by cross-referencing a comprehensive library of necessary input and output parameters. The library may include their expected measurement units and a range of values that may be derived from historical data. Realtime manipulation of one or more model input parameters 104 may occur if one or more inconsistencies, missing values, and / or anomalies are detected. In some cases, after processing the model input parameters 104 at 106 and modeling the flow of carbon dioxide at the CCS site, workflow 100 includes steps for checking the simulated flow model for inconsistencies, missing values, and / or anomalies. In some cases, an ML model is used to perform such review of the simulated flow model.

[0048] Workflow 100 then proceeds, at 110, with performing multi-physics modeling using the flow simulation output data 108 obtained and extracted at 106. Multi -physics modeling at 110 may include using one or more modeling libraries for thermodynamics modeling, rock physicsmodeling, seismic modeling, noise modeling, time-shift calculation, CSEM modeling, gravity modeling, and / or the like. In some cases, at 110, flow simulation output data 108 is processed to (in some cases concurrently) simulate the use of a plurality of geophysical monitoring tools at the CCS site. An example of multi-physics modeling to simulate 4D seismic modeling, CSEM modeling, and gravity modeling is depicted and described with respect to FIG. 2.

[0049] As shown in FIG. 2, to simulate 4D seismic modeling, CSEM modeling, and gravity modeling at the CCS site, rock physics modeling, resistivity modeling, and density modeling are first performed (e.g., at 202, 204, and 206, respectively).

[0050] Rock physics modeling, performed at 202, may be used to generate a model that provides a link between rock properties, such as porosity, lithology, and / or fluid saturation, and elastic attributes that drive the seismic response, such as velocities (e.g., P- and S-wave velocity) and / or impedances. This generated model may then be used for 4D seismic modeling at 212. For example, rock physics modeling may provide the capability to understand the relationship between seismic amplitudes and reservoir properties. Additionally, to perform seismic modeling at 212, thermodynamic relations and equations of state may be employed and translated into the domain of seismic modeling to generate acoustic properties of carbon dioxide and carbon dioxide-fluid mix at the CCS site based on flow simulation output data 108 (e.g., extracted from the flow simulation model).

[0051] Resistivity modeling, performed at 204, may be used to model the ability of electrical current to flow through the subsurface at the CCS site. This generated model may then be used in simulating CSEM modeling at 214. For example, to simulate CSEM modeling, resistivity from flow simulation output data 108, and specifically a saturation model, may be generated and an electromagnetic response may be computed.

[0052] Density modeling, performed at 206, may be used to model density variations across the CCS site, where density is derived from flow simulation output data 108. Modeled density variations may then be used to perform gravity modeling (e.g., at 216) at the CCS site.

[0053] Simulating 4D seismic modeling, CSEM modeling, and gravity modeling through geophysical monitoring tools modeling for the CCS site helps to better understand the performance of carbon dioxide detection and monitoring (e.g., performing CCS monitoring) at the CCS site. Inparticular, a monitoring response may be generated for each modeled geophysical monitoring tool. For example, as illustrated in FIG. 2, a seismic response 222 is generated for the simulated seismic modeling at 212, a CSEM response 224 is generated for the simulated CSEM modeling at 214, and a gravity response 226 is generated for the simulated gravity modeling at 216. Seismic response 222, CSEM response 224, and gravity response 226 are examples of monitoring responses 112 illustrated in FIG. 1 (e.g., generated based on multi-physics modeling at 110).

[0054] Returning to FIG. 1, workflow 100 then proceeds, at 114, with performing uncertainty quantification to determine a level of uncertainty 116 associated with each of the generated monitoring responses 112. As described above, uncertainty quantification at 114 helps to quantify and analyze the uncertainty in the geophysical modeling (e.g., when performing multi-physics modeling at 110), and data (e.g., flow simulation output data 108) used to produce monitoring response 112.

[0055] In some embodiments, Bayesian inference methods are employed to perform uncertainty quantification at 114. Bayesian inference provides a probabilistic assessment of prediction uncertainties for different input parameters. In some embodiments, visualization tools are utilized to model spatial representations of these uncertainties determined using Bayesian inference methods. For example, a map showing the probability distribution of carbon dioxide plume spread underground (e.g., as shown in FIG. 3) may be utilized. Regions represented by patterns 302 in the map may represent higher probabilities of the plume being present, while regions represented by patterns 304 in the map may denote lower probabilities.

[0056] In addition to performing uncertainty quantification, in some embodiments, workflow 100 additionally performs risk map generation at 118. A generated risk map may be used to show the areas where carbon dioxide may migrate and / or leak. The risk map may visualize the areas with the highest probability of carbon dioxide escape and / or unintended migration, thereby helping users understand and mitigate potential hazards. The input to risk map calculation is historical data / models from monitoring tools that track carbon dioxide movements. The input may be specific to a particular CCS site, in some cases. Similar to uncertainty quantification, in some embodiments, Bayesian inference methods are also employed to perform risk map generation at 118. Bayesian inference is a method of statistical inference in which Bayes' theorem is used toupdate the probability for a hypothesis as more evidence or information becomes available. Bayes' theorem may be represented as:where P(H\E) represents the probability of a hypothesis (H) given some evidence (E) (e.g., or when some event happens), P(E\H) represents the probability of some evidence (E) given the hypothesis (Hj. P(H) represents the probability of the hypothesis (77), and P(E) represents the probability of the evidence.

[0057] Workflow 100 then proceeds, at 120, with determining a feasibility of using one or more of the modeled geophysical monitoring tools at the CCS site to allow for effective CCS monitoring. In some embodiments, a feasibility model is used to generate a feasibility score for each geophysical monitoring tool, which may be later used to make a determination as to the feasibility of deploying the corresponding geophysical monitoring tool at the CCS site. The feasibility model may be used to generate a feasibility score for one or more of the geophysical monitoring tools at the CCS site using a Bayesian framework. For example, a Bayesian framework may be used to generate a feasibility score for the geophysical monitoring tools(s) based on, at least, the monitoring responses 112 and determined levels of uncertainty 116. In some embodiments, the feasibility score may be further generated based on the risk map generated at 118. For example, if the risk of carbon dioxide leakage is high at the CCS site, then a feasibility score generated for a geophysical monitoring tool for the CCS site may be higher where the tool is capable of effectively monitoring for leaks at the CCS site.

[0058] In some embodiments, the feasibility score generated for each geophysical monitoring tool is a probability of feasibility (thus, a probability map may be generated when using the Bayesian framework). In some cases, the probability of feasibility generated for a geophysical monitoring tool is a probability of observing time lapse changes at a threshold (e g., as described below with respect to FIG. 3). The threshold may be based on a noise level determined for the CCS site.

[0059] A user and / or another model / component may determine to implement at least one of the geophysical monitoring tools at the CCS site based on the feasibility score generated for each of the geophysical monitoring tools.

[0060] As an illustrative example, three feasibility scores may be generated for first, second, and third geophysical monitoring tools (e.g., for a particular CCS site). The feasibility score for the first geophysical monitoring tool may indicate that the geophysical monitoring tool may not provide for effective monitoring at the CCS site (e.g., such as does not satisfy a feasibility threshold). Similarly, the feasibility score for the second geophysical monitoring tool may also indicate that the geophysical monitoring tool may not provide for effective monitoring at the CCS site. However, a feasibility score for the third geophysical monitoring tool may indicate that the geophysical monitoring tool may likely provide for effective monitoring at the CCS site (e.g., such as satisfies the feasibility threshold). Accordingly, a user and / or another model / component may determine that the third geophysical monitoring tool is to be considered for implementation at the CCS site for carbon dioxide monitoring.

[0061] In some embodiments, the feasibility score(s) (e.g., generated at 120), the risk map (e.g., generated at 1 18), and / or a determination whether to implement at least one of the geophysical monitoring tools (e.g., determined by another model / component) are presented to a user via a user interface. The user interface may be an interactive web application constructed using an application programming interface (API) of the Al platform implementing workflow 100. In some cases, the user interface includes details about the model input parameters 104 (e.g., of the CCS site) used to generate the feasibility score(s), the risk map, and / or the determination whether to implement one or more of the geophysical monitoring tools. The user may determine to implement at least one of the geophysical monitoring tools at the CCS site based on the feasibility score generated for each of the geophysical monitoring tools, the risk map, and / or the determination whether to implement one or more of the geophysical monitoring tools.

[0062] In some embodiments, the feasibility model is re-adjusted (e.g., updated) after implementation.

[0063] For the above example, the feasibility model may process the seismic response 222, a determined level of uncertainty 116 for the seismic response 222, and / or the risk map generated at 118 to generate a first feasibility score for 4D seismic modeling at the CCS site (e.g., for monitoring purposes). Similarly, the machine learning model may process the CSEM response 224, a determined level of uncertainty 116 for the CSEM response 224, and / or the risk map generated at 118 to generate a second feasibility score for CSEM modeling at the CCS site (e.g.,for monitoring purposes). Lastly, the machine learning model may process the gravity response 226 a determined level of uncertainty 116 for the gravity response 226, and / or the risk map generated at 118 to generate a third feasibility score for gravity modeling at the CCS site (e.g., for monitoring purposes). Based on the first, second, and third feasibility scores, a user and / or another model / component model may predict that seismic modeling is available and well-suited for monitoring carbon dioxide migration at the CCS site, while CSEM modeling and gravity modeling are not.

[0064] In some embodiments, the first probability of feasibility for 4D seismic modeling at the CCS site is predicted based on, at least, a change in acoustic impedance for the CCS site over a period of time (and then compared to a threshold, such as a 4% threshold change). The change in acoustic impedance may be determined from the seismic response 222 generated for the 4D seismic monitoring (and in some cases, may be adjusted based on the level of uncertainty 116 determined for seismic response 222).

[0065] FIG. 3 depicts example acoustic impedance change, calculated from 4D seismic modeling (e.g., forward modeling, which is a technique that creates synthetic seismic models from known geological information), that may be used to determine the feasibility of using 4D seismic modeling for CCS monitoring. More specifically, FIG. 3 depicts the acoustic impedance change due to carbon dioxide injection at a CCS site over 50 years. This acoustic impedance change is calculated based on simulating 4D seismic modeling (e.g., using the workflow described above with respect to FIG. 1). In some embodiments, a minimum threshold acoustic impedance change for determining the feasibility of using 4D seismic modeling for CCS monitoring is at or around 4% (e.g., 0.04). Because the acoustic impedance change depicted in FIG. 3 for the CCS site is greater than 0.04, a model determining the feasibility of using 4D seismic modeling may, in fact, determine that 4D seismic modeling is an effective geophysical monitoring tool that may be deployed at the CCS site.

[0066] Returning to FIG. 1, optionally in some embodiments, workflow 100 proceeds (e.g., after determining the feasibility of implementing one or more geophysical monitoring tools at a CCS site) with proxy models creation at 122. Machine learning algorithms may be used to generate proxy models based on the results of the complex models created for a particular CCS site (asdescribed above). The proxy models created may be configured to leverage advanced regression techniques and neural network architectures.Example Operations

[0067] FIG. 4 depicts an example method 400 of feasibility modeling for a plurality of geophysical monitoring tools. Method 400 may be performed by one or more processor(s) of a computing device, such as processor(s) 502 of processing system 500 described below with respect FIG. 5

[0068] Method 400 begins, at block 402, with processing, using a flow simulation model configured to simulate a flow of carbon dioxide at a CCS site, a plurality of model input parameters associated with the CCS site to generate flow simulation data.

[0069] Method 400 proceeds, at block 404, with extracting the flow simulation output data from the flow simulation model.

[0070] Method 400 proceeds, at block 406, with processing the flow simulation data to simulate a use of the plurality of geophysical monitoring tools at the CCS site.

[0071] Method 400 proceeds, at block 408, with, for each of the plurality of geophysical monitoring tools, simulating a monitoring response associated with the CCS site.

[0072] Method 400 proceeds, at block 410, with, for each of the plurality of geophysical monitoring tools, determining a level of uncertainty associated with the generated monitoring response.

[0073] Method 400 proceeds, at block 412, with determining, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site, based on, at least, the monitoring response and the level of uncertainty associated with each of the plurality of geophysical monitoring tools and thereby generate a feasibility score for each of the plurality of geophysical monitoring tools.

[0074] Method 400 proceeds, at block 414, with determining to implement at least one of the plurality of the geophysical monitoring tools at the CCS site based on the feasibility score for the at least one of the plurality of the geophysical monitoring tools.

[0075] In certain aspects, the plurality of geophysical monitoring tools comprises two or more of: four dimensional (4D) seismic modeling, gravity modeling, or CSEM modeling.

[0076] In certain aspects, the plurality of geophysical monitoring tools comprise the 4D seismic modeling. In certain aspects, processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site, at block 406, includes performing rock physics modeling to model a relationship between rock properties and elastic attributes at the CCS site.

[0077] In certain aspects, the plurality of geophysical monitoring tools comprise the gravity modeling. In certain aspects, processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site, at block 406, includes performing density modeling to model density variations across the CCS site.

[0078] In certain aspects, the plurality of geophysical monitoring tools comprise the CSEM modeling. In certain aspects, processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site, at block 406, includes performing resistivity modeling to model an ability of electrical current to flow through a subsurface at the CCS site.

[0079] In certain aspects, the plurality of geophysical monitoring tools comprises the 4D seismic modeling; and the feasibility score generated for the 4D seismic modeling is based on, at least, a change in acoustic impedance for the CCS site over time determined using the monitoring response generated for the 4D seismic modeling and the level of uncertainty associated with the monitoring response.

[0080] In certain aspects, the feasibility score comprises a probability.

[0081] In certain aspects, method 400 further includes generating a risk map identifying one or more risks associated with storage of the carbon dioxide at the CCS site, wherein the feasibility score generated for each of the plurality of geophysical monitoring tools is further generated based on the risk map.

[0082] Note that FIG. 4 is just one example of a method, and other methods including fewer, additional, or alternative steps are possible consistent with this disclosure.Example Processing System for Feasibility Modeling of Geophysical Monitoring Tools

[0083] FIG. 5 depicts an example processing system 500 configured to perform various aspects described herein, including, for example, method 400 as described above with respect to FIG. 4

[0084] Processing system 500 is generally an example of an electronic device configured to execute computer-executable instructions, such as those derived from compiled computer code, including without limitation personal computers, tablet computers, servers, smart phones, smart devices, wearable devices, augmented and / or virtual reality devices, and others.

[0085] In the depicted example, processing system 500 includes one or more processors 502, one or more input / output devices 504, one or more display devices 506, one or more network interfaces 508 through which processing system 500 is connected to one or more networks (e.g., a local network, an intranet, the Internet, or any other group of processing systems communicatively connected to each other), and computer-readable medium 544. In the depicted example, the aforementioned components are coupled by a bus 510, which may generally be configured for data exchange amongst the components. Bus 510 may be representative of multiple buses, while only one is depicted for simplicity.

[0086] Processor(s) 502 are generally configured to retrieve and execute instructions stored in one or more memories, including local memories like computer-readable medium 544, as well as remote memories and data stores. Similarly, processor(s) 502 are configured to store application data residing in local memories like the computer-readable medium 544, as well as remote memories and data stores. More generally, bus 510 is configured to transmit programming instructions and application data among the processor(s) 502, display device(s) 506, network interface(s) 508, and / or computer-readable medium 544. In certain embodiments, processor(s) 502 are representative of a one or more central processing units (CPUs), graphics processing unit (GPUs), tensor processing unit (TPUs), accelerators, and other processing devices.

[0087] Input / output device(s) 504 may include any device, mechanism, system, interactive display, and / or various other hardware and software components for communicating information between processing system 500 and a user of processing system 500. For example, input / outputdevice(s) 504 may include input hardware, such as a keyboard, touch screen, button, microphone, speaker, and / or other device for receiving inputs from the user and sending outputs to the user.

[0088] Display device(s) 506 may generally include any sort of device configured to display data, information, graphics, user interface elements, and the like to a user. For example, display device(s) 506 may include internal and external displays such as an internal display of a tablet computer or an external display for a server computer or a projector. Display device(s) 506 may further include displays for devices, such as augmented, virtual, and / or extended reality devices. In various embodiments, display device(s) 506 may be configured to display a graphical user interface.

[0089] Network interface(s) 508 provide processing system 500 with access to external networks and thereby to external processing systems. Network interface(s) 508 can generally be any hardware and / or software capable of transmitting and / or receiving data via a wired or wireless network connection. Accordingly, network interface(s) 508 can include a communication transceiver for sending and / or receiving any wired and / or wireless communication.

[0090] Computer-readable medium 544 may be a volatile memory, such as a random access memory (RAM), or a nonvolatile memory, such as nonvolatile random access memory (NVRAM), or the like. In this example, computer-readable medium 544 includes flow simulation modeling component 512, multi-physics modeling component 514, uncertainty quantification component 516, risk map generation component 518, feasibility determination component 520, proxy models creation component 522, model input parameters 524, flow simulation data 526, monitoring responses 528, levels of uncertainty 530, feasibility scores 532, proxy models 534, processing logic 536, simulating logic 538, determining logic 540, and generating logic 542.

[0091] Note that FIG. 5 is just one example of a processing system consistent with aspects described herein, and other processing systems having additional, alternative, or fewer components are possible consistent with this disclosure.Example Clauses

[0092] Implementation examples are described in the following numbered clauses:

[0093] Clause 1 : A method for modeling feasibility for a plurality of geophysical monitoring tools, comprising: processing, using a flow simulation model configured to simulate a flow of carbon dioxide at a carbon capture and storage (CCS) site, a plurality of model input parameters associated with the CCS site to generate flow simulation output data; extracting the flow simulation output data from the flow simulation model; processing the flow simulation output data to simulate a use of the plurality of geophysical monitoring tools at the CCS site; for each of the plurality of geophysical monitoring tools: simulating a monitoring response associated with the CCS site; and determining a level of uncertainty associated with the generated monitoring response; determining, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site based on, at least, the monitoring response and the level of uncertainty associated with each of the plurality of geophysical monitoring tools and thereby generate a feasibility score for each of the plurality of geophysical monitoring tools; and determining to implement at least one of the plurality of the geophysical monitoring tools at the CCS site based on the feasibility score for the at least one of the plurality of the geophysical monitoring tools.

[0094] Clause 2: The method of Clause 1, wherein the plurality of geophysical monitoring tools comprises two or more of: four dimensional (4D) seismic modeling, gravity modeling, or controlled source electromagnetic (CSEM) modeling.

[0095] Clause 3: The method of Clause 2, wherein: the plurality of geophysical monitoring tools comprise the 4D seismic modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing rock physics modeling to model a relationship between rock properties and elastic attributes at the CCS site.

[0096] Clause 4: The method of any one of Clauses 2-3, wherein: the plurality of geophysical monitoring tools comprise the gravity modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing density modeling to model density variations across the CCS site.

[0097] Clause 5: The method of any one of Clauses 2-4, wherein: the plurality of geophysical monitoring tools comprise the CSEM modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprisesperforming resistivity modeling to model an ability of electrical current to flow through a subsurface at the CCS site.

[0098] Clause 6: The method of any one of Clauses 2-5, wherein: the plurality of geophysical monitoring tools comprises the 4D seismic modeling; and the feasibility score generated for the 4D seismic modeling is based on, at least, a change in acoustic impedance for the CCS site over time determined using the monitoring response generated for the 4D seismic modeling and the level of uncertainty associated with the monitoring response.

[0099] Clause 7: The method of any one of Clauses 1-6, further comprising: generating a risk map identifying one or more risks associated with storage of the carbon dioxide at the CCS site, wherein the feasibility score generated for each of the plurality of geophysical monitoring tools is further generated based on the risk map.

[0100] Clause 8: The method of any one of Clauses 1-7, wherein the feasibility score comprises a probability.

[0101] Clause 9: One or more apparatuses, comprising: one or more memories; and one or more processors, coupled to the one or more memories, configured to cause the apparatus to perform a method in accordance with any one of Clauses 1-8.

[0102] Clause 10: One or more apparatuses, comprising: one or more memories; and one or more processors, coupled to the one or more memories, configured to perform a method in accordance with any one of Clauses 1-8.

[0103] Clause 1 1 : One or more apparatuses, comprising means for performing a method in accordance with any one of Clauses 1-8.

[0104] Clause 12: A processing system, comprising: a memory comprising computerexecutable instructions; and a processor configured to execute the computer-executable instructions and cause the processing system to perform a method in accordance with any one of Clauses 1-8.

[0105] Clause 13: A processing system, comprising means for performing a method in accordance with any one of Clauses 1-8.

[0106] Clause 14: A non-transitory computer-readable medium storing program code for causing a processing system to perform the steps of any one of Clauses 1-8.

[0107] Clause 15: A computer program product embodied on a computer-readable storage medium comprising code for performing a method in accordance with any one of Clauses 1-8.Additional Considerations

[0108] The preceding description is provided to enable any person skilled in the art to practice the various embodiments described herein. The examples discussed herein are not limiting of the scope, applicability, or embodiments set forth in the claims. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments. For example, changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as appropriate. For instance, the methods described may be performed in an order different from that described, and various steps may be added, omitted, or combined. Also, features described with respect to some examples may be combined in some other examples. For example, an apparatus may be implemented or a method may be practiced using any number of the aspects set forth herein. In addition, the scope of the disclosure is intended to cover such an apparatus or method that is practiced using other structure, functionality, or structure and functionality in addition to, or other than, the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of a claim.

[0109] As used herein, a phrase referring to “at least one of’ a list of items refers to any combination of those items, including single members. As an example, “at least one of: a, b, or c” is intended to cover a, b, c, a-b, a-c, b-c, and a-b-c, as well as any combination with multiples of the same element (e.g., a-a, a-a-a, a-a-b, a-a-c, a-b-b, a-c-c, b-b, b-b-b, b-b-c, c-c, and c-c-c or any other ordering of a, b, and c).

[0110] As used herein, the term “determining” encompasses a wide variety of actions. For example, “determining” may include calculating, computing, processing, deriving, investigating, looking up (e.g., looking up in a table, a database or another data structure), ascertaining and the like. Also, “determining” may include receiving (e.g., receiving information), accessing (e.g.,accessing data in a memory) and the like. Also, “determining” may include resolving, selecting, choosing, establishing and the like.[0U1] The methods disclosed herein comprise one or more steps or actions for achieving the methods. The method steps and / or actions may be interchanged with one another without departing from the scope of the claims. In other words, unless a specific order of steps or actions is specified, the order and / or use of specific steps and / or actions may be modified without departing from the scope of the claims. Further, the various operations of methods described above may be performed by any suitable means capable of performing the corresponding functions. The means may include various hardware and / or software component(s) and / or module(s), including, but not limited to a circuit, an application specific integrated circuit (ASIC), or processor. Generally, where there are operations illustrated in figures, those operations may have corresponding counterpart means-plus- function components with similar numbering.

[0112] The following claims are not intended to be limited to the embodiments shown herein, but are to be accorded the full scope consistent with the language of the claims. Within a claim, reference to an element in the singular is not intended to mean “one and only one” unless specifically so stated, but rather “one or more.” Unless specifically stated otherwise, the term “some” refers to one or more. No claim element is to be construed under the provisions of 35 U.S.C. §112(f) unless the element is expressly recited using the phrase “means for” or, in the case of a method claim, the element is recited using the phrase “step for.” All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims.

Claims

CLAIMSWHAT IS CLAIMED IS:

1. A method for modeling feasibility for a plurality of geophysical monitoring tools, comprising: processing, using a flow simulation model configured to simulate a flow of carbon dioxide at a carbon capture and storage (CCS) site, a plurality of model input parameters associated with the CCS site to generate flow simulation output data; extracting the flow simulation output data from the flow simulation model; processing the flow simulation output data to model a use of the plurality of geophysical monitoring tools at the CCS site; for each of the plurality of geophysical monitoring tools: simulating a monitoring response associated with the CCS site; and determining a level of uncertainty associated with the generated monitoring response; determining, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site based on, at least, the monitoring response and the level of uncertainty associated with each of the plurality of geophysical monitoring tools and thereby generate a feasibility score for each of the plurality of geophysical monitoring tools; and determining to implement at least one of the plurality of the geophysical monitoring tools at the CCS site based on the feasibility score for the at least one of the plurality of the geophysical monitoring tools.

2. The method of Claim 1, wherein the plurality of geophysical monitoring tools comprise two or more of: four dimensional (4D) seismic modeling, gravity modeling, or controlled source electromagnetic (CSEM) modeling.

3. The method of Claim 2, wherein: the plurality of geophysical monitoring tools comprise the 4D seismic modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing rock physics modeling to model a relationship between rock properties and elastic attributes at the CCS site.

4. The method of Claim 2, wherein: the plurality of geophysical monitoring tools comprise the gravity modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing density modeling to model density variations across the CCS site.

5. The method of Claim 2, wherein: the plurality of geophysical monitoring tools comprise the CSEM modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing resistivity modeling to model an ability of electrical current to flow through a subsurface at the CCS site.

6. The method of Claim 2, wherein: the plurality of geophysical monitoring tools comprise the 4D seismic modeling; and the feasibility score generated for the 4D seismic modeling is based on, at least, a change in acoustic impedance for the CCS site over time determined using the monitoring response generated for the 4D seismic modeling and the level of uncertainty associated with the monitoring response.

7. The method of Claim 1, further comprising: generating a risk map identifying one or more risks associated with storage of the carbon dioxide at the CCS site, wherein the feasibility score generated for each of the plurality of geophysical monitoring tools is further generated based on the risk map.

8. The method of Claim 1, wherein the feasibility score comprises a probability.

9. An apparatus, comprising: one or more memories; and one or more processors, coupled to the one or more memories, configured to cause the apparatus to: process, using a flow simulation model configured to simulate a flow of carbon dioxide at a carbon capture and storage (CCS) site, a plurality of model input parameters associated with the CCS site to generate flow simulation output data; extract the flow simulation output data from the flow simulation model; process the flow simulation output data to model a use of a plurality of geophysical monitoring tools at the CCS site; for each of the plurality of geophysical monitoring tools: simulate a monitoring response associated with the CCS site; and determine a level of uncertainty associated with the generated monitoring response; determine, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site based on, at least, the monitoring response and the level of uncertainty associated with each of the plurality of geophysical monitoring tools and thereby generate a feasibility score for each of the plurality of geophysical monitoring tools; and determine to implement at least one of the plurality of the geophysical monitoring tools at the CCS site based on the feasibility score for the at least one of the plurality of the geophysical monitoring tools.

10. The apparatus of Claim 9, wherein the plurality of geophysical monitoring tools comprise two or more of: four dimensional (4D) seismic modeling, gravity modeling, or controlled source electromagnetic (CSEM) modeling.

11. The apparatus of Claim 10, wherein: the plurality of geophysical monitoring tools comprise the 4D seismic modeling; and to process the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site, the one or more processors are configured to cause the apparatus to perform rock physics modeling to model a relationship between rock properties and elastic attributes at the CCS site.

12. The apparatus of Claim 10, wherein: the plurality of geophysical monitoring tools comprise the gravity modeling; and to process the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site, the one or more processors are configured to cause the apparatus to perform density modeling to model density variations across the CCS site.

13. The apparatus of Claim 10, wherein: the plurality of geophysical monitoring tools comprise the CSEM modeling; and to process the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site, the one or more processors are configured to cause the apparatus to perform resistivity modeling to model an ability of electrical current to flow through a subsurface at the CCS site.

14. The apparatus of Claim 10, wherein: the plurality of geophysical monitoring tools comprise the 4D seismic modeling; and the feasibility score generated for the 4D seismic modeling is based on, at least, a change in acoustic impedance for the CCS site over time determined using the monitoring response generated for the 4D seismic modeling and the level of uncertainty associated with the monitoring response.

15. The apparatus of Claim 9, wherein the one or more processors are configured to cause the apparatus to: generate a risk map identifying one or more risks associated with storage of the carbon dioxide at the CCS site,wherein the feasibility score generated for each of the plurality of geophysical monitoring tools is further generated based on the risk map.

16. The apparatus of Claim 9, wherein the feasibility score comprises a probability.

17. One or more non-transitory computer-readable media comprising executable instructions that, when executed by one or more processors of an apparatus, cause the apparatus to perform operations comprising: processing, using a flow simulation model configured to simulate a flow of carbon dioxide at a carbon capture and storage (CCS) site, a plurality of model input parameters associated with the CCS site to generate flow simulation output data; extracting the flow simulation output data from the flow simulation model; processing the flow simulation output data to model a use of a plurality of geophysical monitoring tools at the CCS site; for each of the plurality of geophysical monitoring tools: simulating a monitoring response associated with the CCS site; and determining a level of uncertainty associated with the generated monitoring response; determining, using a Bayesian framework, a feasibility of implementing one or more of the plurality of geophysical monitoring tools at the CCS site based on, at least, the monitoring response and the level of uncertainty associated with each of the plurality of geophysical monitoring tools and thereby generate a feasibility score for each of the plurality of geophysical monitoring tools; and determining to implement at least one of the plurality of the geophysical monitoring tools at the CCS site based on the feasibility score for the at least one of the plurality of the geophysical monitoring tools.

18. The one or more non-transitory computer-readable media of Claim 17, wherein the plurality of geophysical monitoring tools comprise two or more of: four dimensional (4D) seismic modeling, gravity modeling, orcontrolled source electromagnetic (CSEM) modeling.

19. The one or more non-transitory computer-readable media of Claim 18, wherein: the plurality of geophysical monitoring tools comprise the 4D seismic modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing rock physics modeling to model a relationship between rock properties and elastic attributes at the CCS site.

20. The one or more non-transitory computer-readable media of Claim 18, wherein: the plurality of geophysical monitoring tools comprise the gravity modeling; and processing the flow simulation output data to model the use of the plurality of geophysical monitoring tools at the CCS site comprises performing density modeling to model density variations across the CCS site.

Images