Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs

Oil and gas reservoirs represent suitable containers to sequester carbon dioxide (CO2) in a supercritical state because they are accessible, reservoir properties are known, and they previously contained stored buoyant fluids. However, planners must quantify the relative magnitude of the CO2 storage...

Full description

Saved in:
Bibliographic Details
Main Authors: Emil Attanasi, Philip Freeman, Timothy Coburn
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Environmental Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fenvs.2025.1562087/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849310431313657856
author Emil Attanasi
Philip Freeman
Timothy Coburn
author_facet Emil Attanasi
Philip Freeman
Timothy Coburn
author_sort Emil Attanasi
collection DOAJ
description Oil and gas reservoirs represent suitable containers to sequester carbon dioxide (CO2) in a supercritical state because they are accessible, reservoir properties are known, and they previously contained stored buoyant fluids. However, planners must quantify the relative magnitude of the CO2 storage resource in these reservoirs to formulate a comprehensive strategy for CO2 mitigation. Even reconnaissance-type estimates of CO2 storage resources of known oil and gas reservoirs may require complicated calculations involving 1) estimates of recoverable oil and gas, 2) reservoir properties (depth, temperature, pressure, etc.), and 3) the physical qualities of the retained fluids. We demonstrate the application of machine learning (ML) algorithms to bypass these computations to yield more rapid estimates of CO2 storage resources in reservoirs capable of hosting CO2 in a supercritical state. ML algorithms are computationally efficient because they do not impose the strong assumptions on the data-generating process that standard statistical or engineering procedures require. Further, ML algorithms can capture highly complex, particularly nonlinear, relationships among predictor variables. We demonstrate the application of four different ML algorithms using data from onshore and offshore oil and gas reservoirs in Europe, and show they perform well when predictions are compared to engineering estimates. The proposed methods and models provide an effective and novel way to more rapidly and directly determine the subsurface CO2 storage capacity of oil and gas reservoirs around the world, information that operators, researchers, and policymakers alike require to meet energy transition and decarbonization goals.
format Article
id doaj-art-9bedbcae963e4bc79bbc04909aef31b1
institution Kabale University
issn 2296-665X
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Environmental Science
spelling doaj-art-9bedbcae963e4bc79bbc04909aef31b12025-08-20T03:53:43ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2025-04-011310.3389/fenvs.2025.15620871562087Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirsEmil Attanasi0Philip Freeman1Timothy Coburn2U.S. Geological Survey, Geology, Energy and Minerals Science Center, Reston, VA, United StatesU.S. Geological Survey, Geology, Energy and Minerals Science Center, Reston, VA, United StatesDepartment of Systems Engineering, Colorado State University, Fort Collins, CO, United StatesOil and gas reservoirs represent suitable containers to sequester carbon dioxide (CO2) in a supercritical state because they are accessible, reservoir properties are known, and they previously contained stored buoyant fluids. However, planners must quantify the relative magnitude of the CO2 storage resource in these reservoirs to formulate a comprehensive strategy for CO2 mitigation. Even reconnaissance-type estimates of CO2 storage resources of known oil and gas reservoirs may require complicated calculations involving 1) estimates of recoverable oil and gas, 2) reservoir properties (depth, temperature, pressure, etc.), and 3) the physical qualities of the retained fluids. We demonstrate the application of machine learning (ML) algorithms to bypass these computations to yield more rapid estimates of CO2 storage resources in reservoirs capable of hosting CO2 in a supercritical state. ML algorithms are computationally efficient because they do not impose the strong assumptions on the data-generating process that standard statistical or engineering procedures require. Further, ML algorithms can capture highly complex, particularly nonlinear, relationships among predictor variables. We demonstrate the application of four different ML algorithms using data from onshore and offshore oil and gas reservoirs in Europe, and show they perform well when predictions are compared to engineering estimates. The proposed methods and models provide an effective and novel way to more rapidly and directly determine the subsurface CO2 storage capacity of oil and gas reservoirs around the world, information that operators, researchers, and policymakers alike require to meet energy transition and decarbonization goals.https://www.frontiersin.org/articles/10.3389/fenvs.2025.1562087/fullmachine learningcarbon dioxide storage resourcescarbon dioxide sequestrationoil and gas reservoirssupercritical carbon dioxide
spellingShingle Emil Attanasi
Philip Freeman
Timothy Coburn
Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs
Frontiers in Environmental Science
machine learning
carbon dioxide storage resources
carbon dioxide sequestration
oil and gas reservoirs
supercritical carbon dioxide
title Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs
title_full Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs
title_fullStr Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs
title_full_unstemmed Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs
title_short Machine learning provides reconnaissance-type estimates of carbon dioxide storage resources in oil and gas reservoirs
title_sort machine learning provides reconnaissance type estimates of carbon dioxide storage resources in oil and gas reservoirs
topic machine learning
carbon dioxide storage resources
carbon dioxide sequestration
oil and gas reservoirs
supercritical carbon dioxide
url https://www.frontiersin.org/articles/10.3389/fenvs.2025.1562087/full
work_keys_str_mv AT emilattanasi machinelearningprovidesreconnaissancetypeestimatesofcarbondioxidestorageresourcesinoilandgasreservoirs
AT philipfreeman machinelearningprovidesreconnaissancetypeestimatesofcarbondioxidestorageresourcesinoilandgasreservoirs
AT timothycoburn machinelearningprovidesreconnaissancetypeestimatesofcarbondioxidestorageresourcesinoilandgasreservoirs