AI-Enabled Monitoring, Verification, and Accounting of Stored CO₂
Keywords:
artificial intelligence, monitoring verification and accounting, geological CO₂ storage, deep learning, reinforcement learning, carbon accounting, reservoir monitoringAbstract
Monitoring, verification, and accounting (MVA) constitute the regulatory and operational backbone of geological CO₂ storage
(GCS), providing the evidentiary basis for confirming that injected CO₂ remains safely contained, quantifying stored volumes
for carbon credit accounting, and satisfying the compliance requirements of regulatory frameworks governing carbon capture,
utilization, and storage (CCUS). Traditional MVA relies on a combination of geophysical surveys, downhole sensor networks,
and physics-based reservoir simulation, all of which are constrained by high costs, limited monitoring frequency, and the
computational burden of full-physics interpretation. Artificial intelligence (AI), spanning deep learning, reinforcement learning,
and explainable machine learning, is increasingly being integrated into MVA workflows to accelerate data interpretation,
enable near-real-time anomaly detection, and support adaptive monitoring network design under geologic and operational
uncertainty. This review examines the state of AI-enabled MVA across the CO₂ storage lifecycle, synthesizing recent advances
in machine-learning-based monitoring design, deep-learning-based seismic and pressure anomaly detection, reinforcementlearning-
based reservoir management, and reactive transport and geomechanical characterization relevant to long-term
storage verification. It draws on case studies from heterogeneous depleted gas reservoirs, geothermal-analogue reservoir
and heat exchanger systems, and geomechanically informed reservoir characterization, and further considers methodological
parallels with AI-driven monitoring, auditing, and cost-accounting frameworks developed for national-scale healthcare
systems. The review concludes by identifying persistent challenges in ground-truth data scarcity, model transferability, and
regulatory standardization, and proposes a research agenda for advancing AI-enabled MVA toward routine, auditable use in
commercial-scale CO₂ storage projects.
References
Chen, B., Harp, D. R., Lin, Y., Keating, E. H., & Pawar, R. J. (2018). Geologic CO2 sequestration monitoring design: A machine learning and uncertainty quantification based approach. Applied Energy, 225, 332–345. https://doi.org/10.1016/j.apenergy.2018.05.041
Nguyen, T. T. (2026b). Transforming prior authorization through artificial intelligence: A national framework for reducing administrative burden and improving patient access. International Journal of AI, BigData, Computational and Management Studies, 7(3), 17–27.
Nguyen, T. T. (2026c). The economic impact of AI adoption in healthcare: Estimating national cost savings, productivity gains, and long-term health outcomes. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 7(3), 1–11.
Nguyen, T. T. (2026d). National-scale predictive analytics for Medicare and Medicaid: An AI-driven approach to identifying high-risk populations and reducing healthcare costs. Journal of Advanced Scientific Research, 17(6), 1–10.
Sun, A. Y. (2020). Optimal carbon storage reservoir management through deep reinforcement learning. Applied Energy, 278, 115660. https://doi.org/10.1016/j.apenergy.2020.115660
Wang, C., Zhao, Y., Xu, H., Liu, Q., Diwu, P., Tiong, M., Xian, C., Ye, H., Wu, S., Zhang, S., & Liu, H. (2026). Machine learning across the lifecycle of geological CO2 storage: Applications, workflows and requirements for trustworthy deployment. Clean Energy, zkag027. https://doi.org/10.1093/ce/zkag027
Zhong, Z., Sun, A. Y., Yang, Q., & Ouyang, Q. (2019). A deep learning approach to anomaly detection in geological carbon sequestration sites using pressure measurements. Journal of Hydrology, 573, 885–894. https://doi.org/10.1016/j.jhydrol.2019.04.015
Zhou, Z., Lin, Y., Zhang, Z., Wu, Y., Wang, Z., Dilmore, R., & Guthrie, G. (2019). A data-driven CO2 leakage detection using seismic data and spatial–temporal densely connected convolutional neural networks. International Journal of Greenhouse Gas Control, 90, 102790. https://doi.org/10.1016/j.ijggc.2019.102790
