Machine learning across the lifecycle of geological CO2 storage: applications, workflows, and requirements for trustworthy deployment
Clean Energy · 09.07.2026 · 10 (4) · 85-102
DOI: 10.1093/ce/zkag027 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clean Energy, online erschienen am 02.06.2026. Verfasst von Chunkai Wang und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Autonomous Research Project of the National Key Laboratory of Oil and Gas Resources and Engineering.
Abstract (Originalsprache)
As geological CO2 storage moves from pilot demonstrations towards large-scale deployment, storage projects require faster, more transparent, and auditable decisions under strong geological heterogeneity and operational uncertainty. Machine learning (ML) is increasingly used as a set of workflow accelerators that integrate data, simulation, monitoring, and engineering decisions. This review evaluates ML across four lifecycle stages: site screening, injection design, operational monitoring and monitoring, reporting, and verification accounting. Instead of organizing the literature by algorithm family, it uses engineering tasks, performance metrics, and deployable workflows as the main framework. The review summarizes stage-specific data streams, learning tasks, validation needs, and outputs, and identifies three workflow families: surrogate-enabled scenario evaluation and optimization, assimilation-oriented hybrid state updating, and integrated workflows for monitoring, reporting, and verification. It also compares machine-learning and physics-based approaches and outlines requirements for trustworthy deployment, including cross-scenario validation, explicit uncertainty quantification, applicability-domain control, explainability, and workflow governance. The analysis shows that the most useful role of ML is not to replace numerical simulation, but to shorten engineering iteration loops while retaining physical consistency, uncertainty transparency, and auditable evidence. Future progress will depend on open benchmarks, multimodal data fusion, hybrid physics-ML workflows, and governance structures that can support regulatory review and long-term stewardship.
Förderung
- National Natural Science Foundation of China
- Autonomous Research Project of the National Key Laboratory of Oil and Gas Resources and Engineering
Zitieren
APA
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, 10(4), 85-102. https://doi.org/10.1093/ce/zkag027
Vancouver
Wang C, Zhao Y, Xu H, Liu Q, Diwu P, Tiong M, et al. Machine learning across the lifecycle of geological CO2 storage: applications, workflows, and requirements for trustworthy deployment. Clean Energy. 2026;10(4):85-102. doi:10.1093/ce/zkag027
BibTeX
@article{Wang2026,
author = {Wang, Chunkai and Zhao, Yue and Xu, Hengyue and Liu, Qi and Diwu, Pengxiang and Tiong, Michelle and Xian, Chenggang and Ye, Hang and Wu, Shengkun and Zhang, Shengwei and Liu, Hui},
title = {Machine learning across the lifecycle of geological CO2 storage: applications, workflows, and requirements for trustworthy deployment},
journal = {Clean Energy},
year = {2026},
volume = {10},
number = {4},
pages = {85--102},
doi = {10.1093/ce/zkag027}
}
EUVIMED