Revolutionizing carbon capture efficiency: A comprehensive review of AI-Driven Optimization Strategies for CO₂ Capture and Storage Processes
1 Department of Mechanical Engineering, Akwa Ibom State University, Akwa Ibom, Nigeria.
2 Department of Mechanical Engineering, University of Ilorin, Nigeria.
3 Department of Metallurgical and Materials Engineering, University of Nigeria, Nsukka.
4 Department of Environmental Sciences, Indiana University Bloomington, USA.
5 Department of Chemical Engineering, University of Benin, Edo, Nigeria.
6 Research and Development Laboratory (LRDE), EPITA School of Engineering and Advanced Technologies, Paris, France.
7 Department of Electrical Electronics Engineering, The Polytechnic Ibadan, Oyo, Nigeria.
Review
International Journal of Science and Technology Research Archive, 2025, 09(01), 018-043.
Article DOI: 10.53771/ijstra.2025.9.1.0043
Publication history:
Received on 12 May 2025; revised on 21 June 2025; accepted on 23 June 2025
Abstract:
The pressing need to achieve net-zero emissions by 2050 highlights the critical role of Carbon Capture, Utilization, and Storage (CCUS) in addressing climate change, yet high energy costs and scalability challenges limit its adoption. Artificial intelligence (AI) offers innovative solutions to enhance CCUS efficiency through advanced optimization strategies. This review provides a comprehensive analysis of AI-driven approaches, focusing on machine learning (ML) and deep reinforcement learning (DRL) applications across CO₂ capture, sorbent design, and storage monitoring. In capture, AI optimizes solvent-based and membrane-based systems, achieving 10–20% cost reductions in projects like Technology Centre Mongstad and Boundary Dam. For sorbent design, ML accelerates the development of metal-organic frameworks and polymeric membranes, improving CO₂ selectivity by 15–25%. In storage, AI enhances geological site selection and leakage detection, with initiatives like Northern Lights showing 10–15% improved monitoring accuracy. Despite these advancements, challenges such as data scarcity, computational costs, and legacy system integration persist. This article synthesizes progress from 2023–2025, evaluates techno-economic and environmental impacts, and identifies research gaps, including the need for open-access datasets and hybrid AI-process models. By highlighting case studies and proposing future directions, such as AI integration in CCUS hubs, this review underscores AI’s transformative potential to drive cost-effective, scalable CCUS solutions, advancing global decarbonization and sustainable engineering innovation.
Keywords:
Artificial Intelligence; Carbon Capture; Co₂ Storage; Machine Learning; Deep Learning; Techno-Economic Analysis; Environmental Sustainability; Life-Cycle Assessment
Full text article in PDF:
Copyright information:
Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0