AI-driven Carbon Capture and Storage (CCS): an analysis of emerging technologies for sustainable climate solutions

Climate change is driven by large greenhouse gas emissions, which have raised an alarm in efforts to reduce atmospheric carbon dioxide levels with CCS, drawing attention to decarbonization efforts. This review provides a comprehensive analysis of current Carbon Dioxide (CO 2 ) capture methods, including absorption, adsorption, and membrane separation and emerging Direct Air Capture (DAC), while addressing their limitations in cost, efficiency, and scalability. A key focus is the emerging role of Artificial Intelligence (AI) in accelerating CCS deployment. AI-driven techniques, particularly machine learning, are being applied to optimize capture processes, improve system performance, and facilitate the discovery of advanced materials. We synthesize evidence on supervised and unsupervised learning, reinforcement learning and generative models mapped to concrete CCS tasks: sorbent/solvent screening, soft sensing, emissions forecasting, digital-twin control, and storage integrity surveillance This review also highlights recent advancements at the intersection of AI and CCS, evaluates their potential for large-scale implementation, and discusses remaining technical and policy challenges. The findings underscore the strategic importance of integrating AI to enhance the effectiveness and scalability of CCS in support of global decarbonization goals.