AI-driven carbon capture, utilization, and storage (CCUS) for decarbonizing energy systems

Abstract The transition to net-zero emissions has become a global priority, with Carbon Capture, Utilization, and Storage (CCUS) emerging as a key technology for decarbonizing hard-to-abate sectors such as cement, steel, and energy production. Despite its potential, CCUS faces significant challenges related to efficiency, scalability, and system integration. Artificial Intelligence (AI) offers promising solutions to enhance CCUS performance across the entire value chain, including capture, utilization, and storage processes. Advanced AI techniques, such as machine learning, deep learning, and reinforcement learning, are increasingly being employed to optimize capture operations, accelerate materials discovery, and enable real-time monitoring and fault detection in CCUS systems. However, several barriers remain, including limited availability of high-quality datasets, challenges in model interpretability, and insufficient cross-disciplinary integration between AI and CCUS research communities. AI-driven optimization of multi-stage CCUS systems is essential for improving operational efficiency and enabling large-scale deployment. Future research should therefore prioritize system-level integration, AI-guided materials design, and the coupling of CCUS with renewable energy systems to enhance economic and environmental performance. Addressing these challenges will strengthen the role of AI-enabled CCUS as a critical pathway toward achieving global net-zero emissions targets.