Geologic storage of CO₂, H₂, and compressed air is critical to advancing low-carbon energy systems by enabling carbon sequestration and mitigating renewable energy intermittency through power-to-gas strategies. Progress in these applications requires a rigorous understanding of coupled geochemical, geomechanical, hydrodynamic, and microbial processes governing gas–rock interactions. Recent advances in data-driven and artificial intelligence (AI) approaches are enhancing subsurface characterization, predictive modeling, uncertainty quantification, and real-time monitoring. Integrating physics-based models with machine learning offers new opportunities to improve storage performance and reliability.

This session invites experimental, modeling, and AI-enabled studies on geologic storage, including underground hydrogen storage, compressed air energy storage (CAES), CO₂ mineralization in mafic and ultramafic formations, innovative storage strategies in diverse geologic settings, and machine learning applications for subsurface analysis, leakage detection, and risk assessment.

• EP - Earth and Planetary Surface Processes