Scientific Machine Learning Enhanced Forecasting in Geological Carbon Storage

Learn how scientific machine learning frameworks can revolutionize forecasting capabilities for geological carbon storage in this 56-minute webinar presented by the Society for Industrial and Applied Mathematics. Explore the central challenges in predicting subsurface CO2 migration and trapping, including geological heterogeneity, data scarcity, and computational costs of high-fidelity simulations. Discover how digital twins combine experimental data, physics-based models, and machine learning surrogates to reproduce and predict CO2 dynamics across both pressure-driven and capillary-buoyancy-dominated flow regimes. Examine quantitative studies of CO2 retention and plume migration while identifying key geological and barrier properties that control storage performance. Understand the development of scalable and interpretable scientific machine learning foundations for digital twins of subsurface energy storage, bridging experimental observables with predictive modeling of CO2 sequestration in realistic heterogeneous formations. Gain insights into cutting-edge research that aims to enhance the accuracy and reliability of geological carbon storage forecasting across multiple scales.