Carbon Sequestration

Carbon sequestration aims to capture and store atmospheric carbon dioxide, primarily to mitigate climate change. Current research focuses on improving the efficiency and safety of geological carbon sequestration (GCS) through advanced modeling techniques, including machine learning approaches like Fourier neural operators and deep reinforcement learning, to optimize injection strategies and predict CO2 migration. These efforts leverage both physics-based simulations and data-driven models, incorporating uncertainty quantification to enhance prediction accuracy and guide decision-making in GCS projects. The development of robust and efficient models is crucial for advancing GCS as a viable large-scale climate change mitigation strategy.