Cutting-edge developments in artificial intelligence (AI) are revolutionizing Earth and environmental sciences. This session provides a forum to explore and advance AI-driven innovations that leverage data to deepen insights into our planet's history, current state, and future trajectories. We welcome research on sophisticated AI approaches -- such as machine learning (ML), neural networks, and deep learning -- applied to diverse fields like atmospheric science, oceanography, climate studies, geospace, and other geophysical domains. Topics of interest include, but are not limited to, techniques for analyzing large datasets (e.g., pattern recognition, inverse problems); data-driven modeling and forecasting (e.g., dimensionality reduction, inverse modeling); methods integrating data with physical models (e.g., physics-informed ML, data assimilation); and advanced mathematical, statistical, or theory-driven ML approaches (e.g., optimization, causal inference, Koopman and Mori-Zwanzig frameworks). Join us for engaging presentations and discussions in this dynamic, interdisciplinary domain.

Cutting-edge developments in artificial intelligence (AI) are revolutionizing Earth and environmental sciences. This session provides a forum to explore and advance AI-driven innovations that leverage data to deepen insights into our planet's history, current state, and future trajectories. We welcome research on sophisticated AI approaches -- such as machine learning (ML), neural networks, and deep learning -- applied to diverse fields like atmospheric science, oceanography, climate studies, geospace, and other geophysical domains. Topics of interest include, but are not limited to, techniques for analyzing large datasets (e.g., pattern recognition, inverse problems); data-driven modeling and forecasting (e.g., dimensionality reduction, inverse modeling); methods integrating data with physical models (e.g., physics-informed ML, data assimilation); and advanced mathematical, statistical, or theory-driven ML approaches (e.g., optimization, causal inference, Koopman and Mori-Zwanzig frameworks). Join us for engaging presentations and discussions in this dynamic, interdisciplinary domain.