The rapid expansion of spatiotemporal data from satellites, in situ observations, simulations, and sensor networks is transforming both Earth and space science. Advances in artificial intelligence and machine learning (AI/ML)—including deep learning, foundation models, and generative AI—are enabling new approaches to analyze and model complex, multiscale processes across the Earth system and near-Earth space environment. This session invites contributions that integrate spatiotemporal data analytics with emerging AI/ML methods to advance understanding, prediction, and decision-making.

We welcome studies addressing challenges such as data heterogeneity, sparsity, uncertainty, scalability, and interpretability. Topics include novel AI/ML models (e.g., transformers, graph neural networks, physics-informed learning), multi-source data fusion, hybrid physical–AI modeling, digital twins, and real-time monitoring systems. Applications may span hydrology, climate, extreme events, ecosystems, space weather, and heliophysics.

This session aims to foster interdisciplinary exchange and highlight innovations bridging data, models, and actionable intelligence across Earth and space systems.

• A - Atmospheric Sciences
• ED - Education
• GH - GeoHealth
• H - Hydrology