This session highlights the growing role of artificial intelligence (AI) in advancing scientific discovery within the heliophysics community. We focus on recent progress in AI methodologies that enable new insights and complement traditional research approaches. Contributions are invited that apply AI across heliophysical domains, including the solar wind, magnetosphere, ionosphere, thermosphere, and mesosphere.

We encourage studies that integrate AI techniques, such as data-driven deep learning, interpretable machine-learning, physics-informed neural networks (PINNs), and PDE-based approaches, with established methods, including theory, first-principles simulations, empirical modeling, and statistical analyses. Such integrative approaches are essential for improving our understanding of complex Sun-Earth system dynamics.

This session is organized in collaboration with the ML-based Geospace Environment Modeling (GEM) resource group, which focuses on advancing data-driven heliophysics modeling. Our goal is to bring together current AI-driven efforts and promote collaboration across the heliophysics community to accelerate progress in understanding solar wind-Earth interactions.

• NG - Nonlinear Geophysics
• SA - SPA-Aeronomy