Machine Learning (ML) is increasingly integrated into weather and climate science workflows, from emulating complex dynamical systems to enhancing predictive capabilities and uncertainty quantification. However, the opaque nature of many ML models poses challenges for scientific credibility, operational deployment, and stakeholder trust. Explainable AI (XAI) offers a suite of methodologies to interrogate, interpret, and validate ML models, enabling more transparent and accountable use of data-driven approaches in Earth system science.

This session invites contributions that advance the use of XAI to improve trust, interpretability, and robustness in ML applications across weather and climate domains — not only to validate and constrain models, but also to enable scientific discovery and insight. We welcome submissions that address:

• Development and application of XAI techniques for interpreting ML-based forecasts, reanalyses, and climate projections
• Integration of physical constraints and domain knowledge into interpretable ML frameworks
• Use of XAI to diagnose model biases, failure modes, and uncertainty propagation
• Explainability-driven approaches to support causal inference, feature attribution, process understanding, and knowledge discovery, including the identification of emergent patterns or physical insights from ML models
• Human-in-the-loop and stakeholder-informed validation of ML models in climate and weather services
• Tooling challenges in applying XAI to high-dimensional, regression-based climate and weather problems where current methods are often limited in scalability, generality, and interpretive power
• Operational and policy-relevant applications of XAI in climate adaptation, mitigation, and risk assessment

We encourage interdisciplinary submissions that bridge ML, weather and climate science, software engineering, and human-computer interaction, and that demonstrate real-world impact or translational potential.