2026 Workshop on Machine Learning for Land and Hydrology

Foundations of machine learning for hydrology and land-surface modelling, including fully data-driven, hybrid, and physics-informed approaches.

Global and regional ML-based forecasting systems for streamflow, floods, soil moisture, snow, and land-surface processes, with an emphasis on scalability and operational use.

Applications and case studies demonstrating ML performance across climates, basins, and forecasting horizons.

Evaluation, datasets, and benchmarking, including standardised datasets, metrics for extremes, uncertainty quantification, and robustness under non-stationarity.

Emerging and advanced methods, including transfer learning, generalisation to data-poor regions, and next-generation forecasting concepts.

Responsible AI in Hydrology: Addressing data sovereignty, algorithmic bias in disaster response, and ensuring equitable model performance across transboundary and data-poor regions.