Primary Convener:
Luisa Vieira Lucchese, University of Pittsburgh

Convener:
John Gardner, University of North Carolina at Chapel Hill
Dongmei Feng, University of Cincinnati
Admin Husic, Virginia Tech
Shuyu Chang, The Pennsylvania State University

Early Career Convener:
Luisa Vieira Lucchese, University of Pittsburgh

Chair:
John Gardner, University of North Carolina at Chapel Hill
Admin Husic, University of Kansas
Shuyu Chang, The Pennsylvania State University
Luisa Vieira Lucchese, University of Pittsburgh

Machine Learning (ML) is increasingly used in hydrology and water quality research to process and analyze large datasets and draw new insights. This session will explore recent advancements in ML modeling and their applications in large-scale hydrology, including but not limited to streamflow forecasts, sediment and nutrient load estimation, flood extent mapping, water storage change, or any part of the water cycle. Among the possible data sources for large scale ML models are satellite remote sensing datasets, in-situ observations, and reanalysis data. We welcome contributions using any ML model from tree-based to deep learning, as well as explainable artificial intelligence (XAI) and hybrid modeling techniques. We also invite contributions that present new regional, continental, or global datasets generated by or analyzed with the help of ML.

Index Terms
1855 Remote sensing
1871 Surface water quality
1926 Geospatial
1942 Machine learning

Cross-Listed:
IN - Informatics

Suggested Itineraries:
Machine Learning and AI
Open Science and Open Data
Global Impacts‚ Solutions‚ & Policies

Neighborhoods:
3. Earth Covering