Machine learning (ML) use cases for snow have rapidly increased over recent years, with applications to snow modeling, snow remote sensing, and data processing. Snow, including seasonal snow, presents a unique use case for ML frameworks as it is variable over multiple spatial and temporal scales, and current sensors and observation networks present limitations due to clouds, forests, and the need for observations in hard-to-reach places. In this session, we welcome published and in-progress work on applications of ML for snow, whether for dataset development, hydrologic modeling, or snow remote sensing. We also welcome experiments that identify model structures and workflows specific to snow datasets, as well as lessons learned for capacity building for ML for snow. Unlike broader cryosphere or hydrology ML sessions, this session focuses specifically on the unique data characteristics and observational constraints of snow, and prioritizes community knowledge-sharing and capacity building alongside scientific results.

• C - Cryosphere
• IN - Informatics