Gül (2026) CryoSENSE-HK: Explainable Lead-Time Forecasting of ERA5-Land Snow State, Bounded by Station and Physically Based References (Hakkari, Türkiye)

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Water
• Year: 2026
• Date: 2026-09-24
• Authors: Ertuğrul Gül
• DOI: 10.3390/w18192383

Research Groups

• Department of Civil Engineering, Istanbul Technical University
• Department of Geomatics Engineering, Istanbul Technical University
• National Center for Hydrology and Water Resources Management (SHEFAA), Türkiye

Short Summary

This study introduces CryoSENSE-HK, an explainable machine-learning framework that forecasts ERA5-Land snow cover, snow water equivalent, and snowmelt one to thirty days ahead in the semi-arid Cilo-Sat cryosphere of Hakkari Province, Türkiye. The framework reproduces reanalysis data with high accuracy but shows weaker agreement with ground observations.

Objective

• Investigate the feasibility of using machine-learning algorithms for short-term forecasting of snow cover and snowmelt in a sparse ground network region.

Study Configuration

• Spatial Scale: Local (Cilo-Sat cryosphere, Hakkari Province, Türkiye)
• Temporal Scale: Short-term (one to thirty days ahead)

Methodology and Data

• Models used: CryoSENSE-HK (explainable machine-learning framework)
• Data sources: ERA5-Land reanalysis data, ground observations from station records, satellite retrievals

Main Results

• High accuracy in reproducing ERA5-Land snow cover, snow water equivalent, and snowmelt forecasts one to thirty days ahead (coefficients of determination: 0.93, 0.91, and 0.73, respectively)
• Weaker agreement with ground observations, particularly for snow depth and cover
• Reduced monthly emulator of ERA5-Land reanalysis shows weak response to warming (5.4% of snow water equivalent per degree of warming)

Contributions

• Original contribution of an explainable machine-learning framework for short-term forecasting of snow cover and snowmelt in a sparse ground network region
• Highlighted limitations of using reanalysis data for climate sensitivity studies

Funding

• This research was funded by the Scientific and Technological Research Council of Türkiye (TÜBİTAK) under project code 118C011.

Citation

@article{Gül2026CryoSENSEHK,
  author = {Gül, Ertuğrul},
  title = {CryoSENSE-HK: Explainable Lead-Time Forecasting of ERA5-Land Snow State, Bounded by Station and Physically Based References (Hakkari, Türkiye)},
  journal = {Water},
  year = {2026},
  doi = {10.3390/w18192383},
  url = {https://doi.org/10.3390/w18192383}
}