Structural bias should be addressed before effective parameter learning - Insights from SMAP soil moisture simulations using differentiable process-based models
Differentiable hydrologic models combining neural networks with process-based backbones—fully implemented or approximated by surrogate models—offer highly competitive accuracy and improved interpretability. However, the impacts of surrogate model fide
Authors
- Kathryn Lawson (ORCID: https://orcid.org/0000-0003-0075-7911)
- Jiangtao Liu (ORCID: https://orcid.org/0000-0002-9219-8354)
- Chaopeng Shen (ORCID: https://orcid.org/0000-0002-0685-1901)
- Farshid Rahmani (ORCID: https://orcid.org/0000-0001-9241-7206)
- Peijun Li (ORCID: https://orcid.org/0000-0002-5897-9093)
Institutions
- Pennsylvania State University (US)
Publication Details
- Published
- 2025-09-22
- DOI
- https://doi.org/10.22541/essoar.175855507.72741303/v1
- Primary Topic
- Soil Moisture and Remote Sensing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Energy
- U.S. Army Corps of Engineers