Published November 2, 2026
| Version v0.1
Software
Open
HydroTuring: a conservation-law benchmark for AI hydrologic models
Authors/Creators
- 1. University of Colorado Boulder
- 2. South China University of Technology
- 3. Department of Electrical Engineering, Columbia University, New York, NY, USA
- 4. Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, China
- 5. Department of Civil and Environmental Engineering (D.I.C.A.), Politecnico di Milano, Milano 20133, Italy
- 6. Independent Researcher
- 7. Laboratory of Catchment Hydrology and Geomorphology, École Polytechnique Fédérale de Lausanne (EPFL), 1951 Sion, Switzerland
- 8. Center for Systems Integration and Sustainability, Department of Fisheries and Wildlife, Michigan State University, East Lansing, MI 48823, USA
- 9. Dalian University of Technology, Dalian, China
- 10. Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu, China
- 11. Indian Institute of Technology Mandi, Mandi, Himachal Pradesh, India
- 12. School of Civil Engineering and Environmental Science, University of Oklahoma, Norman, OK, USA
- 13. State Key Laboratory of Earth Surface Processes and Disaster Risk Reduction, Faculty of Geographical Science, Beijing Normal University, Beijing, China
- 14. University of Illinois Urbana-Champaign
- 15. Institute of Global Environmental Change, Xi'an Jiaotong University, Xi'an 710049, China
- 16. Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA
- 17. School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China
- 18. Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY, USA
Description
HydroTuring tests whether an AI-based hydrologic model conserves mass, energy and momentum, rather than whether it fits a hydrograph. Forcing is generated at run time from a recorded seed, so there is nothing to memorise. Every probe must demonstrably separate a physically exact reference model from models that close the budget by construction, that hide a silent sink, or that reach closure through a degenerate partition.
Notes
Files
Flood-Lab/HydroTuring-v0.1.zip
Additional details
Related works
- Is supplement to
- Software: https://github.com/Flood-Lab/HydroTuring/tree/v0.1 (URL)
Software
- Repository URL
- https://github.com/Flood-Lab/HydroTuring