Calibrating a large-domain land/hydrology process model in the age of AI: the SUMMA CAMELS emulator experiments

Farahani, Mozhgan A.; Wood, Andrew W.; Tang, Guoqiang; Mizukami, Naoki

doi:https://doi.org/10.5194/hess-29-4515-2025

Articles | Volume 29, issue 18

https://doi.org/10.5194/hess-29-4515-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-29-4515-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 29, issue 18

Research article

|

22 Sep 2025

Research article |

| 22 Sep 2025

Calibrating a large-domain land/hydrology process model in the age of AI: the SUMMA CAMELS emulator experiments

Mozhgan A. Farahani, Andrew W. Wood, Guoqiang Tang, and Naoki Mizukami

Data sets

Data for LSE-SUMMA parameter calibration and regionalization paper Mozhgan A. Farahani and Andy Wood https://doi.org/10.5281/zenodo.16422768

M-Earth: The Ensemble Meteorological Dataset for Planet Earth G. Tang et al. https://doi.org/10.20383/102.0547

ERA5-Land hourly data from 1950 to present J. Muñoz Sabater https://doi.org/10.24381/cds.e2161ba

Model code and software

ESCOMP/mizuRoute: v3.0.0 N. Mizukami et al. https://doi.org/10.5281/zenodo.16376407

Short summary

We present a new strategy to calibrate large-domain land/hydrology models over diverse regions. Using the Structure for Unifying Multiple Modeling Alternatives (SUMMA) and mizuRoute models, our approach integrates catchment attributes, parameters, and performance metrics to optimize streamflow simulations. Leveraging advances in machine learning for hydrology, we improve calibration and enable regionalization to ungauged basins, which is valuable for national-scale water security studies.