When physics gets in the way: an entropy-based evaluation of conceptual constraints in hybrid hydrological models

Álvarez Chaves, Manuel; Acuña Espinoza, Eduardo; Ehret, Uwe; Guthke, Anneli

doi:10.5194/hess-30-629-2026

Articles | Volume 30, issue 3

https://doi.org/10.5194/hess-30-629-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-30-629-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 30, issue 3

Research article

|

04 Feb 2026

Research article |

| 04 Feb 2026

When physics gets in the way: an entropy-based evaluation of conceptual constraints in hybrid hydrological models

Manuel Álvarez Chaves, Eduardo Acuña Espinoza, Uwe Ehret, and Anneli Guthke

Data sets

Catchment attributes and hydro-meteorological timeseries for 671 catchments across Great Britain (CAMELS-GB) G. Coxon et al. https://doi.org/10.5285/8344e4f3-d2ea-44f5-8afa-86d2987543a9

Replication Data for: An entropy-based evaluation of conceptual constraints in hybrid hydrological models M. Álvarez et al. https://doi.org/10.18419/DARUS-4920

Model code and software

Hy2DL: Hybrid Hydrological modeling using Deep Learning methods E. Acuna et al. https://doi.org/10.5281/zenodo.17251944

UNITE Toolbox M. Álvarez et al. https://doi.org/10.18419/DARUS-4188

Short summary

This study evaluates hybrid hydrological models combining physics-based and data-driven components, using Information Theory to measure their relative contributions. When testing conceptual models with Long Short-Term Memory (LSTM) networks that adjust parameters over time, we found performance primarily comes from the data-driven component, with physics constraints adding minimal value. We propose a quantitative tool to analyse this behaviour and suggest a workflow for diagnosing hybrid models.