Unveiling the limits of deep learning models in hydrological extrapolation tasks

Baste, Sanika; Klotz, Daniel; Acuña Espinoza, Eduardo; Bardossy, Andras; Loritz, Ralf

doi:https://doi.org/10.5194/hess-29-5871-2025

Articles | Volume 29, issue 21

https://doi.org/10.5194/hess-29-5871-2025

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

https://doi.org/10.5194/hess-29-5871-2025

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

Articles | Volume 29, issue 21

Research article

|

03 Nov 2025

Research article |

| 03 Nov 2025

Unveiling the limits of deep learning models in hydrological extrapolation tasks

Sanika Baste, Daniel Klotz, Eduardo Acuña Espinoza, Andras Bardossy, and Ralf Loritz

Data sets

CAMELS: Catchment Attributes and MEteorology for Large-sample Studies (1.2) A. J. Newman et al. https://doi.org/10.5065/D6MW2F4D

Catchment attributes and hydro-meteorological time series for large-sample studies across hydrologic Switzerland (CAMELS-CH) (0.9) M. Höge et al. https://doi.org/10.5281/zenodo.15025258

Model code and software

Unveiling the Limits of Deep Learning Models in Hydrological Extrapolation Tasks S. Baste https://doi.org/10.5281/zenodo.14771377

Short summary

This study evaluates the extrapolation performance of long short-term memory (LSTM) networks in rainfall–runoff modeling, specifically under extreme precipitation conditions. The findings reveal that the LSTM cannot predict discharge values beyond a theoretical limit and that this limit is well below the extremity of its training data. This behavior results from the LSTM's gating structures rather than saturation of the cell states alone.