The need for uncertainty: why probabilistic LSTMs are key to improving flood predictions and enabling learned warning rules

Baste, Sanika; Lerch, Sebastian; Klotz, Daniel; Loritz, Ralf

doi:10.5194/hess-30-6339-2026

Articles | Volume 30, issue 20

https://doi.org/10.5194/hess-30-6339-2026

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

https://doi.org/10.5194/hess-30-6339-2026

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

Articles | Volume 30, issue 20

Research article

|

16 Oct 2026

Research article |

| 16 Oct 2026

The need for uncertainty: why probabilistic LSTMs are key to improving flood predictions and enabling learned warning rules

Sanika Baste, Sebastian Lerch, Daniel Klotz, and Ralf Loritz

Data sets

Catchment attributes and hydro-meteorological time series for large-sample studies across hydrologic Switzerland (CAMELS-CH) M. Höge et al. https://doi.org/10.5281/zenodo.7784632

Model code and software

The need for uncertainty: why probabilistic LSTMs are key to improving flood predictions and enabling learned warning rules Sanika Baste https://doi.org/10.5281/zenodo.18385505

Short summary

Probabilistic runoff predictions capture the likelihood of rare, high-stakes events that deterministic models – which predict only the conditional expectation – tend to underestimate. This added information can improve flood warning communication by learning reward-based rules for selecting predictive quantiles suited to specific hydrological and societal contexts.