Articles | Volume 29, issue 4
https://doi.org/10.5194/hess-29-1061-2025
https://doi.org/10.5194/hess-29-1061-2025
Research article
 | Highlight paper
 | 
27 Feb 2025
Research article | Highlight paper |  | 27 Feb 2025

CH-RUN: a deep-learning-based spatially contiguous runoff reconstruction for Switzerland

Basil Kraft, Michael Schirmer, William H. Aeberhard, Massimiliano Zappa, Sonia I. Seneviratne, and Lukas Gudmundsson

Data sets

CH-RUN: Runoff reconstruction for Switzerland (CHRUN_v1) Basil Kraft et al. 20.500.11850/714281

Model code and software

bask0/mach-flow: CH-Run v1.0 Basil Kraft https://doi.org/10.5281/zenodo.14904538

Download
Executive editor
This study integrates deep learning techniques into hydrological modelling to reconstruct runoff data. The extended reconstruction of runoff spanning over six decades (1962-2023) provides an unprecedented data basis to study long-term runoff patterns and trends in Switzerland. The findings spotlight a shift towards less frequent wet years and more frequent dry conditions in Switzerland. This insight is also relevant given the current situation of extreme droughts and floods in Europe.
Short summary
This study reconstructs daily runoff in Switzerland (1962–2023) using a deep-learning model, providing a spatially contiguous dataset on a medium-sized catchment grid. The model outperforms traditional hydrological methods, revealing shifts in Swiss water resources, including more frequent dry years and declining summer runoff. The reconstruction is publicly available.
Share