Preprints
https://doi.org/10.5194/egusphere-2024-993
https://doi.org/10.5194/egusphere-2024-993
22 Apr 2024
 | 22 Apr 2024
Status: this preprint is open for discussion.

CH-RUN: A data-driven spatially contiguous runoff monitoring product for Switzerland

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

Abstract. This study presents a data-driven reconstruction of daily runoff that covers the entirety of Switzerland over an extensive period from 1962 to 2023. To this end, we harness the capabilities of deep learning-based models to learn complex runoff-generating processes directly from observations, thereby facilitating efficient large-scale simulation of runoff rates at ungauged locations. By driving the resulting model with gridded temperature and precipitation data available since the 1960s, we provide a spatiotemporally continuous reconstruction of runoff. The efficacy of the developed model is thoroughly assessed through spatiotemporal cross-validation and compared against a distributed hydrological model, a model used operationally in Switzerland.

The developed data-driven model demonstrates not only competitive performance but also notable improvements over traditional hydrological modeling in replicating daily runoff patterns, capturing annual variability, and discerning long-term trends. The resulting long-term reconstruction of runoff is subsequently used to delineate significant shifts in Swiss water resources throughout the past decades. These are characterized by an increased occurrence of dry years, contributing to a negative decadal trend, particularly during the summer months. These insights are pivotal for the understanding and management of water resources, particularly in the context of climate change and environmental conservation. The reconstruction product is made available online.

Furthermore, the reduced data dependency and computational efficiency of our model pave the way for simulating diverse scenarios and conducting comprehensive climate attribution studies. This represents a substantial progression in the field, allowing for the analysis of thousands of scenarios in a time frame significantly shorter than traditional methods.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Basil Kraft, Michael Schirmer, William H. Aeberhard, Massimiliano Zappa, Sonia I. Seneviratne, and Lukas Gudmundsson

Status: open (until 19 Jun 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Basil Kraft, Michael Schirmer, William H. Aeberhard, Massimiliano Zappa, Sonia I. Seneviratne, and Lukas Gudmundsson

Model code and software

CH-RUN: Model code Basil Kraft https://github.com/bask0/mach-flow

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

Viewed

Total article views: 280 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
192 80 8 280 4 4
  • HTML: 192
  • PDF: 80
  • XML: 8
  • Total: 280
  • BibTeX: 4
  • EndNote: 4
Views and downloads (calculated since 22 Apr 2024)
Cumulative views and downloads (calculated since 22 Apr 2024)

Viewed (geographical distribution)

Total article views: 284 (including HTML, PDF, and XML) Thereof 284 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 19 May 2024
Download
Short summary
This study uses deep learning to predict spatially contiguous water runoff in Switzerland from 1962–2023. It outperforms traditional models, requiring less data and computational power. Key findings include increased dry years and summer water scarcity. This method offers significant advancements in water monitoring.