Checking for non-preferred file/folder path names (may take a long time depending on the number of files/folders) ...

Generalizability of data-driven hydrological models in the European Alps
Authors:
Owners: This resource does not have an owner who is an active HydroShare user. Contact CUAHSI (help@cuahsi.org) to determine if accessing this resource is possible.
Type: Resource
Storage: The size of this resource is 3.8 GB
Created: Oct 24, 2025 at 8:45 a.m. (UTC)
Last updated: Oct 27, 2025 at 2:50 p.m. (UTC)
Citation: See how to cite this resource
Content types: CSV Content 
Sharing Status: Private (Accessible via direct link sharing)
Views: 24
Downloads: 0
+1 Votes: Be the first one to 
 this.
Comments: No comments (yet)

Abstract

This data accompanies the submitted manuscript "Hybrid models generalize better to warmer climate conditions than process-based and purely data-driven models" by Bohl et al.
The dataset provides daily streamflow observations and catchment-averaged meteorological data from E-OBS v29.0e, and static catchment attributes for a large sample of 918 catchments in Central Europe. It also provides the code used to setup and run the hydrological models.

The study domain covers the European Alps and the lowland regions around them, specifically the four major river basins originating in the Central Alps: the Danube, Rhine, Rhône and Po. It includes catchments in southern Germany (Bavaria and Baden-Württemberg), Austria, Switzerland, and eastern France (Rhône and Rhine basins).

Subject Keywords

Coverage

Spatial

Coordinate System/Geographic Projection:
WGS 84 EPSG:4326
Coordinate Units:
Decimal degrees
Place/Area Name:
European Alps
North Latitude
50.5739°
East Longitude
16.6717°
South Latitude
43.5264°
West Longitude
4.3238°

Temporal

Start Date:
End Date:

Content

README.md

Data and code for the Hybrid models generalize better to warmer climate conditions than process-based and purely data-driven models paper

This folder contains the data, code and model runs for the paper and is structured as follows

  • dataset contains the dataset used to train the models as well as code and some of the raw data used to create the dataset
  • experiments contains the model runs
  • Hy2DL contains the code used to train and regionalize the HBV model and is based on code provided with Espinoza et al. 2025
  • neuralhydrology is a slightly modified version of the Neuralhydrology implementation provided with the paper Espinoza et al. 2025 and was used to train the LSTM and hybrid model

References for Hy2DL and neuralhydrology

Acuña Espinoza, E., Loritz, R., Kratzert, F., Klotz, D., Gauch, M., Álvarez Chaves, M., and Ehret, U.: Analyzing the generalization capabilities of a hybrid hydrological model for extrapolation to extreme events, Hydrol. Earth Syst. Sci., 29, 1277–1294, https://doi.org/10.5194/hess-29-1277-2025, 2025.

How to Cite

Bohl, J. P., Wood, R. R., Götte, J., Brunner, M. (2025). Generalizability of data-driven hydrological models in the European Alps, HydroShare, http://www.hydroshare.org/resource/0e708f4a9f8440c880408221d3fa86b5

This resource is shared under the Creative Commons Attribution CC BY.

 http://creativecommons.org/licenses/by/4.0/
CC-BY

Comments

There are currently no comments

New Comment

required