Hydrology and Earth System Sciences
Hydrology and Earth System Sciences
HESS
Articles | Volume 30, issue 7
Articles | Volume 30, issue 7
https://doi.org/10.5194/hess-30-1877-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-30-1877-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 30, issue 7
Research article
 | 
09 Apr 2026
Research article |  | 09 Apr 2026

Strategies for incorporating static features into global deep learning models

Tanja Liesch and Marc Ohmer

Related authors

ALPAKAS: Alpine hydrographs and catchment attributes for karst springs
Felix Joger, Pauline Thinius, Zhao Chen, Andreas Hartmann, Nico Goldscheider, Tanja Liesch, Gerhard Schubert, and Stefan Broda
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2026-707,https://doi.org/10.5194/essd-2026-707, 2026
Preprint under review for ESSD
Short summary
High-Resolution Karst Spring Discharge Datasets of the Euro-Mediterranean Mountain Regions
Süleyman Selim Çallı, Kübra Özdemir Çallı, Brahim Akdim, Bruno Arfib, Aleksey Benderev, Sandra Beranger, Avi Burg, Onur Can, Jean-Baptiste Charlier, Mehmet Çelik, Arda Melih Çetin, Fehdi Chemseddine, Miroslava Deliyska, Lucio Di Matteo, Marco Dionigi, Romeo Eftimi, Jutta Eybl, Davide Fronzi, Nico Goldscheider, Ergin Gökkaya, Jorge Jodar, Herve Jourde, Eva Kaminsky, Konstantina Katsanou, Alireza Kavousi, Melike Kaya, David Labat, Tanja Liesch, Peter Malik, Christian Massari, Cyril Mayaud, Naomi Mazzilli, Pavel Pracny, Natasa Ravbar, Nathan Rispal, Simon Seelig, Vianney Sivelle, Marc Steinmann, Daniela Valigi, Gerfried Winkler, Ahmet Kemal Yahşi, and Andreas Hartmann
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2026-281,https://doi.org/10.5194/essd-2026-281, 2026
Revised manuscript under review for ESSD
Short summary
Never Train a Deep Learning Model on a Single Well? Revisiting Training Strategies for Groundwater Level Prediction
Marc Ohmer and Tanja Liesch
Hydrol. Earth Syst. Sci., 30, 2373–2394, https://doi.org/10.5194/hess-30-2373-2026,https://doi.org/10.5194/hess-30-2373-2026, 2026
Short summary
Validation strategies for deep learning-based groundwater level time series prediction using exogenous meteorological input features
Fabienne Doll, Tanja Liesch, Maria Wetzel, Stefan Kunz, and Stefan Broda
Geosci. Model Dev., 19, 2657–2675, https://doi.org/10.5194/gmd-19-2657-2026,https://doi.org/10.5194/gmd-19-2657-2026, 2026
Short summary
GEMS-GER: a machine learning benchmark dataset of long-term groundwater levels in Germany with meteorological forcings and site-specific environmental features
Marc Ohmer, Tanja Liesch, Bastian Habbel, Benedikt Heudorfer, Mariana Gomez, Patrick Clos, Maximilian Nölscher, and Stefan Broda
Earth Syst. Sci. Data, 18, 77–95, https://doi.org/10.5194/essd-18-77-2026,https://doi.org/10.5194/essd-18-77-2026, 2026
Short summary
More articles (7)

Cited articles

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zhen, X.: Tensorflow: A system for large-scale machine learning, in: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), 265–283, 2016. a
Arsenault, R., Martel, J.-L., Brunet, F., Brissette, F., and Mai, J.: Continuous streamflow prediction in ungauged basins: long short-term memory neural networks clearly outperform traditional hydrological models, Hydrol. Earth Syst. Sci., 27, 139–157, https://doi.org/10.5194/hess-27-139-2023, 2023. a
Chollet, F. and contributors: Keras, https://github.com/fchollet/keras (last access: 7 April 2026), 2015. a
Clark, S. R., Pagendam, D., and Ryan, L.: Forecasting Multiple Groundwater Time Series with Local and Global Deep Learning Networks, Int. J. Env. Res. Pub. He., 19, 5091, https://doi.org/10.3390/ijerph19095091, 2022. a
DWD-CDC: Daily grids of evapotranspiration, soil moisture, soil temperature, https://opendata.dwd.de/climate_environment/CDC/grids_germany/daily/ (last access: 7 April 2026), 2024. a
More articles (33)
Download
Short summary
We studied how to add site information to deep learning models that predict groundwater levels at many wells at once. Using data from Germany, we compared four simple ways to combine time varying weather with time invariant site characteristics. All methods gave similar average accuracy. Repeating site data at each time step was slightly best but used more computer power. The informativeness of site information mattered more than the method, guiding future model design.
Read more
Share