Validation strategies for deep learning-based groundwater level time series prediction using exogenous meteorological input features

Doll, Fabienne; Liesch, Tanja; Wetzel, Maria; Kunz, Stefan; Broda, Stefan

doi:10.5194/gmd-19-2657-2026

Articles | Volume 19, issue 7

https://doi.org/10.5194/gmd-19-2657-2026

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

https://doi.org/10.5194/gmd-19-2657-2026

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

Articles | Volume 19, issue 7

Methods for assessment of models

|

07 Apr 2026

Methods for assessment of models |

| 07 Apr 2026

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

Data sets

Data and Code to Validation Strategies for Deep Learning-Based Groundwater Level Time Series Prediction Using Exogenous Meteorological Input Features F. Doll et al. https://doi.org/10.5281/zenodo.18467734

Model code and software

Data and Code to Validation Strategies for Deep Learning-Based Groundwater Level Time Series Prediction Using Exogenous Meteorological Input Features F. Doll et al. https://doi.org/10.5281/zenodo.18467734

Short summary

With the growing use of machine learning for groundwater level (GWL) prediction, proper performance estimation is crucial. This study compares three validation strategies—blocked cross-validation (bl-CV), repeated out-of-sample (repOOS), and out-of-sample (OOS)—for 1D-CNN and LSTM models using meteorological inputs. Results show that bl-CV offers the most reliable performance estimates, while OOS is the most uncertain, highlighting the need for careful method selection.