Articles | Volume 28, issue 3
https://doi.org/10.5194/hess-28-525-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-28-525-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
08 Feb 2024
Research article |
| 08 Feb 2024
| 08 Feb 2024
On the challenges of global entity-aware deep learning models for groundwater level prediction
Benedikt Heudorfer
CORRESPONDING AUTHOR
Karlsruhe Institute of Technology (KIT), Institute of Applied Geosciences, Kaiserstr. 12, 76131 Karlsruhe, Germany
Tanja Liesch
Karlsruhe Institute of Technology (KIT), Institute of Applied Geosciences, Kaiserstr. 12, 76131 Karlsruhe, Germany
Stefan Broda
Federal Institute for Geosciences and Natural Resources (BGR), Wilhelmstr. 25–30, 13593 Berlin, Germany
Viewed
Total article views: 5,138 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Aug 2023)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 3,877 | 1,158 | 103 | 5,138 | 267 | 118 | 134 |
- HTML: 3,877
- PDF: 1,158
- XML: 103
- Total: 5,138
- Supplement: 267
- BibTeX: 118
- EndNote: 134
Total article views: 4,068 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 08 Feb 2024)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 3,217 | 776 | 75 | 4,068 | 145 | 100 | 120 |
- HTML: 3,217
- PDF: 776
- XML: 75
- Total: 4,068
- Supplement: 145
- BibTeX: 100
- EndNote: 120
Total article views: 1,070 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Aug 2023)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 660 | 382 | 28 | 1,070 | 122 | 18 | 14 |
- HTML: 660
- PDF: 382
- XML: 28
- Total: 1,070
- Supplement: 122
- BibTeX: 18
- EndNote: 14
Viewed (geographical distribution)
Total article views: 5,138 (including HTML, PDF, and XML)
Thereof 4,969 with geography defined
and 169 with unknown origin.
Total article views: 4,068 (including HTML, PDF, and XML)
Thereof 3,934 with geography defined
and 134 with unknown origin.
Total article views: 1,070 (including HTML, PDF, and XML)
Thereof 1,035 with geography defined
and 35 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
22 citations as recorded by crossref.
- Spatial and temporal forecasting of groundwater anomalies in complex aquifer undergoing climate and land use change A. Talib et al. https://doi.org/10.1016/j.jhydrol.2024.131525
- Impact of Climate Change on Groundwater Level Changes: An Evaluation Based on Deep Neural Networks S. Afrifa et al. https://doi.org/10.1155/acis/7641994
- A novel framework for multi-step water level predicting by spatial–temporal deep learning models based on integrated physical models S. Zhang et al. https://doi.org/10.1016/j.jhydrol.2025.133683
- Using Entity-Aware LSTM to Enhance Streamflow Predictions in Transboundary and Large Lake Basins Y. Park et al. https://doi.org/10.3390/hydrology12100261
- Groundwater dynamics clustering and prediction based on grey relational analysis and LSTM model: A case study in Beijing Plain, China Y. Zhou et al. https://doi.org/10.1016/j.ejrh.2024.102011
- Multi-site deep learning for groundwater level prediction across global datasets: toward scalable applications under data scarcity A. Nolte et al. https://doi.org/10.2166/hydro.2025.095
- Is smart sampling worth it? Impact of training data selection on the performance of LSTMs in streamflow prediction B. Heudorfer & R. Loritz https://doi.org/10.2166/nh.2026.119
- Deep learning framework for mapping nitrate pollution in coastal aquifers under land use pressure M. Chahid et al. https://doi.org/10.1038/s41598-025-18996-7
- Deep learning for groundwater level simulation in unconfined aquifers across the contiguous United States: Analyzing simulations at multiple lead times and integrating groundwater signatures K. Boo et al. https://doi.org/10.1016/j.jhydrol.2026.134949
- Assessing groundwater level modelling using a 1-D convolutional neural network (CNN): linking model performances to geospatial and time series features M. Gomez et al. https://doi.org/10.5194/hess-28-4407-2024
- Can deep learning outperform mechanistic modeling of peatland water table dynamics? H. Van Nieuwenhove et al. https://doi.org/10.1088/3049-4753/ae7726
- Enhancing groundwater forecasting through a spatio-temporal feature mixer deep learning model S. Patra & H. Chu https://doi.org/10.1016/j.engappai.2026.115429
- Strategies for incorporating static features into global deep learning models T. Liesch & M. Ohmer https://doi.org/10.5194/hess-30-1877-2026
- Training deep learning models with a multi-station approach and static aquifer attributes for groundwater level simulation: what is the best way to leverage regionalised information? S. Chidepudi et al. https://doi.org/10.5194/hess-29-841-2025
- Mapping the spatial heterogeneity of nitrogen species in road dust through integrated multi-source remote sensing and interpretable machine learning M. Ashraf et al. https://doi.org/10.1016/j.envres.2026.124867
- Never Train a Deep Learning Model on a Single Well? Revisiting Training Strategies for Groundwater Level Prediction M. Ohmer & T. Liesch https://doi.org/10.5194/hess-30-2373-2026
- Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs Y. Cao et al. https://doi.org/10.3390/rs18101622
- Towards a global spatial machine learning model for seasonal groundwater level predictions in Germany S. Kunz et al. https://doi.org/10.5194/hess-29-3405-2025
- Associations between deep learning runoff predictions and hydrogeological conditions in Australia S. Clark & J. Jaffrés https://doi.org/10.1016/j.jhydrol.2024.132569
- Soil moisture as a key predictor for regional groundwater levels: a deep learning study from Brandenburg, Germany M. Eckert & A. Rudolph https://doi.org/10.1088/3033-4942/ae4266
- Direct impact of climate change on groundwater levels in the Iberian Peninsula A. Rouhani et al. https://doi.org/10.1016/j.scitotenv.2025.179009
- GEMS-GER: a machine learning benchmark dataset of long-term groundwater levels in Germany with meteorological forcings and site-specific environmental features M. Ohmer et al. https://doi.org/10.5194/essd-18-77-2026
22 citations as recorded by crossref.
- Spatial and temporal forecasting of groundwater anomalies in complex aquifer undergoing climate and land use change A. Talib et al. https://doi.org/10.1016/j.jhydrol.2024.131525
- Impact of Climate Change on Groundwater Level Changes: An Evaluation Based on Deep Neural Networks S. Afrifa et al. https://doi.org/10.1155/acis/7641994
- A novel framework for multi-step water level predicting by spatial–temporal deep learning models based on integrated physical models S. Zhang et al. https://doi.org/10.1016/j.jhydrol.2025.133683
- Using Entity-Aware LSTM to Enhance Streamflow Predictions in Transboundary and Large Lake Basins Y. Park et al. https://doi.org/10.3390/hydrology12100261
- Groundwater dynamics clustering and prediction based on grey relational analysis and LSTM model: A case study in Beijing Plain, China Y. Zhou et al. https://doi.org/10.1016/j.ejrh.2024.102011
- Multi-site deep learning for groundwater level prediction across global datasets: toward scalable applications under data scarcity A. Nolte et al. https://doi.org/10.2166/hydro.2025.095
- Is smart sampling worth it? Impact of training data selection on the performance of LSTMs in streamflow prediction B. Heudorfer & R. Loritz https://doi.org/10.2166/nh.2026.119
- Deep learning framework for mapping nitrate pollution in coastal aquifers under land use pressure M. Chahid et al. https://doi.org/10.1038/s41598-025-18996-7
- Deep learning for groundwater level simulation in unconfined aquifers across the contiguous United States: Analyzing simulations at multiple lead times and integrating groundwater signatures K. Boo et al. https://doi.org/10.1016/j.jhydrol.2026.134949
- Assessing groundwater level modelling using a 1-D convolutional neural network (CNN): linking model performances to geospatial and time series features M. Gomez et al. https://doi.org/10.5194/hess-28-4407-2024
- Can deep learning outperform mechanistic modeling of peatland water table dynamics? H. Van Nieuwenhove et al. https://doi.org/10.1088/3049-4753/ae7726
- Enhancing groundwater forecasting through a spatio-temporal feature mixer deep learning model S. Patra & H. Chu https://doi.org/10.1016/j.engappai.2026.115429
- Strategies for incorporating static features into global deep learning models T. Liesch & M. Ohmer https://doi.org/10.5194/hess-30-1877-2026
- Training deep learning models with a multi-station approach and static aquifer attributes for groundwater level simulation: what is the best way to leverage regionalised information? S. Chidepudi et al. https://doi.org/10.5194/hess-29-841-2025
- Mapping the spatial heterogeneity of nitrogen species in road dust through integrated multi-source remote sensing and interpretable machine learning M. Ashraf et al. https://doi.org/10.1016/j.envres.2026.124867
- Never Train a Deep Learning Model on a Single Well? Revisiting Training Strategies for Groundwater Level Prediction M. Ohmer & T. Liesch https://doi.org/10.5194/hess-30-2373-2026
- Estimating Regional Groundwater Level by Combining Satellite, Model, and Large-Sample Observations Inputs Y. Cao et al. https://doi.org/10.3390/rs18101622
- Towards a global spatial machine learning model for seasonal groundwater level predictions in Germany S. Kunz et al. https://doi.org/10.5194/hess-29-3405-2025
- Associations between deep learning runoff predictions and hydrogeological conditions in Australia S. Clark & J. Jaffrés https://doi.org/10.1016/j.jhydrol.2024.132569
- Soil moisture as a key predictor for regional groundwater levels: a deep learning study from Brandenburg, Germany M. Eckert & A. Rudolph https://doi.org/10.1088/3033-4942/ae4266
- Direct impact of climate change on groundwater levels in the Iberian Peninsula A. Rouhani et al. https://doi.org/10.1016/j.scitotenv.2025.179009
- GEMS-GER: a machine learning benchmark dataset of long-term groundwater levels in Germany with meteorological forcings and site-specific environmental features M. Ohmer et al. https://doi.org/10.5194/essd-18-77-2026
Saved (final revised paper)
Latest update: 21 Jul 2026
Download
The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.
- Article
(5368 KB) - Full-text XML
- Corrigendum
-
Supplement
(4083 KB) - BibTeX
- EndNote
Short summary
We build a neural network to predict groundwater levels from monitoring wells. We predict all wells at the same time, by learning the differences between wells with static features, making it an entity-aware global model. This works, but we also test different static features and find that the model does not use them to learn exactly how the wells are different, but only to uniquely identify them. As this model class is not actually entity aware, we suggest further steps to make it so.
We build a neural network to predict groundwater levels from monitoring wells. We predict all...
