Articles | Volume 29, issue 13
https://doi.org/10.5194/hess-29-2811-2025
© Author(s) 2025. 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-29-2811-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
04 Jul 2025
Research article |
| 04 Jul 2025
| 04 Jul 2025
Assessing the adequacy of traditional hydrological models for climate change impact studies: a case for long short-term memory (LSTM) neural networks
Jean-Luc Martel
CORRESPONDING AUTHOR
Hydrology, Climate and Climate Change (HC3) laboratory, École de technologie supérieure, Montréal, H3C 1K3, Canada
François Brissette
Hydrology, Climate and Climate Change (HC3) laboratory, École de technologie supérieure, Montréal, H3C 1K3, Canada
Richard Arsenault
Hydrology, Climate and Climate Change (HC3) laboratory, École de technologie supérieure, Montréal, H3C 1K3, Canada
Richard Turcotte
Direction principale de l'expertise hydrique (DPEH), Ministère de l'Environnement et de la Lutte contre les changements climatiques, de la Faune et des Parcs (MELCCFP), Québec, G1R 5V7, Canada
Mariana Castañeda-Gonzalez
Hydrology, Climate and Climate Change (HC3) laboratory, École de technologie supérieure, Montréal, H3C 1K3, Canada
William Armstrong
Hydrology, Climate and Climate Change (HC3) laboratory, École de technologie supérieure, Montréal, H3C 1K3, Canada
Edouard Mailhot
Direction principale de l'expertise hydrique (DPEH), Ministère de l'Environnement et de la Lutte contre les changements climatiques, de la Faune et des Parcs (MELCCFP), Québec, G1R 5V7, Canada
Jasmine Pelletier-Dumont
Direction principale de l'expertise hydrique (DPEH), Ministère de l'Environnement et de la Lutte contre les changements climatiques, de la Faune et des Parcs (MELCCFP), Québec, G1R 5V7, Canada
Gabriel Rondeau-Genesse
Ouranos, Montréal, H3A 1B9, Canada
Louis-Philippe Caron
Ouranos, Montréal, H3A 1B9, Canada
Viewed
Total article views: 7,801 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 05 Aug 2024)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 4,486 | 1,755 | 1,560 | 7,801 | 416 | 203 | 226 |
- HTML: 4,486
- PDF: 1,755
- XML: 1,560
- Total: 7,801
- Supplement: 416
- BibTeX: 203
- EndNote: 226
Total article views: 2,364 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 04 Jul 2025)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 1,747 | 492 | 125 | 2,364 | 120 | 92 | 92 |
- HTML: 1,747
- PDF: 492
- XML: 125
- Total: 2,364
- Supplement: 120
- BibTeX: 92
- EndNote: 92
Total article views: 5,437 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 05 Aug 2024)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,739 | 1,263 | 1,435 | 5,437 | 296 | 111 | 134 |
- HTML: 2,739
- PDF: 1,263
- XML: 1,435
- Total: 5,437
- Supplement: 296
- BibTeX: 111
- EndNote: 134
Viewed (geographical distribution)
Total article views: 7,801 (including HTML, PDF, and XML)
Thereof 7,719 with geography defined
and 82 with unknown origin.
Total article views: 2,364 (including HTML, PDF, and XML)
Thereof 2,297 with geography defined
and 67 with unknown origin.
Total article views: 5,437 (including HTML, PDF, and XML)
Thereof 5,422 with geography defined
and 15 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
12 citations as recorded by crossref.
- Event-based training data thresholds for BiLSTM versus Xinanjiang models: Insights from the applications of 19 Chinese catchments Y. Li et al. https://doi.org/10.1016/j.ejrh.2026.103299
- Assessing temporal and spatial generalization of LSTMs for streamflow modeling in French watersheds with and without European training data M. Puche et al. https://doi.org/10.1016/j.ejrh.2025.103022
- Fusing dynamic physical constraints with PINN-xLSTM to enhance accuracy and physical consistency in runoff prediction under extreme hydrological events Y. Yang et al. https://doi.org/10.1016/j.jhydrol.2026.135310
- Comparison of LSTM and conceptual hydrological models for runoff simulation under changing climatic conditions in Iran A. Jahanshahi & M. Booij https://doi.org/10.1016/j.jaridenv.2026.105679
- Multi-Objective Hyperparameter Optimization Improves the Interpretability of LSTM Rainfall–Runoff Models Q. Tan et al. https://doi.org/10.3390/hydrology13080218
- On the improved reconstruction of GRACE-TWSA for assessing droughts and their governing factors in a dam-regulated region P. Bhunia & . Abhishek https://doi.org/10.1016/j.pce.2026.104765
- A Robust Calibration and Evaluation Framework for Dynamic Catchment Characteristics in Hydrological Modeling T. Lan et al. https://doi.org/10.5194/hess-30-2455-2026
- How much historical data do we need? The role of data recency and training period length in LSTM-based rainfall-runoff modeling Q. Yu & B. Tolson https://doi.org/10.1016/j.jhydrol.2026.135046
- Climate-aware natural hazard modelling in data-scarce regions: a structured review of GIS, remote sensing, and artificial intelligence C. EL KIHAL et al. https://doi.org/10.1007/s12517-026-12586-1
- Hybrid models generalize better to warmer climate conditions than process-based and purely data-driven models J. Bohl et al. https://doi.org/10.5194/hess-30-4667-2026
- Learning groundwater dynamics across heterogeneous aquifers: A clustering-integrated spatiotemporal deep learning framework S. Ho et al. https://doi.org/10.1016/j.ejrh.2026.103770
- Strategies for incorporating static features into global deep learning models T. Liesch & M. Ohmer https://doi.org/10.5194/hess-30-1877-2026
12 citations as recorded by crossref.
- Event-based training data thresholds for BiLSTM versus Xinanjiang models: Insights from the applications of 19 Chinese catchments Y. Li et al. https://doi.org/10.1016/j.ejrh.2026.103299
- Assessing temporal and spatial generalization of LSTMs for streamflow modeling in French watersheds with and without European training data M. Puche et al. https://doi.org/10.1016/j.ejrh.2025.103022
- Fusing dynamic physical constraints with PINN-xLSTM to enhance accuracy and physical consistency in runoff prediction under extreme hydrological events Y. Yang et al. https://doi.org/10.1016/j.jhydrol.2026.135310
- Comparison of LSTM and conceptual hydrological models for runoff simulation under changing climatic conditions in Iran A. Jahanshahi & M. Booij https://doi.org/10.1016/j.jaridenv.2026.105679
- Multi-Objective Hyperparameter Optimization Improves the Interpretability of LSTM Rainfall–Runoff Models Q. Tan et al. https://doi.org/10.3390/hydrology13080218
- On the improved reconstruction of GRACE-TWSA for assessing droughts and their governing factors in a dam-regulated region P. Bhunia & . Abhishek https://doi.org/10.1016/j.pce.2026.104765
- A Robust Calibration and Evaluation Framework for Dynamic Catchment Characteristics in Hydrological Modeling T. Lan et al. https://doi.org/10.5194/hess-30-2455-2026
- How much historical data do we need? The role of data recency and training period length in LSTM-based rainfall-runoff modeling Q. Yu & B. Tolson https://doi.org/10.1016/j.jhydrol.2026.135046
- Climate-aware natural hazard modelling in data-scarce regions: a structured review of GIS, remote sensing, and artificial intelligence C. EL KIHAL et al. https://doi.org/10.1007/s12517-026-12586-1
- Hybrid models generalize better to warmer climate conditions than process-based and purely data-driven models J. Bohl et al. https://doi.org/10.5194/hess-30-4667-2026
- Learning groundwater dynamics across heterogeneous aquifers: A clustering-integrated spatiotemporal deep learning framework S. Ho et al. https://doi.org/10.1016/j.ejrh.2026.103770
- Strategies for incorporating static features into global deep learning models T. Liesch & M. Ohmer https://doi.org/10.5194/hess-30-1877-2026
Saved (final revised paper)
Latest update: 08 Sep 2026
Short summary
This study compares long short-term memory (LSTM) neural networks with traditional hydrological models to predict future streamflow under climate change. Using data from 148 catchments, it finds that LSTM models, which learn from extensive data sequences, perform differently and often better than traditional hydrological models. The continental LSTM model, which includes data from diverse climate zones, is particularly effective for understanding climate impacts on water resources.
This study compares long short-term memory (LSTM) neural networks with traditional hydrological...
