Articles | Volume 29, issue 19
https://doi.org/10.5194/hess-29-4951-2025
© 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-29-4951-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Exploring the ability of LSTM-based hydrological models to simulate streamflow time series for flood frequency analysis
Jean-Luc Martel
CORRESPONDING AUTHOR
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
François Brissette
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
Simon Lachance-Cloutier
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
Related authors
Frédéric Talbot, Simon Ricard, Guillaume Drolet, Annie Poulin, Jean-Luc Martel, Richard Arsenault, and Jean-Daniel Sylvain
EGUsphere, https://doi.org/10.5194/egusphere-2025-4450, https://doi.org/10.5194/egusphere-2025-4450, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
This study compares three hydrological modeling approaches for assessing climate change impacts on water systems. We evaluate the conventional method alongside a fully- and semi-asynchronous methods, which excels in capturing extreme events but faces challenges with event timing. The results highlight the potential of the semi-asynchronous method as an innovative and robust tool for hydrological modeling under climate change.
Jean-Luc Martel, François Brissette, Richard Arsenault, Richard Turcotte, Mariana Castañeda-Gonzalez, William Armstrong, Edouard Mailhot, Jasmine Pelletier-Dumont, Gabriel Rondeau-Genesse, and Louis-Philippe Caron
Hydrol. Earth Syst. Sci., 29, 2811–2836, https://doi.org/10.5194/hess-29-2811-2025, https://doi.org/10.5194/hess-29-2811-2025, 2025
Short summary
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.
Frédéric Talbot, Simon Ricard, Jean-Daniel Sylvain, Guillaume Drolet, Annie Poulin, Jean-Luc Martel, and Richard Arsenault
EGUsphere, https://doi.org/10.5194/egusphere-2024-3037, https://doi.org/10.5194/egusphere-2024-3037, 2024
Preprint archived
Short summary
Short summary
This study compares two hydrological modeling approaches for assessing climate change impacts on water systems. We evaluate the conventional method alongside the asynchronous method, which excels in capturing extreme events but faces challenges with event timing. Our findings suggest that a semi-asynchronous approach, blending the strengths of both methods, could offer better results. This research provides key insights for supporting sustainable resource planning in a changing climate.
Mehrad Rahimpour Asenjan, Francois Brissette, Richard Arsenault, and Jean-Luc Martel
EGUsphere, https://doi.org/10.5194/egusphere-2024-1183, https://doi.org/10.5194/egusphere-2024-1183, 2024
Preprint archived
Short summary
Short summary
Our study examines how combining climate models impacts future streamflow predictions, crucial for understanding climate change. Comparing six methods across 3,107 North American catchments, we found unequal weighting significantly improves rainfall and temperature projections. However, for streamflow, both equal and unequal weighting perform similarly with bias correction. Our findings underscore the need to carefully select weighting methods and correct biases for accurate climate projections.
Mehrad Rahimpour Asenjan, Francois Brissette, Jean-Luc Martel, and Richard Arsenault
Hydrol. Earth Syst. Sci., 27, 4355–4367, https://doi.org/10.5194/hess-27-4355-2023, https://doi.org/10.5194/hess-27-4355-2023, 2023
Short summary
Short summary
Climate models are central to climate change impact studies. Some models project a future deemed too hot by many. We looked at how including hot models may skew the result of impact studies. Applied to hydrology, this study shows that hot models do not systematically produce hydrological outliers.
Richard Arsenault, Jean-Luc Martel, Frédéric Brunet, François Brissette, and Juliane Mai
Hydrol. Earth Syst. Sci., 27, 139–157, https://doi.org/10.5194/hess-27-139-2023, https://doi.org/10.5194/hess-27-139-2023, 2023
Short summary
Short summary
Predicting flow in rivers where no observation records are available is a daunting task. For decades, hydrological models were set up on these gauges, and their parameters were estimated based on the hydrological response of similar or nearby catchments where records exist. New developments in machine learning have now made it possible to estimate flows at ungauged locations more precisely than with hydrological models. This study confirms the performance superiority of machine learning models.
Gabriel Rondeau-Genesse, Louis-Philippe Caron, Kristelle Audet, Laurent Da Silva, Daniel Tarte, Rachel Parent, Élise Comeau, and Dominic Matte
Hydrol. Earth Syst. Sci., 29, 4893–4912, https://doi.org/10.5194/hess-29-4893-2025, https://doi.org/10.5194/hess-29-4893-2025, 2025
Short summary
Short summary
The 2021 drought in Quebec showcased the province’s potential vulnerability. This study uses a storyline approach to explore the impacts of future extreme droughts under +2 °C and +3 °C global warming scenarios. Results show that future droughts similar to that of 2021 could worsen significantly, with water levels dropping for longer periods and impacting ecosystems and human activities.
Frédéric Talbot, Simon Ricard, Guillaume Drolet, Annie Poulin, Jean-Luc Martel, Richard Arsenault, and Jean-Daniel Sylvain
EGUsphere, https://doi.org/10.5194/egusphere-2025-4450, https://doi.org/10.5194/egusphere-2025-4450, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
This study compares three hydrological modeling approaches for assessing climate change impacts on water systems. We evaluate the conventional method alongside a fully- and semi-asynchronous methods, which excels in capturing extreme events but faces challenges with event timing. The results highlight the potential of the semi-asynchronous method as an innovative and robust tool for hydrological modeling under climate change.
Behmard Sabzipour, Philippe Lucas-Picher, Richard Turcotte, and Gabriel Rondeau-Genesse
EGUsphere, https://doi.org/10.5194/egusphere-2025-3436, https://doi.org/10.5194/egusphere-2025-3436, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
Quebec, Canada is experiencing more frequent and intense rainfall events during the warm seasons, a trend expected to increase due to climate change. This raises the risk of more frequent and severe flooding in urban areas. To better understand extreme rainfall and the resulting floods, this study evaluates, for the first time in Canada, the advantages of using high-resolution climate model outputs. We then assess whether these data can improve peak flow simulations using a hydrological model.
Jean-Luc Martel, François Brissette, Richard Arsenault, Richard Turcotte, Mariana Castañeda-Gonzalez, William Armstrong, Edouard Mailhot, Jasmine Pelletier-Dumont, Gabriel Rondeau-Genesse, and Louis-Philippe Caron
Hydrol. Earth Syst. Sci., 29, 2811–2836, https://doi.org/10.5194/hess-29-2811-2025, https://doi.org/10.5194/hess-29-2811-2025, 2025
Short summary
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.
Malcolm J. Roberts, Kevin A. Reed, Qing Bao, Joseph J. Barsugli, Suzana J. Camargo, Louis-Philippe Caron, Ping Chang, Cheng-Ta Chen, Hannah M. Christensen, Gokhan Danabasoglu, Ivy Frenger, Neven S. Fučkar, Shabeh ul Hasson, Helene T. Hewitt, Huanping Huang, Daehyun Kim, Chihiro Kodama, Michael Lai, Lai-Yung Ruby Leung, Ryo Mizuta, Paulo Nobre, Pablo Ortega, Dominique Paquin, Christopher D. Roberts, Enrico Scoccimarro, Jon Seddon, Anne Marie Treguier, Chia-Ying Tu, Paul A. Ullrich, Pier Luigi Vidale, Michael F. Wehner, Colin M. Zarzycki, Bosong Zhang, Wei Zhang, and Ming Zhao
Geosci. Model Dev., 18, 1307–1332, https://doi.org/10.5194/gmd-18-1307-2025, https://doi.org/10.5194/gmd-18-1307-2025, 2025
Short summary
Short summary
HighResMIP2 is a model intercomparison project focusing on high-resolution global climate models, that is, those with grid spacings of 25 km or less in the atmosphere and ocean, using simulations of decades to a century in length. We are proposing an update of our simulation protocol to make the models more applicable to key questions for climate variability and hazard in present-day and future projections and to build links with other communities to provide more robust climate information.
Frédéric Talbot, Jean-Daniel Sylvain, Guillaume Drolet, Annie Poulin, and Richard Arsenault
EGUsphere, https://doi.org/10.5194/egusphere-2024-3353, https://doi.org/10.5194/egusphere-2024-3353, 2024
Short summary
Short summary
This research explores different modelling approaches within a distributed and physically based hydrological model, emphasizing configurations that integrate groundwater recharge and dynamics. The study demonstrates that precise adjustments in model calibration can enhance the accuracy and representation of hydrological variables, which are crucial for effective water management and climate change adaptation strategies.
Frédéric Talbot, Simon Ricard, Jean-Daniel Sylvain, Guillaume Drolet, Annie Poulin, Jean-Luc Martel, and Richard Arsenault
EGUsphere, https://doi.org/10.5194/egusphere-2024-3037, https://doi.org/10.5194/egusphere-2024-3037, 2024
Preprint archived
Short summary
Short summary
This study compares two hydrological modeling approaches for assessing climate change impacts on water systems. We evaluate the conventional method alongside the asynchronous method, which excels in capturing extreme events but faces challenges with event timing. Our findings suggest that a semi-asynchronous approach, blending the strengths of both methods, could offer better results. This research provides key insights for supporting sustainable resource planning in a changing climate.
Mehrad Rahimpour Asenjan, Francois Brissette, Richard Arsenault, and Jean-Luc Martel
EGUsphere, https://doi.org/10.5194/egusphere-2024-1183, https://doi.org/10.5194/egusphere-2024-1183, 2024
Preprint archived
Short summary
Short summary
Our study examines how combining climate models impacts future streamflow predictions, crucial for understanding climate change. Comparing six methods across 3,107 North American catchments, we found unequal weighting significantly improves rainfall and temperature projections. However, for streamflow, both equal and unequal weighting perform similarly with bias correction. Our findings underscore the need to carefully select weighting methods and correct biases for accurate climate projections.
Mehrad Rahimpour Asenjan, Francois Brissette, Jean-Luc Martel, and Richard Arsenault
Hydrol. Earth Syst. Sci., 27, 4355–4367, https://doi.org/10.5194/hess-27-4355-2023, https://doi.org/10.5194/hess-27-4355-2023, 2023
Short summary
Short summary
Climate models are central to climate change impact studies. Some models project a future deemed too hot by many. We looked at how including hot models may skew the result of impact studies. Applied to hydrology, this study shows that hot models do not systematically produce hydrological outliers.
Richard Arsenault, Jean-Luc Martel, Frédéric Brunet, François Brissette, and Juliane Mai
Hydrol. Earth Syst. Sci., 27, 139–157, https://doi.org/10.5194/hess-27-139-2023, https://doi.org/10.5194/hess-27-139-2023, 2023
Short summary
Short summary
Predicting flow in rivers where no observation records are available is a daunting task. For decades, hydrological models were set up on these gauges, and their parameters were estimated based on the hydrological response of similar or nearby catchments where records exist. New developments in machine learning have now made it possible to estimate flows at ungauged locations more precisely than with hydrological models. This study confirms the performance superiority of machine learning models.
Jean Odry, Marie-Amélie Boucher, Simon Lachance-Cloutier, Richard Turcotte, and Pierre-Yves St-Louis
The Cryosphere, 16, 3489–3506, https://doi.org/10.5194/tc-16-3489-2022, https://doi.org/10.5194/tc-16-3489-2022, 2022
Short summary
Short summary
The research deals with the assimilation of in-situ local snow observations in a large-scale spatialized snow modeling framework over the province of Quebec (eastern Canada). The methodology is based on proposing multiple spatialized snow scenarios using the snow model and weighting them according to the available observations. The paper especially focuses on the spatial coherence of the snow scenario proposed in the framework.
Juliane Mai, Hongren Shen, Bryan A. Tolson, Étienne Gaborit, Richard Arsenault, James R. Craig, Vincent Fortin, Lauren M. Fry, Martin Gauch, Daniel Klotz, Frederik Kratzert, Nicole O'Brien, Daniel G. Princz, Sinan Rasiya Koya, Tirthankar Roy, Frank Seglenieks, Narayan K. Shrestha, André G. T. Temgoua, Vincent Vionnet, and Jonathan W. Waddell
Hydrol. Earth Syst. Sci., 26, 3537–3572, https://doi.org/10.5194/hess-26-3537-2022, https://doi.org/10.5194/hess-26-3537-2022, 2022
Short summary
Short summary
Model intercomparison studies are carried out to test various models and compare the quality of their outputs over the same domain. In this study, 13 diverse model setups using the same input data are evaluated over the Great Lakes region. Various model outputs – such as streamflow, evaporation, soil moisture, and amount of snow on the ground – are compared using standardized methods and metrics. The basin-wise model outputs and observations are made available through an interactive website.
Mostafa Tarek, François Brissette, and Richard Arsenault
Hydrol. Earth Syst. Sci., 25, 3331–3350, https://doi.org/10.5194/hess-25-3331-2021, https://doi.org/10.5194/hess-25-3331-2021, 2021
Short summary
Short summary
It is not known how much uncertainty the choice of a reference data set may bring to impact studies. This study compares precipitation and temperature data sets to evaluate the uncertainty contribution to the results of climate change studies. Results show that all data sets provide good streamflow simulations over the reference period. The reference data sets also provided uncertainty that was equal to or larger than that related to general circulation models over most of the catchments.
Cited articles
Apel, H., Thieken, A. H., Merz, B., and Blöschl, G.: Flood risk assessment and associated uncertainty, Nat. Hazards Earth Syst. Sci., 4, 295–308, https://doi.org/10.5194/nhess-4-295-2004, 2004.
Arsenault, R. and Brissette, F. P.: Continuous streamflow prediction in ungauged basins: The effects of equifinality and parameter set selection on uncertainty in regionalization approaches, Water Resour. Res., 50, 6135–6153, https://doi.org/10.1002/2013WR014898, 2014.
Arsenault, R., Essou, G. R. C., and Brissette, F. P.: Improving hydrological model simulations with combined multi-input and multimodel averaging frameworks, J. Hydrol. Eng., 22, 04016066, https://doi.org/10.1061/(ASCE)HE.1943-5584.0001489, 2017.
Arsenault, R., Brissette, F., and Martel, J.-L.: The hazards of split-sample validation in hydrological model calibration, J. Hydrol., 566, 346–362, https://doi.org/10.1016/j.jhydrol.2018.09.027, 2018.
Arsenault, R., Breton-Dufour, M., Poulin, A., Dallaire, G., and Romero-Lopez, R.: Streamflow prediction in ungauged basins: analysis of regionalization methods in a hydrologically heterogeneous region of Mexico, Hydrol. Sci. J., 64, 1297–1311, https://doi.org/10.1080/02626667.2019.1639716, 2019.
Arsenault, R., Brissette, F., Martel, J.-L., Troin, M., Lévesque, G., Davidson-Chaput, J., Castañeda Gonzalez, M., Ameli, A., and Poulin, A.: A comprehensive, multisource database for hydrometeorological modeling of 14,425 North American watersheds [data set], Scientific Data, 7, 243, https://doi.org/10.1038/s41597-020-00583-2, 2020a.
Arsenault, R., Brissette, F., Martel, J. L., Troin, M., Lévesque, G., Davidson-Chaput, J., Castañeda Gonzalez, M., Ameli, A., and Poulin, A.: HYSETS - A 14425 watershed Hydrometeorological Sandbox over North America [data set], https://doi.org/10.17605/OSF.IO/RPC3W, 2020b.
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, 2023a.
Arsenault, R., Huard, D., Martel, J.-L., Troin, M., Mai, J., Brissette, F., Jauvin, C., Vu, L., Craig, J. R., Smith, T. J., Logan, T., Tolson, B. A., Han, M., Gravel, F., and Langlois, S.: The PAVICS-Hydro platform: A virtual laboratory for hydroclimatic modelling and forecasting over North America, Environ. Model. Softw., 168, 105808, https://doi.org/10.1016/j.envsoft.2023.105808, 2023b.
Arsenault, R., Martel, J.-L., and Brissette, F.: LSTM for FFA - codes and data. https://osf.io/zwtnq/ (last access: 8 July 2024), 2024
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology: Artificial neural networks in hydrology. I: Preliminary concepts, J. Hydrol. Eng., 5, 115–123, https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115), 2000.
Ayzel, G. and Heistermann, M.: The effect of calibration data length on the performance of a conceptual hydrological model versus LSTM and GRU: A case study for six basins from the CAMELS dataset, Comput. Geosci., 149, 104708, https://doi.org/10.1016/j.cageo.2021.104708, 2021.
Bergeron, O.: Guide d'utilisation 2016 – Grilles climatiques quotidiennes du Programme de surveillance du climat du Québec, version 1.2, Québec, ministère du Développement durable, de l'Environnement et de la Lutte contre les changements climatiques, Direction du suivi de l'état de l'environnement, 33 pp., https://numerique.banq.qc.ca/patrimoine/details/52327/2545296 (last access: 8 July 2024), 2016.
Castaneda-Gonzalez, M., Poulin, A., Romero-Lopez, R., and Turcotte, R.: Hydrological models weighting for hydrological projections: The impacts on future peak flows, J. Hydrol., 625, 130098, https://doi.org/10.1016/j.jhydrol.2023.130098, 2023.
CEHQ: Hydroclimatic atlas of southern Québec. The impact of climate change on high, low and mean flow regimes for the 2050 horizon, Centre d'expertise hydrique du Québec (CEHQ), 81, https://www.cehq.gouv.qc.ca/hydrometrie/atlas/Atlas_hydroclimatique_2015EN.pdf (last access: 8 July 2024), 2015.
Coles, S., Bawa, J., Trenner, L., and Dorazio, P.: An introduction to statistical modeling of extreme values, Springer, https://doi.org/10.1007/978-1-4471-3675-0, 2001.
Copernicus Climate Change Service, Climate Data Store: ERA5 hourly data on single levels from 1940 to present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS) [data set], https://doi.org/10.24381/cds.adbb2d47, 2023.
Cunnane, C.: Unbiased plotting positions – A review, J. Hydrol., 37, 205–222, https://doi.org/10.1016/0022-1694(78)90017-3, 1978.
Dallaire, G., Poulin, A., Arsenault, R., and Brissette, F.: Uncertainty of potential evapotranspiration modelling in climate change impact studies on low flows in North America, Hydrological Sciences Journal, 66, 689–702, 2021.
Do, H. X., Westra, S., and Leonard, M.: A global-scale investigation of trends in annual maximum streamflow, J. Hydrol., 552, 28–43, https://doi.org/10.1016/j.jhydrol.2017.06.015, 2017.
England Jr., J. F., Cohn, T. A., Faber, B. A., Stedinger, J. R., Thomas Jr., W. O., Veilleux, A. G., Kiang, J. E., and Mason Jr., R. R.: Guidelines for determining flood flow frequency, Bulletin 17C, US Geological Survey1411342232, https://doi.org/10.3133/tm4B5, 2019.
Fang, K., Kifer, D., Lawson, K., Feng, D., and Shen, C.: The data synergy effects of time-series deep learning models in hydrology, Water Resour. Res., 58, e2021WR029583, https://doi.org/10.1029/2021WR029583, 2022.
Feng, D., Fang, K., and Shen, C.: Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales, Water Resour. Res., 56, e2019WR026793, https://doi.org/10.1029/2019WR026793, 2020.
Feng, D., Beck, H., Lawson, K., and Shen, C.: The suitability of differentiable, physics-informed machine learning hydrologic models for ungauged regions and climate change impact assessment, Hydrol. Earth Syst. Sci., 27, 2357–2373, https://doi.org/10.5194/hess-27-2357-2023, 2023.
Fortin, V.: Le modèle météo-apport HSAMI: historique, théorie et application, Technical report from Institut de Recherche d'Hydro-Québec, 68 pp., 2000.
Fortin, J.-P., Turcotte, R., Massicotte, S., Moussa, R., Fitzback, J., and Villeneuve, J.-P.: Distributed watershed model compatible with remote sensing and GIS data. II: Application to Chaudière watershed, J. Hydrol. Eng., 6, 100–108, https://doi.org/10.1061/(ASCE)1084-0699(2001)6:2(100), 2001a.
Fortin, J.-P., Turcotte, R., Massicotte, S., Moussa, R., Fitzback, J., and Villeneuve, J.-P.: Distributed watershed model compatible with remote sensing and GIS data. I: Description of model, J. Hydrol. Eng., 6, 91–99, https://doi.org/10.1061/(ASCE)1084-0699(2001)6:2(91), 2001b.
Frame, J. M., Kratzert, F., Gupta, H. V., Ullrich, P., and Nearing, G. S.: On strictly enforced mass conservation constraints for modelling the Rainfall-Runoff process, Hydrol. Process., 37, e14847, https://doi.org/10.1002/hyp.14847, 2023.
Gupta, H. V., Kling, H., Yilmaz, K. K., and Martinez, G. F.: Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling, J. Hydrol., 377, 80–91, https://doi.org/10.1016/j.jhydrol.2009.08.003, 2009.
Hao, R. and Bai, Z.: Comparative study for daily streamflow simulation with different machine learning methods, Water, 15, 1179, https://doi.org/10.3390/w15061179, 2023.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., De Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.-N.: The ERA5 global reanalysis, Q. J. Roy. Meteorol. Soc., 146, 1999–2049, https://doi.org/10.1002/qj.3803, 2020.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Hu, L., Nikolopoulos, E. I., Marra, F., and Anagnostou, E. N.: Sensitivity of flood frequency analysis to data record, statistical model, and parameter estimation methods: An evaluation over the contiguous United States, J. Flood Risk Manag., 13, e12580, https://doi.org/10.1111/jfr3.12580, 2020.
Huot, P.-L., Poulin, A., Audet, C., and Alarie, S.: A hybrid optimization approach for efficient calibration of computationally intensive hydrological models, Hydrol. Sci. J., 64, 1204–1222, https://doi.org/10.1080/02626667.2019.1624922, 2019.
In-na, N. and Nyuyen, V.-T.-V.: An unbiased plotting position formula for the general extreme value distribution, J. Hydrol., 106, 193–209, https://doi.org/10.1016/0022-1694(89)90072-3, 1989.
Kling, H., Fuchs, M., and Paulin, M.: Runoff conditions in the upper Danube basin under an ensemble of climate change scenarios, J. Hydrol., 424–425, 264–277, https://doi.org/10.1016/j.jhydrol.2012.01.011, 2012.
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018.
Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A. K., Hochreiter, S., and Nearing, G. S.: Toward improved predictions in ungauged basins: Exploiting the power of machine learning, Water Resour. Res., 55, 11344–11354, https://doi.org/10.1029/2019WR026065, 2019a.
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019b.
Kratzert, F., Klotz, D., Hochreiter, S., and Nearing, G. S.: A note on leveraging synergy in multiple meteorological data sets with deep learning for rainfall–runoff modeling, Hydrol. Earth Syst. Sci., 25, 2685–2703, https://doi.org/10.5194/hess-25-2685-2021, 2021.
Kratzert, F., Gauch, M., Klotz, D., and Nearing, G.: HESS Opinions: Never train a Long Short-Term Memory (LSTM) network on a single basin, Hydrol. Earth Syst. Sci., 28, 4187–4201, https://doi.org/10.5194/hess-28-4187-2024, 2024.
Laio, F., Di Baldassarre, G., and Montanari, A.: Model selection techniques for the frequency analysis of hydrological extremes, Water Resour. Res., 45, https://doi.org/10.1029/2007WR006666, 2009.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Li, P., Zhang, J., and Krebs, P.: Prediction of flow based on a CNN-LSTM combined deep learning approach, Water, 14, 993, https://doi.org/10.3390/w14060993, 2022.
Liu, B., Tang, Q., Zhao, G., Gao, L., Shen, C., and Pan, B.: Physics-guided long short-term memory network for streamflow and flood simulations in the Lancang–Mekong River basin, Water, 14, 1429, https://doi.org/10.3390/w14091429, 2022.
Loshchilov, I. and Hutter, F.: Decoupled weight decay regularization, arXiv [preprint], https://doi.org/10.48550/arXiv.1711.05101, 2017.
Loshchilov, I. and Hutter, F.: Fixing weight decay regularization in adam, https://openreview.net/forum?id=rk6qdGgCZ (last access: 8 July 2024), 2018.
Lucas-Picher, P., Riboust, P., Somot, S., and Laprise, R.: Reconstruction of the spring 2011 Richelieu River flood by two regional climate models and a hydrological model, J. Hydrometeorol., 16, 36–54, https://doi.org/10.1175/JHM-D-14-0116.1, 2015.
Mai, J.: Ten strategies towards successful calibration of environmental models, J. Hydrol., 620, 129414, https://doi.org/10.1016/j.jhydrol.2023.129414, 2023.
Maldonado, S., López, J., and Vairetti, C.: An alternative SMOTE oversampling strategy for high-dimensional datasets, Appl. Soft Comput., 76, 380–389, https://doi.org/10.1016/j.asoc.2018.12.024, 2019.
Martel, J.-L., Brissette, F. P., Lucas-Picher, P., Troin, M., and Arsenault, R.: Climate change and rainfall Intensity–Duration–Frequency curves: Overview of science and guidelines for adaptation, J. Hydrol. Eng., 26, 03121001, https://doi.org/10.1061/(ASCE)HE.1943-5584.0002122, 2021.
Martel, J.-L., Arsenault, R., Lachance-Cloutier, S., Castaneda-Gonzalez, M., Turcotte, R., and Poulin, A.: Improved historical reconstruction of daily flows and annual maxima in gauged and ungauged basins, J. Hydrol., 623, 129777, https://doi.org/10.1016/j.jhydrol.2023.129777, 2023.
Nash, J. E. and Sutcliffe, J. V.: River flow forecasting through conceptual models part I – A discussion of principles, J. Hydrol., 10, 282–290, https://doi.org/10.1016/0022-1694(70)90255-6, 1970.
Nearing, G. S., Sampson, A. K., Kratzert, F., and Frame, J. M.: Post-processing a Conceptual Rainfall-runoff Model with an LSTM, EarthArXiv, https://doi.org/10.31223/osf.io/53te4, 2020.
Papalexiou, S. M.: Rainfall generation revisited: Introducing CoSMoS-2s and advancing copula-based intermittent time series modeling, Water Resour. Res., 58, e2021WR031641, https://doi.org/10.1029/2021WR031641, 2022.
Rasiya Koya, S. and Roy, T.: Temporal fusion transformers for streamflow prediction: Value of combining attention with recurrence, J. Hydrol., 637, 131301, https://doi.org/10.1016/j.jhydrol.2024.131301, 2024.
Rousseau, A. N., Fortin, J.-P., Turcotte, R., Royer, A., Savary, S., Quévy, F., Noël, P., and Paniconi, C.: PHYSITEL, a specialized GIS for supporting the implementation of distributed hydrological models, Water News, 31, 18–20, 2011.
Shen, C. and Lawson, K.: Applications of deep learning in hydrology, in: Deep Learning for the Earth Sciences, 283–297, https://doi.org/10.1002/9781119646181.ch19, 2021.
Shen, H., Tolson, B. A., and Mai, J.: Time to update the split-sample approach in hydrological model calibration, Water Resour. Res., 58, e2021WR031523, https://doi.org/10.1029/2021WR031523, 2022.
Snieder, E., Abogadil, K., and Khan, U. T.: Resampling and ensemble techniques for improving ANN-based high-flow forecast accuracy, Hydrol. Earth Syst. Sci., 25, 2543–2566, https://doi.org/10.5194/hess-25-2543-2021, 2021.
Tarek, M., Brissette, F. P., and Arsenault, R.: Evaluation of the ERA5 reanalysis as a potential reference dataset for hydrological modelling over North America, Hydrol. Earth Syst. Sci., 24, 2527–2544, https://doi.org/10.5194/hess-24-2527-2020, 2020.
Tarek, M., Arsenault, R., Brissette, F., and Martel, J.-L.: Daily streamflow prediction in ungauged basins: an analysis of common regionalization methods over the African continent, Hydrol. Sci. J., 66, 1695–1711, https://doi.org/10.1080/02626667.2021.1948046, 2021.
Tolson, B. A. and Shoemaker, C. A.: Dynamically dimensioned search algorithm for computationally efficient watershed model calibration, Water Resour. Res., 43, https://doi.org/10.1029/2005WR004723, 2007.
Turcotte, R., Fortin, L.-G., Fortin, V., Fortin, J.-P., and Villeneuve, J.-P.: Operational analysis of the spatial distribution and the temporal evolution of the snowpack water equivalent in southern Québec, Canada, Hydrol. Res., 38, 211–234, https://doi.org/10.2166/nh.2007.009, 2007.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I.: Attention is all you need, Adv. Neur. In., 30, https://doi.org/10.48550/arXiv.1706.03762, 2017.
Wang, Y.-Y., Wang, W., Chau, L.-W., Xu, D.-M., Zang, H.-F., Liu, C.-J., and Ma, Q.: A new stable and interpretable flood forecasting model combining multi-head attention mechanism and multiple linear regression, J. Hydroinform., 25, 2561–2588, https://doi.org/10.2166/hydro.2023.160, 2023.
Wei, Y., Wang, R., and Feng, P.: Improving hydrological modeling with hybrid models: A comparative study of different mechanisms for coupling deep learning models with process-based models, Water Resour. Manag., https://doi.org/10.1007/s11269-024-03780-5, 2024.
Wilbrand, K., Taormina, R., ten Veldhuis, M.-C., Visser, M., Hrachowitz, M., Nuttall, J., and Dahm, R.: Predicting streamflow with LSTM networks using global datasets, Front. Water, 5, https://doi.org/10.3389/frwa.2023.1166124, 2023.
Wu, Y., Ding, Y., and Feng, J.: SMOTE-Boost-based sparse Bayesian model for flood prediction, EURASIP Journal on Wireless Communications and Networking, 2020, 78, https://doi.org/10.1186/s13638-020-01689-2, 2020.
Short summary
This study explores six methods to improve the ability of long short-term memory (LSTM) neural networks to predict peak streamflows, crucial for flood analysis. By enhancing data inputs and model techniques, the research shows that LSTM models can match or surpass traditional hydrological models in simulating peak flows. Tested on 88 catchments in Quebec, Canada, these methods offer promising strategies for better flood prediction.
This study explores six methods to improve the ability of long short-term memory (LSTM) neural...