Articles | Volume 26, issue 13
https://doi.org/10.5194/hess-26-3377-2022
https://doi.org/10.5194/hess-26-3377-2022
Research article
 | 
05 Jul 2022
Research article |  | 05 Jul 2022

Deep learning rainfall–runoff predictions of extreme events

Jonathan M. Frame, Frederik Kratzert, Daniel Klotz, Martin Gauch, Guy Shalev, Oren Gilon, Logan M. Qualls, Hoshin V. Gupta, and Grey S. Nearing

Related authors

Technical note: Data assimilation and autoregression for using near-real-time streamflow observations in long short-term memory networks
Grey S. Nearing, Daniel Klotz, Jonathan M. Frame, Martin Gauch, Oren Gilon, Frederik Kratzert, Alden Keefe Sampson, Guy Shalev, and Sella Nevo
Hydrol. Earth Syst. Sci., 26, 5493–5513, https://doi.org/10.5194/hess-26-5493-2022,https://doi.org/10.5194/hess-26-5493-2022, 2022
Short summary

Related subject area

Subject: Catchment hydrology | Techniques and Approaches: Modelling approaches
Stable water isotopes and tritium tracers tell the same tale: no evidence for underestimation of catchment transit times inferred by stable isotopes in StorAge Selection (SAS)-function models
Siyuan Wang, Markus Hrachowitz, Gerrit Schoups, and Christine Stumpp
Hydrol. Earth Syst. Sci., 27, 3083–3114, https://doi.org/10.5194/hess-27-3083-2023,https://doi.org/10.5194/hess-27-3083-2023, 2023
Short summary
Uncertainty in water transit time estimation with StorAge Selection functions and tracer data interpolation
Arianna Borriero, Rohini Kumar, Tam V. Nguyen, Jan H. Fleckenstein, and Stefanie R. Lutz
Hydrol. Earth Syst. Sci., 27, 2989–3004, https://doi.org/10.5194/hess-27-2989-2023,https://doi.org/10.5194/hess-27-2989-2023, 2023
Short summary
Changes in Mediterranean flood processes and seasonality
Yves Tramblay, Patrick Arnaud, Guillaume Artigue, Michel Lang, Emmanuel Paquet, Luc Neppel, and Eric Sauquet
Hydrol. Earth Syst. Sci., 27, 2973–2987, https://doi.org/10.5194/hess-27-2973-2023,https://doi.org/10.5194/hess-27-2973-2023, 2023
Short summary
Can the combining of wetlands with reservoir operation reduce the risk of future floods and droughts?
Yanfeng Wu, Jingxuan Sun, Boting Hu, Y. Jun Xu, Alain N. Rousseau, and Guangxin Zhang
Hydrol. Earth Syst. Sci., 27, 2725–2745, https://doi.org/10.5194/hess-27-2725-2023,https://doi.org/10.5194/hess-27-2725-2023, 2023
Short summary
Knowledge-informed deep learning for hydrological model calibration: an application to Coal Creek Watershed in Colorado
Peishi Jiang, Pin Shuai, Alexander Sun, Maruti K. Mudunuru, and Xingyuan Chen
Hydrol. Earth Syst. Sci., 27, 2621–2644, https://doi.org/10.5194/hess-27-2621-2023,https://doi.org/10.5194/hess-27-2621-2023, 2023
Short summary

Cited articles

Addor, N., Newman, A. J., Mizukami, N., and Clark, M. P.: The CAMELS data set: catchment attributes and meteorology for large-sample studies, Hydrol. Earth Syst. Sci., 21, 5293–5313, https://doi.org/10.5194/hess-21-5293-2017, 2017a. a, b
Addor, N., Newman, A. J., Mizukami, N., and Clark, M. P.: The CAMELS data set: catchment attributes and meteorology for large-sample studies, version 2.0. Boulder, CO, UCAR/NCAR [data set], https://doi.org/10.5065/D6G73C3Q, 2017b. a
Burkey, J.: Log-Pearson Flood Flow Frequency using USGS 17B, MATLAB Central File Exchange [code], https://www.mathworks.com/matlabcentral/fileexchange/22628-log-pearson-flood-flow-frequency-using-usgs-17b (last access: 17 June 2022), 2009. a
Cameron, D., Kneale, P., and See, L.: An evaluation of a traditional and a neural net modelling approach to flood forecasting for an upland catchment, Hydrol. Process., 16, 1033–1046, https://doi.org/10.1002/hyp.317, 2002. a
Frame, J.: jmframe/mclstm_2021_extrapolate: Submit to HESS 5_August_2021, Zenodo [code], https://doi.org/10.5281/zenodo.5165216, 2021a. a, b
Download

The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.

Short summary
The most accurate rainfall–runoff predictions are currently based on deep learning. There is a concern among hydrologists that deep learning models may not be reliable in extrapolation or for predicting extreme events. This study tests that hypothesis. The deep learning models remained relatively accurate in predicting extreme events compared with traditional models, even when extreme events were not included in the training set.