Deep learning rainfall–runoff predictions of extreme events

Abstract The most accurate rainfall–runoff predictions are currently based on deep learning. There is a concern among hydrologists that the predictive accuracy of data-driven models based on deep learning may not be reliable in extrapolation or for predicting extreme events. This study tests that hypothesis using long short-term memory (LSTM) networks and an LSTM variant that is architecturally constrained to conserve mass. The LSTM network (and the mass-conserving LSTM variant) remained relatively accurate in predicting extreme (high-return-period) events compared with both a conceptual model (the Sacramento Model) and a process-based model (the US National Water Model), even when extreme events were not included in the training period. Adding mass balance constraints to the data-driven model (LSTM) reduced model skill during extreme events.

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch

References and Relationships

• Bibliographic citation: Deep learning rainfall–runoff predictions of extreme events ; volume:26 ; number:13 ; year:2022 ; pages:3377-3392 ; extent:16 ; Hydrology and earth system sciences ; 26, Heft 13 (2022), 3377-3392 (gesamt 16)

Contributors, Places and Time

• Creator: Frame, Jonathan M. ; Kratzert, Frederik ; Klotz, Daniel ; Gauch, Martin ; Shelev, Guy ; Gilon, Oren ; Qualls, Logan M. ; Gupta, Hoshin V. ; Nearing, Grey S.

Further information

• DOI: 10.5194/hess-26-3377-2022
• URN: urn:nbn:de:101:1-2022070705162720980740
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 15.08.2025, 7:33 AM CEST