Deep learning rainfall–runoff predictions of extreme events

作者：Jonathan Frame, Frederik Kratzert, Daniel Klotz, Martin Gauch, Guy Shalev, Oren Gilon, Logan M. Qualls, Hoshin V. Gupta, Grey Nearing · 发表于：Hydrology and earth system sciences · 年份：2022 · DOI：10.5194/hess-26-3377-2022 · 被引用次数：377 · 研究领域：Hydrology and Watershed Management Studies、Hydrological Forecasting Using AI、Flood Risk Assessment and Management

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.