Abstract/Summary

Accurate river streamflow forecasts are a vital tool in the fields of water security, flood preparation and agriculture, as well as in industry more generally. Traditional physics-based models used to produce streamflow forecasts have become increasingly sophisticated, with forecasts improving accordingly. However, the development of such models is often bound by two soft limits: empiricism -- many physical relationships are represented empirical formulae; and data sparsity -- long time-series of observational data are often required for the calibration of these models. Artificial neural networks have previously been shown to be highly effective at simulating nonlinear systems where knowledge of the underlying physical relationships is incomplete. However, they also suffer from issues related to data sparsity. Recently, hybrid forecasting systems, which combine the traditional physics-based approach with statistical forecasting techniques, have been investigated for use in hydrological applications. In this study, we test the efficacy of a type of neural network, the long-short term memory (LSTM), at predicting streamflow at ten river gauge stations across various climatic regions of the western United States. The LSTM is trained on the catchment-mean meteorological and hydrological variables from the ERA5 and GloFAS-ERA5 reanalyses as well as historical streamflow observations. The performance of these hybrid forecasts is evaluated and compared to the performance of both raw and bias-corrected output from the Copernicus Emergency Management Service (CEMS) physics-based Global Flood Awareness System (GloFAS). Two periods are considered, a testing phase (June 2019 to June 2020), during which the models were fed with ERA5 data to investigate how well they simulated streamflow at the ten stations; and an operational phase (September 2020 to October 2021), during which the models were fed forecast variables from ECMWF's Integrated Forecasting System (IFS), to investigate how well they could predict streamflow at lead times of up to ten days. Implications and potential improvements to this work are discussed. In summary, this is the first time an LSTM has been used in a hybrid system to create a medium-range streamflow forecast, and in beating established physics-based models, shows promise for the future of neural networks in hydrological forecasting.