Computing River Discharge Using Water Surface Elevation Based on Deep Learning Networks

Accurately computing river discharge is crucial, but traditional computing methods are complex and need the assistance of many other hydraulic parameters. Therefore, it is of practical value to develop a convenient and effective auto-computation technique for river discharge. Water surface elevation is relatively easy to obtain and there is a strong relationship between river discharge and water surface elevation, which can be used to compute river discharge. Unlike previous usage of deep learning to predict short-term river discharge that need multiple parameters besides water level, this paper proved that deep learning has the potential to accurately compute long-term river discharge purely based on water level. It showed that the majority of relative errors on the test dataset were within +/- 5%, particularly it could operate continuously for almost one year with high precision without retraining. Then, we used BiGRU to compute river flow with different hyperparameters, and its best RMSE, NSE, MAE, and MAPE values were 256 m3/s, 0.9973, 207 m3/s, and 0.0336, respectively. With this data-driven based technology, it will be more convenient to obtain river discharge time series directly from local water surface elevation time series accurately in natural rivers, which is of practical value to water resources management and flood protection.