Predicting discharge in catchment outlet using deep learning methods: case study of Niamey in the Ansongo-Niamey basin

Abstract

Hydrological models are one of the key challenges in hydrology. Their goal is to understand, predict and manage water resources. Most of the hydrological models so far were physically based and conceptual models. But in the past two decades, fully data-driven (empirical) models started to emerge with the breakthroughs of novel deep learning methods in runoff prediction. The breakthrough was mostly favored by the large volume, variety and velocity of water-related data. Long Short-Term Memory networks (LSTMs), particularly achieved the outstanding milestone of outperforming classic hydrological models in less than a decade. Moreover, they have the potential to change the way hydrological modeling is performed. In this study, we used precipitation, maximum and minimal temperature at the Ansongo-Niamey basin mixed with the discharge at Ansongo and Kandadji to predict the discharge at Niamey using LSTM neural networks. After data prepossessing and hyperparameter optimization, the LSTM model performed well with a R2 of 0.897, a NSE of 0.852 and a RMSE of 229.158. This performance matches those of well-known physically based models used to simulate Niamey’s discharge and therefore demonstrates the efficiency of deep learning methods in a West African context.