Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting

TLDR

Flood forecasting is essential for integrated water resource management. The study proposes a Long Short-Term Memory neural network that uses daily discharge and rainfall to forecast floods. The authors trained the LSTM on data from the Da River basin in Vietnam, exploring how pre‑1985 input combinations affect one‑, two‑, and three‑day flow predictions at Hoa Binh Station. The model achieved Nash–Sutcliffe efficiencies of 99%, 95%, and 87% for one‑, two‑, and three‑day forecasts, demonstrating its viability for flood forecasting on the Da River.

Abstract

Flood forecasting is an essential requirement in integrated water resource management. This paper suggests a Long Short-Term Memory (LSTM) neural network model for flood forecasting, where the daily discharge and rainfall were used as input data. Moreover, characteristics of the data sets which may influence the model performance were also of interest. As a result, the Da River basin in Vietnam was chosen and two different combinations of input data sets from before 1985 (when the Hoa Binh dam was built) were used for one-day, two-day, and three-day flowrate forecasting ahead at Hoa Binh Station. The predictive ability of the model is quite impressive: The Nash–Sutcliffe efficiency (NSE) reached 99%, 95%, and 87% corresponding to three forecasting cases, respectively. The findings of this study suggest a viable option for flood forecasting on the Da River in Vietnam, where the river basin stretches between many countries and downstream flows (Vietnam) may fluctuate suddenly due to flood discharge from upstream hydroelectric reservoirs.