A novel smoothing-based long short-term memory framework for short-to medium-range flood forecasting

ABSTRACT

A novel smoothing-based long short-term memory (Smooth-LSTM) framework for flood forecasting up to five days ahead is proposed, and compared with the benchmark LSTM (LSTM) model, an Artificial Neural Network (ANN) model, and the conceptual Nedbør Afstrømnings Model (MIKE11 NAM)-Hydrodynamic (HD) (MIKE) hydrological model. This framework was tested in the typical middle Mahanadi River basin (India), which has a tropical monsoon-type climate. Variation of training loss indicated the LSTM network has a higher learning ability at smaller network and batch sizes. The Smooth-LSTM model could predict streamflow with higher Nash-Sutcliffe efficiency of 0.82–0.87 at up to five days lead time with a better reproduction of the observed crucial high peak floods, whereas the corresponding MIKE, ANN and LSTM model-based forecasts were acceptable only up to four-, three- and one-day lead times, respectively. Overall, the Smooth-LSTM model is found to be robust in operational flood forecasting, with lower uncertainty and the least sensitivity to redundant input information.

KEYWORDS:

• ANN
• flood forecasting
• long short-term memory (LSTM)
• MIKE 11 NAM-HD
• smoothing windows

Editor A. Castellarin Associate Editor O. Kisi

Editor A. Castellarin Associate Editor O. Kisi

Acknowledgements

The authors sincerely thank the Hirakud Dam Circle (HDC), Department of Water Resources (Prachi Division), Odisha, Central Water Commission (CWC) and India Meteorological Department (IMD) for providing the necessary datasets to carry out the study.

Disclosure statement

No potential conflict of interest was reported by the authors.

Data availability statement

All data, models, and code generated or used during the study appear in the submitted article.

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/02626667.2023.2173012