What question did this study set out to answer?

The aim is to enhance flood forecasting capabilities using deep learning for river level predictions.

December 8, 2025AIP AdvancesOpen Access

Application of deep learning for hourly river level forecast: A case study of Sarawak River, Malaysia

View Full Paper

Ask AI

Bookmark

Authors

Application of deep learning models improves prediction accuracy in flood forecasting, indicating better water resource management.

The aim is to enhance flood forecasting capabilities using deep learning for river level predictions.
Employs four AI models: LSTM, BiLSTM, CNN-BiLSTM, and CNN-BiLSTM-XGB.
Analyzes river water level data from the Sarawak River in Malaysia.
Evaluates model performance on training, validation, and test sets.
CNN-BiLSTM-XGB model achieved an R2 value of 0.973, a 17.1% improvement over LSTM.
Demonstrated superior prediction accuracy and robustness in extensive simulations.
Addressed overfitting issues present in initial model performances.

H. C. Zhou (2025) studied this question.

View Full Paper

Ask AI

Bookmark