Skip to content
Conference

Wavelet-LSTM-Based River Water Level Forecasting in Pahang

Sep 2026 · 2026 7th International Conference on Artificial Intelligence and Data Sciences (AiDAS) · pp. 335-339 · 0 citations · 10 references

Abstract

Water level forecasting is important in Malaysia because many rivers experience sudden changes during the monsoon season, especially in the Pahang River Basin. Accurate forecasting is essential for effective flood warning systems and water resource management. However, river water level data in Malaysia are often noisy, highly variable, and nonlinear, making them difficult to predict using traditional models. This study aims to develop a Wavelet–Long Short Term Memory (LSTM) model-based for forecasting river water levels in the Pahang River Basin. The study first identifies suitable hydrometeorological variables and then applies wavelet decomposition to enhance the forecasting process. The proposed hybrid model combines wavelet transform and Long Short-Term Memory (LSTM) networks to capture both short-term and long-term patterns in the data. The model is trained and tested using historical river water level data, and its performance is compared with a standard LSTM model. The results show that the proposed Wavelet–LSTM model achieves better forecasting accuracy and is more effective in handling highly variable river conditions. This study highlights the potential of hybrid deep learning models for river water level forecasting in Malaysia and encourages the use of advanced data-driven approaches for flood prediction and water management.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.