Advancements in Daily Precipitation Forecasting: A Deep Dive into Daily Precipitation Forecasting Hybrid Methods in the Tropical Climate of Thailand
Journal article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Muhammad Waqas, Usa Wannasingha Humphries, Phyo Thandar Hliang, Angkool Wangwongchai, Porntip Dechpichai
Publisher: Elsevier
Publication year: 2024
Volume number: 12
Start page: 102757
ISSN: 22150161
eISSN: 2215-0161
URL: https://methods-x.com/retrieve/pii/S2215016124002103
Languages: English-Great Britain (EN-GB)
Abstract
resource management. Precise precipitation forecasting is critical to effective management. This study introduced a Daily Precipitation Forecasting Hybrid (DPFH) technique for central Thailand, which uses three different input-based models to improve prediction accuracy.
• The proposed methods precisely combine the biorthogonal wavelet transformation (BWT) function through BWT-RBFNN (Radial Basis Function Neural Networks) and (BWT-LSTM-RNN)Long Short-Term Memory Recurrent Neural Networks. Comparative analyses reveal that hybrid models perform better than conventional deep LSTM-RNN and Multilayer Perceptron Artificial Neural Networks (MLP-ANN). Although MLP-ANN showed moderate effectiveness, LSTM-RNN displayed notable enhancements, particularly evidenced by an impressive R2 (0.96) in Model M-2.
• The combination of BWT-LSTM-RNN yielded substantial enhancements, constantly surpassing standalone models. Specifically, DPFH-3 exhibited superior performance across multiple observation stations.
• The findings emphasize the efficiency of the BWT-LSTM-RNN models in capturing varied precipitation patterns, highlighting their potential to significantly improve the accuracy of precipitation forecasts, particularly in the context of water resource management in central Thailand.
Keywords
Artificial Intelligence, Deep Learning, Forecasting, Neural networks, Short Term Precipitation, wavelet Transformation