Weather forecasting using artificial neural network

• Main Author: Wong, Wei Keat
• Format: Final Year Project Report
• Language: English; English
• Published: Universiti Malaysia Sarawak, (UNIMAS) 2014
• Subjects: Q Science (General); T Technology (General)
• Online Access: http://ir.unimas.my/id/eprint/39012/1/Wong%20Wei%20Keat%20%2824pgs%29.pdf; http://ir.unimas.my/id/eprint/39012/4/Wong%20Wei%20Keat%20%28ft%29.pdf; http://ir.unimas.my/id/eprint/39012/

This project studies the better weather forecasting approaches. In this study, Kuching city been selected as the study area. The Kuching meteorology data used in this study is collected from the Malaysian Meteorological Department. Artificial neural network (ANN) is adopted in this study as ANN has better performance and it can perform weather forecasting better than conventional weather forecast model. Two neural network algorithms, Back Propagation (BPNN) and Radial Basis Function (RBFNN) were tested with the Kuching meteorology data set. Both neural network models are trained and tested with different testing criteria, thus the results and performance generated by these two neural network algorithms were compared. The experimental results showed that the BPNN model has better performance in weather forecasting compared to RBFNN.