Rainfall-funoff modelling in batang layar and oya sub-catchments using pre-developed ann model for tinjar catchment

• Main Author: Awangku Faizal Sallehin, Awangku Brahim
• Format: Final Year Project Report
• Language: English
• Published: Universiti Malaysia Sarawak, UNIMAS 2009
• Subjects: TD Environmental technology. Sanitary engineering
• Online Access: http://ir.unimas.my/id/eprint/4562/1/AWANGKU%20FAIZAL%20SALLEHIN%20BIN%20AWANGKU%20BRAHIM%2024pgs.pdf; http://ir.unimas.my/id/eprint/4562/

Artificial Neural Network (ANN) has been widely used to forecast Rainfall-Runoff relationships. Many ANN has been developed by experts in order to forecast RainfallRunoff relationships in certain catchment. However, there are uncertainties whether the developed ANN can be used to forecast Rainfall-Runoff relationships in other catchments dominantly, just like how it can forecast Rainfall-Runoff relationships for its purposed catchments. Therefore, the purpose of this study is to check whether a developed ANN for forecasting Rainfall-Runoff relationships in Sungai Tinjar catchment can be used in two other catchments which are Batang Layar and Hulu Batang Oya. The network was trained using Back Propagation Algorithm. The Back Propagation Algorithm consists two phases; forward phase and backward phase. The variant used is Resilient Backpropagation (trainrp). To do the training, Matlab 7 computer software was used. This study had successfully proven that a developed ANN for forecasting Rain-Runoff relationships in Sungai Tinjar Catchment is achievable for Batang Layar and Hulu Batang Oya Catchment; however deeper understanding and further improvement of the network are necessary.