Artificial Neural Network Model For Rainfall-Runoff Relationship

• Main Authors: Harun, Sobri, Ahmat Nor, Nor Irwan, Mohd. Kassim, Amir Hashim
• Format: Article
• Language: English
• Published: Penerbit UTM Press 2002
• Subjects: TA Engineering (General). Civil engineering (General)
• Online Access: http://eprints.utm.my/id/eprint/1408/1/JT37B1.pdf; http://eprints.utm.my/id/eprint/1408/; http://www.penerbit.utm.my/onlinejournal/37/B/JT37B1.pdf

The modelling of hydraulic and hydrological processes is important in view of the many uses of water resources such as hydropower generation, irrigation, water supply, and flood control. There are many previous works using the artificial neural network (ANN) method for modelling various complex non-linear relationships of hydrologic processes. The ANN is well known as a flexible mathematical structure and has the ability to generalize patterns in imprecise or noisy and ambiguous input and output data sets. The study area is Sungai Lui catchment (Selangor, Malaysia). This paper presents the proposed ANN model for prediction of daily runoff using the rainfall as input nodes. The method for selection of input nodes by [10] and [5] is applied. Further, the results are compared between ANN and HEC-HMS model. It has been found that the ANN models show a good generalization of rainfall-runoff relationship and is better than HEC-HMS model.