Please use this identifier to cite or link to this item:
Title: Monthly rainfall prediction model of Peninsular Malaysia Using Clonal Selection Algorithm
Authors: Rodi, N.S.N. 
Malek, M.A. 
Ismail, A.R. 
Issue Date: 2018
Abstract: Nowadays, various algorithms inspired by natural processes have been extensively applied in solving engineering problems. This study proposed Artificial Immune Systems (AIS), a computational approach inspired by the processes of human immune system, as an algorithm to predict future rainfall. This proposed algorithm is another alternative technique as compared to the commonly used Statistical, Stochastic and Artificial Neural Network techniques traditionally use in Hydrology. Rainfall prediction is pertinent in order to solve many hydrological problems. The proposed Clonal Selection Algorithm (CSA) is one of the main algorithms in AIS, which inspired on Clonal selection theory in the immune system of human body that includes selection, hyper mutation, and receptor editing processes. This study proposed algorithm is utilised to predict future monthly rainfall in Peninsular Malaysia. The collected data includes rainfall and other four (4) meteorological parameters from year 1988 to 2017 at four selected meteorological stations. The parameters used in this analysis are humidity, wind speed, temperature and pressure at monthly interval. Four (4) meteorological stations involved are Chuping (north), Subang Jaya(west), Senai (south) and Kota Bharu (west) represented peninsular Malaysia. Based on the results at testing stage, it is found that the trend and peaks of the hydrographs from generated data are approximately similar to the actual historical data. The highest similarity percentage obtained is 91%. The high values of similarity percentage obtained between simulated and actual rainfall data in this study, reinforced the hypothesis that CSA is suitable to be used for prediction of continuous time series data such as monthly rainfall data which highly variable in nature. As a conclusion, the results showed that the proposed Clonal Selection Algorithm is acceptable and stable at all stations. © 2018 Authors.
Appears in Collections:UNITEN Scholarly Publication

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.