An implementation of weighted moving average and genetic programming for rainfall forecasting in Bandung Regency
Budy Utama Putra, Fhira Nhita, Adiwijaya Adiwijaya, Deni Saepudin, Untari Novia Wisesty · 2017
This paper is the results of research about the weather forecast in Bandung Regency using one of the Evolutionary Algorithms (EA), that is Genetic Programming (GP). In this research, we use the monthly rainfall data in Bandung Regency for the last 11 years (2005–2015). First of all, the data is processed by Weighted Moving Average (WMA) algorithm as preprocessing step. Next, GP Algorithm is used to process the rainfall weather forecast which represents non-linear chromosome as a tree. In a population, chromosomes have different lengths because a child's chromosomes can be longer or shorter than his parents. To produce child, GP Algorithm applies the recombination process and the mutation using the several scenarios of probability of crossover and probability of mutation. By applying Genetic Programming algorithm, the system of weather forecast in Bandung regency has a performance above 70% in accuracy.