Climate Signal Clustering Using Genetic Algorithm for Precipitation Forecasting: A Case Study of Southeast of Iran

摘要

In this paper, an innovative method for clustering of climate signals is developed using Genetic Algorithm (GA), In this model, the relation of the signals with the variations of another climatic variable is considered in clustering algorithm. In the case study, the model is used for clustering the Sea Surface Temperature (SST) data in Omman Sea, Arabian Sea, and Indian Ocean considering the precipitation variations in Sistan-Balouchestan Province in Southeast of Iran. For this purpose, the precipitation data is classified to the three categories of below normal, normal, and above normal and the fitness function of the GA model is formulated to minimize the variance of the precipitation for each selected cluster. The results show that the model can be effectively used for prediction of low and high precipitation seasons in the study area using the SST variations in the defined clusters.