Monthly rainfall categorization based on optimized features and neural network

Rainfall is a complex process that result from different atmospheric interactions. Rainfall forecasting is highly effective for various industries including the sugarcane industry. In this study, we propose a neural network based approach for classifying monthly rainfall. Rainfall classification is defined as determining the category of rainfall amount based on a certain threshold. Five distinct locations were selected to perform the study: Innisfail, Planecreek, Bingera, Maryborough in Queensland, Australia and Yamba in New South Wales, Australia. Multiple local and global climate indices have been linked to formation of rain. Hence, different local and global climate indices are proposed as possible predictors of rain. A Particle Swarm Optimization (PSO) algorithm was incorporated to select best features for each month in each location. An average accuracy of 87.65% was recorded with the proposed approach over the five selected locations. The developed models were compared against other neural network models where all features were used as input features. An average difference of 25.00%, 23.89%, 24.02%, 20.00%, 20.59% was recorded for Innisfail, Planecreek, Bingera, Maryborough and Yamba respectively. The analysis of statistical results suggests that the artificial neural networks can be used as a promising alternative approach for rainfall categorization over multiple weather zones and over Australia. In addition, selection of input features should be carefully considered when designing rainfall forecasting models.