Design of mathematical model for the prediction of rainfall

Abstract

There are several soft computing methods in use to predict rainfall. Mainly two features were included to increase rainfall prediction: (1) using data pre-processing procedure and (2) using a modular approach. The projected pre-processing approach incorporated Moving Average (MA) and Singular Spectrum Analysis (SSA). The method of modular was poised of Support Vectors Regression l (SVR) models or the Rough Set Technique (RST). In the development for forecasting of rainfall, the RST was initially applied for the data- preprocessing. Modular models used to pre-process the preparation data into three distinct subsets (level-1, level-2, and level-3) from the scales of the trained data, and lastly, two SVRs were used in the level-2 and level-3 subsets. In contrast, Artificial Neural Network (ANN) or SVR was concerned with predicting and was useful in training the data. Each day’s rate of downpour proof, the level-1 subset tended to be modelled by the ANN because it was overwhelming in the training data. ANN is beneficial for huge-scale samples training because of its corresponding information processing configuration. This work explores the use of hybridization technique of RST and time series, where RST helps to find the essential attribute from the collection of raw meteorological data set then analyzing the important characteristic using time series and various classifiers. There are several prediction techniques available to predict based on meteorological data set to suitably predict a meteorological phenomenon. In this work, our objective is to find the most frequent meteorological phenomena which affects our state most. Purposefully, we consider the RST to predict the most significant meteorological phenomena by using the RST and predict the rainfall per day basis. Hybrid soft computing techniques and RST are used in the present work. We validate our claim using the Chi-square test.