Time Series Analysis based Tamilnadu Monsoon Rainfall Prediction using Seasonal ARIMA

Abstract

Amount of Rainfall prediction is a major issue for the weather department as it is associated with the human's life and the economy. Excess rainfall is the major cause of natural disasters such as drought and flood which are encountered by the people every year across the world. The time series machine learning model is used for forecasting rainfall at Tamilnadu. Forecasting data required for the analysis is available in the Indian meteorological department. To model the monthly rainfall in Tamilnadu for the period from January 1990 to December 2017, the seasonal ARIMA (Auto Regressive Integrated Moving Average) technique is applied. Using the SARIMA (Seasonal Auto Regressive Integrated Moving Average), the stationarity of the time series flow was demonstrated by the rainfall prediction model and the seasonal correlogram assessed. In relation to the Mean Squared Error (MSE) and Root Mean Squared Error, the output of this model is assessed (RMSE). Therefore, it reveals that the ARIMA model accurately forecasts the Rainfall with less error and the derived model could be used to forecast Monsoon rainfall for the upcoming years.