Abstract:
Time series analysis plays a major role in predicting and analyzing climatological data. Temperature is one of the most vital elements of the climate system and modeling of the temperature helps the interested party those who are depending on it directly or indirectly to prepare in advance. The aim of this study is to develop a time series model which can help in improving the predictions of monthly temperature of Katunayake. This paper describes the Box-Jenkins time series seasonal ARIMA model for prediction of monthly maximum temperature in Katunayake region, Sri Lanka. In this study, 181 monthly temperature data were considered during the period 2001-2016. For the model selection, 169 observations were used while the rest of 12 observations were used to validate the model. The results indicate that the SARIMA(3,0,2)(2,0,2)12 model was the best model to predict monthly maximum temperature in Katunayake region.
