Modeling and forecasting rainfall pattern in Ghana as a seasonal arima process:The Case of Ashanti Region

Abstract

Understanding the rainfall process is critical for the solution of several regional environmental problems of integrated water resources management at regional scales, with implications for agriculture, climate change, and natural hazards such as floods and droughts. Statistical modeling and data analysis are key instruments for studying these processes. The main objective of this article is to examine rainfall pattern over time, from 1974 to 2010, in Ashanti region of Ghana. Data for the study was obtained from the Ashanti regional division of Ghana meteorological service. It was subsequently analyzed using Seasonal Autoregressive Integrated Moving Average (SARIMA). The results showed that rainfall pattern in Ashanti region significantly changes over time. There are periods of low variability and others of extreme variability separated by periods of transition. Also, it was found that there is a slight decrease in rainfall figures from August to December when the post sample forecast is compared to the actual rainfall figures. However, February to March experienced a slight increase in rainfall figures in terms forecast figures. Generally, therefore, the forecast figures for the months show an increase in the rainfall figures for the subsequent year(s), all things being equal