Rainfall forecast using SARIMA model along the coastal areas of Sindh Province

Abstract

Rainfall forecasting is critical for economic activities such as agriculture, watershed management, and flood control. It requires mathematical modelling and simulation. This paper investigates the time series analysis and forecasting of the monthly rainfall for the Sindh coastline, Pakistan. The seasonal autoregressive integrated moving average (SARIMA) model was used for the last three decades (1991-2020) and forecasting was done for the next two years. The model is based on the Box Jenkins methodology. The decomposition of time series plots into trend, seasonal and random components showed a seasonal effect. The Augmented Dickey–Fuller (ADF) and Mann–Kendall (MK) tests showed the inherent stationarity of the rainfall data. The best SARIMA models for monthly rainfall were SARIMA (1,0,1)(3,1,1)12 and SARIMA (1,0,1)(1,1,1)12 with Akaike information criterion corrected (AICC) values of 1507 and 1387, respectively. The model predictions indicate that, in the years 2021/22, July will likely have the most rainfall, followed by August and June. The diagnostic statistical test values directed that the adequacy of the models is consistent for projected monthly rainfall forecasts.