A Hybrid Wavelet-Arima Model for Standardized Precipitation Index Drought Forecasting

Abstract

ABSTRACT

This paper proposes A Hybrid Wavelet-Auto-Regressive Integrated Moving
Average (W-ARIMA) model to explore the ability of the hybrid model over an ARIMA
model. It combines two methods, a Discrete Wavelet Transform (DWT) and ARIMA
model using the Standardized Precipitation Index (SPI) drought data for forecasting
drought modeling development. SPI data from January 1954 to December 2008 used was
divided into two - (80%/20% for training/testing respectively). The results were compared
with the conventional ARIMA model with Mean Square Error (MSE) and Mean Average
Error (MAE) as an error measure. The results of the proposed method achieved the best
forecasting performance.