Prediction of Monsoon Rainfall Using Large Scale Climate Signals: A Case Study

Abstract

In this paper, a comprehensive investigation on application Artificial Neural Networks in long-term rainfall forecasting is presented. A variety of ANN-models have been developed to process and train a system with large scale climate signals for the summer precipitation spells. The summer monsoon is one of the most dynamic climate systems that controls rainfall variation in some Asian countries such as India and Pakistan and delivers a component of annual rainfall in these regions. The sum of rainfall during July, August and September is called summer monsoon rainfall. In order to quantify the effects of large scale climate signals on the precipitation in the study area, long-term records of SST (Sea Surface Temperature) and SLP (Sea Level Pressure) over Oman Sea, Arabian Sea and Indian Ocean have been examined. The SSTs over west coast of India as well as the SSTs over the Oman Sea shows a high correlation with monsoon rainfall in Iran. Also SLP over the Northern part of India shows a significant correlation with recorded rainfall at different points of the region. These signals can be used as useful predictors for monsoon rainfall at the southeastern part of Iran. The results show that considering a set of predictors developed in this study could significantly increase the accuracy of long-lead precipitation forecasting in the study area using ANN models.