Implementation of Rainfall Forecasting using ANN

Abstract

Prediction of rainfall is essential for many sectors, including flood mitigation, disaster prevention, agriculture production, and water resource management. Rain forecasts are used to warn of natural disasters such as floods or to plan planting activities to improve the quality of crop yields. An accurate rainfall prediction remains a challenging task due to the uncertainty of natural phenomena considering that rainfall is a non-linear and dynamic process. Various climatic variables such as temperature, relative humidity, wind speed and direction, are among those that affect the dynamic process of rainfall. This study suggests a machine learning technique based on Artificial Neural Network (ANN) model to forecast rainfall by using two-years historical local rain rate and others meteorological data. Evaluation metrics such as mean absolute error, root mean square error, and correlation coefficient, are used to evaluate model’s performance. The results show good performance and sensible prediction accuracy. The comparison with existing model clearly depicted that ANN model predicts rainfall better than statistical models particularly at lower and moderate rain rate.