A neural network model for rainfall estimation

Abstract

This paper investigates the use of an artificial neural network (ANN) to estimate the six hour rainfall over the south-east coast of Tasmania. ANNs are becoming increasingly prominent in many areas of weather forecasting due to their potential to capture the complex relationships between the many factors that contribute to certain weather conditions. The estimations produced by the ANNs were compared to one estimation technique and one forecasting technique used by the Bureau of Meteorology. The results confirm that ANNs have the potential for successful application to the problem of rainfall estimation.