Use of Artificial Neural Networks in Precipitation Forecasting

The purpose of this paper is to study the potential uses of Artificial Neural Networks (ANNs) in estimating monthly precipitation for the City of Memphis, Tennessee. One of the popular models, the backpropagation algorithm (BP), was developed and installed in an internal program. Annual precipitation data from the City of Memphis provides the basis data to train the networks. The trained networks were then used to verify and predict precipitation for the City of Memphis. The results indicated that ANNs can recognize the precipitation pattern and provide an analogous precipitation trend to the existing precipitation data. One of the major advantages of this method is that its performance does not require a large quantity of data in the trend analysis.