A Comparative Study Of Rainfall Prediction Neural Network And Decision Tree

Abstract

Weather forecasting is a vital application in meteorology and has been one of the most scientifically and technologically challenging problems around the world. In this paper, data mining technique was used for forecasting precipitation. This was carried out using Artificial Neural Network and Decision Tree algorithms and meteorological data collected between 2004 and 2008 from the city of Kathmandu, Nepal. A data model for the meteorological data was developed and this was used to train the two different algorithms. The performances of these algorithms were compared using standard performance metrics, and the algorithm which gave the best results used to generate classification rules for the mean weather variables. A predictive Neural Network model was also developed for the weather prediction program and the results compared with actual weather data for the predicted periods. In order to build a model for Artificial Neural Network and Decision Tree. Among the total data set , 80%,70 % and 75 % data set, were used for training and 20%, 30 % and 35 % were used for the Testing. Experimentation results show, feed-forward multi layer Perceptron based neural network classifier has lower error rate than Decision Tree. MLP classification system has the average system accuracy rate of 77.98%, system error rate of 22.02%, precision rate of 12.08%, and recall rate of 78.57%. Similarly, Decision Tree system has the average system accuracy rate of 73.74%, system error rate of 26.26%, and precision rate of 9.52% recall rate of 71.42%.