期刊名称：International Journal of Electronics Communication and Computer Engineering
印刷版ISSN：2249-071X
电子版ISSN：2278-4209
出版年度：2012
卷号：3
期号：5
页码：1176-1179
出版社：IJECCE
摘要：In this paper, Artificial Neural Network (ANN) models are developed to predict rainfall and rainfall Rate in the one of the major city of India i. e. Indore. The Artificial Neural Network models are trained and tested with the corresponding rainfall Data which collected from Metrology Department of India for the Indore(M. P) these Rainfall data is of last five years on monthly basis. The Data collected was in the form of weather Radar Data. In this work we compare the Actual rainfall in 2012 and predicted model of Rainfall on the basis of last five years (2007-11). The Goal of this paper is to Estimation of rainfall of 2007-11 and on the basis of these data predict the rainfall of year 2012 and also estimated. A new method is presented for calculate daily rainfall amounts from ground based radar. Radar observations of rainfall and their use in prediction of rainfall. Radar-rainfall products are crucial for input to runoff and flood prediction models, The main goal of this paper is to provide accurate estimation of rainfall on daily basis another thing from this paper shows the prediction model of rainfall to avoid flood. This research has been addressed two approaches, namely prediction model of rainfall on the basis of previous year’s data and the second is its estimation by using neural network. The results of estimation show that the neural network can be successfully applied to obtain rainfall estimation on the ground based on radar observation. The rainfall estimates obtained from several existing techniques. This neural network schemes enables the network to account for any variability in relationship between radar measurements and precipitation estimation. This precipitation estimation method is good compromise between competing demands of accuracy and generalization. In this paper we prepared the rainfall data 2007-10 and estimated using neural network
