Performance Comparison of Artificial Neural Network Models for Daily Rainfall Prediction

• 作 者: S.Renuga Devi P.Arulmozhivarman C.Venkatesh Pranay Agarwal
• 机 构: School of Electronics Engineering, VIT University,Faculty of Engineering, EBET Group of Institutions
• 出 处: International Journal of Automation and Computing
• 发表日期: 2016年05期
• 关键词: Rainfall prediction artificial neural networks distributed time delay neural net

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network(BPN), cascade-forward back propagation neural network(CBPN), distributed time delay neural network(DTDNN) and nonlinear autoregressive exogenous network(NARX), and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and around Coonoor(a taluk of Nilgiris). Based on the performance analysis,NARX network outperformed all the other networks. Though there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performed considerably well confirming its prediction capabilities. Levenberg Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was instrumental in identifying the key predictors.

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network (BPN), cascade-forward back propagation neural network (CBPN), distributed time delay neural network (DTDNN) and nonlinear autoregressive exogenous network (NARX), and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and Around there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performing well prediction of its prediction capabilities. Levenberg (a taluk of Nilgiris). Based on the performance analysis, NARX network outperformed all the other networks. Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was i nstrumental in identifying the key predictors