Time Series Analysis of Forecasting Indian Rainfall
Akashdeep Gupta1, Anjali Gautam2, Chirag Jain3, Himanshu Prasad4, Neeta Verma5
1Akashdeep Gupta, Inderprastha Engineering College, Ghaziabad (U.P.), India
2Anjali Gautam, Inderprastha Engineering College, Ghaziabad (U.P.), India
3Chirag Jain, Inderprastha Engineering College, Ghaziabad (U.P.), India
4Himanshu Prasad, Inderprastha Engineering College, Ghaziabad (U.P.), India
5Neeta Verma, Inderprastha Engineering College, Ghaziabad (U.P.), India
Manuscript received on May 03, 2013. | Revised Manuscript Received on May 10, 2013. | Manuscript published on May 20, 2013. | PP: 42-45 | Volume-1, Issue-6, May 2013.
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents a study of neural network model for prediction of Indian rainfall. The purpose of this paper is to evaluate the applicability of ANN. In this paper the performance of different networks have been evaluated and tested.The multilayered artificial neural network with learning by backpropagation algorithm is used .The paper implements weather prediction by building training and testing data sets and finding the number of hidden neurons in these layers for the best performance. The proposed model has been able to predict values with suitable results. The prediction is made on the bases of previous data. The criteria for prediction in the model are correlation, RMSE, standard deviation .Prediction of Rainfall is necessary for Agricultural & Metrological Department. In India, most of our Economy is dependent on agriculture. A big percentage of GDP is contributed by agriculture. In India, agriculture provides around 70% of employment either directly or indirectly. This is major reason for analysis of prediction of rainfall.
Keywords: Artificial Neural Network, Root Mean Square Error, Standard Deviation, and Backpropagation.