To forecast daily Rainfall, in this study a system is designed and developed in MATLAB 7.10 using Multi-layer Feed Forward Neural Network with Back-Propagation. The Network is trained using Delta Learning Rule. A dataset of 31488 samples were collected from Nungambakkam Meteorological Station, Chennai for the period of 2005 to 2015 by registering with India Meteorological Department (IMD), Pune. The data was organized into day-wise hourly recordings as well as day-wise maximum, minimum, average data of Relative Humidity (RH), Temperature and Pressure along with Rainfall data. The collected dataset were pre-processed and normalized with Min-Max Linear Scaling method and are used for both training and for testing the data. The developed system gives more accuracy of 95.5443% when the training data set is 50% and the testing data set is 50% with least Mean Squared Error (MSE) value 0.011555. Again to validate the accuracy rate obtained from this neural network model, Heidke Skill Score (HSS) has been computed.
Article Details
Unique Paper ID: 154183
Publication Volume & Issue: Volume 8, Issue 10
Page(s): 665 - 674
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024