RAINFALL FORECASTING WITH HOURLY SURFACE DATA OF HUMIDITY, PRESSURE AND TEMPERATURE USING ARTIFICIAL NEURAL NETWORK
Author(s):
P Dhandapani, Dr T Anuradha
DOI Number:
Unsubscribe
Keywords:
Rainfall Forecast, Backpropagation Neural Networks, Delta Learning Rule, Heidke Skill Score (HSS)
Abstract
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

Last Date: 15th March 2024

Call For Paper

Volume 10 Issue 10

Last Date for paper submitting for March Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews