Open AccessRainfall Forecasting Based on Surface Data of Chennai Region Using Artificial Neural Networks
Publication year - 2020
Publication title -
journal of science and technolgy
Language(s) - English
Resource type - Journals
ISSN - 2456-5660
DOI - 10.46243/jst.2020.v5.i6.pp26-36
Subject(s) - artificial neural network , wind speed , mean squared error , data set , meteorology , relative humidity , matlab , training (meteorology) , backpropagation , environmental science , training set , computer science , statistics , data mining , mathematics , artificial intelligence , geography , operating system
In this study, we developed user friendly rainfall forecasting system based on Back propagation NeuralNetwork using MATLAB 7.10 to forecast Hourly rainfall in Chennai region. The dataset of 31488 samples has beencollected from Nungambakkam Meteorological Station, Chennai for the period of 2005 to 2015. The data wasorganized into day-wise hourly recordings as well as day-wise, maximum, minimum, average data of RelativeHumidity (RH), Temperature, Pressure and Wind Speed along with Rainfall data. The collected dataset has beenused both for training and for testing the data. The developed system gives more accuracy of 94.8197% when thetraining data set is 55% and the testing data set is 45% with least Mean Squared Error (MSE) value 0.012437.