International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 89 - Number 16 |
Year of Publication: 2014 |
Authors: Himadri Chakrabarty, Sonia Bhattacharya |
10.5120/15712-4362 |
Himadri Chakrabarty, Sonia Bhattacharya . Prediction of Severe Thunderstorms Applying Neural Network using RSRW Data. International Journal of Computer Applications. 89, 16 ( March 2014), 1-5. DOI=10.5120/15712-4362
Severe thunderstorm is a seasonal and mesoscale atmospheric event. The sudden increase in wind speed and the other weather features during this event have various destructive effects on the people. Correct forecasting with enough lead time is very important to minimize the damages occurring in day-to-day life. In this paper, artificial neural network technique has been applied to predict the severe thunderstorm. Multilayer Perceptron (MLP) has been applied on the weather parameters of moisture difference, adiabatic lapse rate and vertical wind shear which were recorded by the radiosonde-rawind (RSRW) in the early morning at 06. 00 am local time. MLP classified and predicted 'severe storm' and 'no storm' days in this work correctly nearly up to 70% having around 12 hours lead time.