Lightning Prediction Modelling Using MLPNN Structure. Case Study: Kuala Lumpur International Airport (KLIA)
Mastura Mohd Ramzi, Ramli Adnan, Abd Manan Samad, Fazlina Ahmat Ruslan · 2018
Lightning is one of the global phenomena that can occurs anytime and everywhere and common phenomena in the tropical region like Malaysia. Lightning can cause serious damages to human life, animal and property. Realizing the seriousness of the effects, efforts are being made to design models to predict the lightning occurrence. This study is about the application of Artificial Neural Network (ANN) in predicting the lightning occurrence using meteorological data supplied by Malaysian Meteorological Department. The area for the case study was Kuala Lumpur International Airport (KLIA). The input are meteorological parameters that consists of five parameters: temperature, mean relative humidity, mean msl pressure, mean surface wind speed and rainfall amount and the number of lightning occurrence as the output target. The ANN model was developed using MATLAB toolbox. The model was trained using Levenberg-Marquardt training algorithm. Data obtained from the simulations shows that the model was capable to predict the lightning occurrence with high Best Fit, low RMSE and good R-value which was 94.64%, 0.000786 and 0.99999 respectively.