Development of Artificial Neural Network (ANN) for lightning prediction under Malaysia environment / Jeremy AK Stewart Bedimbap

The purpose of this project is to present the development of Artificial Neural Network (ANN) for lightning prediction under Malaysia environment. The study of Artificial Neural Network is very important in achieving the objective. The system was implemented using the data from Malaysia Meteorological Service (MMS) and Tenaga National Berhad (TNB) for weather data and lightning data respectively. In the proposed method, a three layer back-propagation neural network with Levenberg Marquardt algorithm has been developed and predicts the output data for the next four hours. Through training, ANN will able to recognize the pattern of input data and predict for the future output. The Levenberg Marquardt technique has been used to train ANN that receive input data and select the best output with the smallest error between output data and target data. The understanding of lightning characteristic is also important in this project because its help to improve the performance of the ANN system in predicting lightning activity. All the simulation in this project is using Matlab software.