Lightning Prediction Using Fuzzy Logic Technique

Lightning is an event where electrical charges are released from the clouds. A lightning prediction system is used to estimate the probability of a lightning strike according to the changes in the environment. By the identification process, the safety of life and structures could be protected from lightning strikes. This paper is to develop an algorithm for lightning prediction using the fuzzy logic technique. A few tests have been conducted to evaluate the performance of the system. For the validity test, the system gives a positive result of more than 90% accuracy for being able to predict the imminence of lightning. The consistency test shows that the system was able to predict lightning repetitively at least 1 hour before lightning activity happens. The sensitivity test proves that lightning prediction relies heavily on the humidity and that 70% is the threshold to change between not imminent to imminent. The linearity test once again proves that humidity has a direct relationship that could affect the prediction of lightning. The stability test shows that the system will be stable after predicting the 6th to 7th hour data. Finally, it could be concluded that the accuracy of this system in lightning prediction is more than 95% after being tested with real data from the meteorological department.