Fusion of artificial neural network and fuzzy system for short term weather forecasting

Abstract

Weather forecasting is the challenging problem for the modern life. Some researches have been conducted to design the accurate prediction in some past years but still it is incomplete. In this paper, we propose the system of short period weather forecasting designed based on the current weather parameter consisted of temperature, humidity, air pressure, wind direction and speed and present weather condition. This system uses fusion of feed forward artificial neural network (ANN) and fuzzy system architecture as main algorithm of weather prediction, Lavendberg-Marquadt as learning algorithm and fuzzy C-mean (FCM) as clustering method in initialisation step. Based on the system architecture, this method can predict the weather continuously despite the change of unpredictable patterns. Furthermore, this system has clear reasoning logic on the fuzzy logic instead of its adaptation ability on its neural network architecture. The performance of proposed system has accuracy up to 78% for validity among three possible weathers, i.e., shiny, cloudy and rainy.