Jaafar Ghadban - Computer engineering Faculty of Engineering and Technology Imam Khomeini International University

Knowledge of weather data or climate data in a region is essential for business, society, agriculture and energy applications. The main aim of this paper is to overview of forecasting weather by using neural networks. By usingthis technique we can predict weather data and can find the hidden patterns inside the large dataset in order totransfer the retrieved information into usable knowledge for classification and prediction. In this paper, a neuralnetwork-based algorithm for predicting the air temperature for a future time. I have used Back Propagation Neural (BPN) Network for modeling and it was trained on 2 years weather data which are of (2013 – 2014) for Qazvin city in Islamic republic of Iran. The weather data set comprising 18455 records containing attributes like temperature, atmospheric pressure, humidity and wind speed. The prediction error is found to be very less and the curve of learning data converges very sharply

Artificial Neural Network (ANN), Back Propagation Neural Network (BPN), forecasting weather