Canadian Weather Analysis Using Connectionist Learning Paradigms

In this paper, we present a comparative study of different neural network models for forecasting the weather of Vancouver, British Columbia, Canada. For developing the models, we used one year’s data comprising of daily maximum and minimum temperature and wind-speed. We used a Multi-Layered Perceptron (MLP) and an Elman Recurrent Neural Network (ERNN) trained using the one-step-secant and Levenberg-Marquardt algorithms. To ensure the effectiveness of neurocomputing techniques, we also tested the different connectionist models using a different training and test data set. Our goal is to develop an accurate and reliable predictive model for weather analysis. Experimental results obtained have shown Radial Basis Function Network (RBFN) produced the most accurate forecast model compared to ERNN and MLP.