Neural networks fusion for temperature forecasting

Abstract

Weather conditions have a direct relationship with energy consumption, touristic activities, and farm tasks. By means of the fusion of artificial neural networks, this work presents a system with a general method that obtains an accurate temperature prediction. The objective is temperature, but the method is easily scalable to obtain any other meteorological parameter; this is one strength of the model. This research carries out a temperature prediction modeling that contributes to obtain better results with different applications as energy generation or in other different fields such as tourism or farming. The database contains data of 5 years from stations located in Gran Canaria at Gran Canaria Airport and in Tenerife at Tenerife Sur Airport. Data are collected hourly, what means more than 100,000 samples. This quantity of samples gives sturdiness to the study. With this method, our best result in terms of mean absolute error and using data from meteorological stations in Canary Islands is 0.41 °C.