Prediction of Seasonal Temperature Using Soft Computing Techniques: Application in Benevento (Southern Italy) Area

TL;DR

This study applies Artificial Neural Networks and Genetic Programming to forecast seasonal temperatures in Benevento, Italy, demonstrating low error rates and providing explicit predictive formulas, advancing soft computing applications in regional climate prediction.

Contribution

It introduces the use of neural networks and genetic programming for seasonal temperature forecasting in Southern Italy, with genetic programming providing explicit predictive formulas.

Findings

Both methods show low error rates.

Genetic programming offers explicit predictive formulas.

Effective temperature forecasting in a specific Italian region.

Abstract

In this work two soft computing methods, Artificial Neural Networks and Genetic Programming, are proposed in order to forecast the mean temperature that will occur in future seasons. The area in which the soft computing techniques were applied is that of the surroundings of the town of Benevento, in the south of Italy, having geographic coordinates (lat. 41{\deg}07'50"N; long.14{\deg}47'13"E). This area is not affected by maritime influences as well as by winds coming from the west. The methods are fed by data recorded in the meteorological stations of Benevento and Castelvenere, located in the hilly area, which characterizes the territory surrounding this city, at 144 m a.s.l. Both the applied methods show low error rates, while the Genetic Programming offers an explicit rule representation (a formula) explaining the prevision. Keywords Seasonal Temperature Forecasting; Soft Computing; Artificial Neural Networks; Genetic Programming; Southern Italy.