| Autor: |
Telesca, Vito, Caniani, Donatella, Calace, Stefania, Mancini, Ignazio M., Marotta, Lucia |
| Předmět: |
|
| Zdroj: |
International Multidisciplinary Scientific Conference on Social Sciences & Arts SGEM; 2016, p925-932, 8p |
| Abstrakt: |
Climate is a primary resource for coastal tourism. It defines the length and quality of the tourist season and plays a key role in destination choices. The Mediterranean is both one of the most visited tourist destination and one of the most sensitive area to climate change worldwide. Increasingly, tourists are considering the weather of the day or week as well as other climate-related factors during the choice of holiday destination. Wind, humidity, air and water temperature, and cloud cover are few of the variables affecting visitors' decisions and satisfaction, and it is important as well for tourism businesses and tourism development in general. In this study, a stochastic weather generator and a neuro-fuzzy network was developed to generate precipitation and air temperature (max-mean-min) on a daily basis in particular for meteorological stations of coastal area in Basilicata (Southern Italy). Several simulations were carried out to build an optimal model, whose efficiency is evaluated with the RMSE (Root Mean Square Error) and the MAE (Mean Absolute Error), obtained comparing simulated and observed values. Subsequently, the developed neuro-fuzzy model was applied to generate other weather variables, such as relative humidity, solar radiation and wind velocity. The simulations showed the good performance of the neuro-fuzzy network in the data filling of the available series. The evaluation of the performance was made by comparing the values of RMSE and MAE obtained with the neuro-fuzzy method developed in this study and literature methods such as multiple linear regressions and trend line. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
