WorldCIST'14 - The 2014 World Conference on Information Systems and Technologies

Full Program »

Toward Evolutionary Nonlinear Prediction Model for Temperature Forecast Using Less Weather Elements

This paper presents the notion of evolutionary nonlinear prediction technique for temperature forecast based on GP (Genetic Programming). The linear regression method is widely used in most of numeric weather prediction model. Their performances are acceptable, but some limitation is existed for nonlinear natures of the weather prediction. We explain how to apply symbolic regression method using GP for the nonlinear prediction model using less weather elements. In order to verify the possibility of the proposed method, experiments of temperature forecast for the sampled locations in South Korea are executed.

Author(s):

Kisung Seo    
Seokyeong University
Korea, Republic Of

 

Powered by OpenConf®
Copyright ©2002-2013 Zakon Group LLC