Effect of climatic parameters on soil temperature estimation by hybrid refrigeration simulation algorithm

Studies of geography to urban planning, climatology, civil construction and agriculture also conducted in an area to estimate soil temperature is dependent on the area. In this study, at 50 cm soil depth by using simulated annealing hybrid algorithm and Support Vector Machine single model in the city of Adana in Turkey weather station was simulated. The results showed that the hybrid model simulation of refrigeration is based on vector support machine with 0.986 nash-sutcliuf about criteria, the absolute error mean square error equal to 0.732 and root mean square error is equal to 0.86 well estimated. As well as single machine backup rate vector model for benchmarking Nash-sutcliuf about 982.0 and the absolute error mean square error equal to 0.793 and root mean square error is equal to 0.96 is obtained. The results showed that hybrid algorithm simulation of refrigeration could be fitted as a means of efficiently in deep soil temperature modeling.