Assessment of Data-Driven Models in Downscaling of the Daily Temperature in Birjand Synoptic Station

In this study, seven models such as multivariate regression, contemporaneous autoregressive-moving average (carma), carma-arch (autoregressive conditional heteroskedasticity), support vector regression (svr), adaptive neuro-fuzzy inference system (anfis), support vector machine (svm) and genetic programming (gp) were investigated to downscaling the maximum daily temperature of birjand synoptic station using 26 predictor’s parameters that resulting from the fifth intergovernmental panel on climate change (ipcc) report and compared. the max daily temperature values measured from 12/03/1961 until 20/12/2005. in all mentioned methods from 26 predictive parameters using the pearson correlation test, 15 parameters were selected that have a high correlation with the max daily temperature values. the results of evaluating the accuracy and model indicated that from the same models such as gp, anfis and svm, the gp model has the least amount of errors (about 4 °c) and in the regression models (multivariate regression and svr), svr have been lowest error rate (about 1 °c) and the highest accuracy in simulated max daily temperature values. the results of the investigation the error rate of the mentioned models indicated that after the svr model, two carma and carma-arch stochastic models have high and acceptable accuracy about 97 percentages. in general, the results of the simulation the max daily temperature indicates the best accuracy of regression toward another methods. one of the reasons for the results of the svr model is to optimize the parameters of the model using the ant colony algorithm for estimating the maximum temperature values of the birjand synoptic station.