Temperature alteration plays special role as one of the most basic climate elements. So inspection of temperature alteration and anticipation has scientific- applied magnitude. In this study inspection of several cases of statistical characteristics of monthly­ average, maximum and minimum temperature and illumination of their alteration method­, temperatures predictability by ANFIS is evaluated­. Applied data is over 288 months during 24 years of statistical period since January of 1987 until December of 2010 through synoptic stations of Pars Abad, Ardebil and Khalkhal. According to equations of data lineal process­, lineal process of temperatures through all of the stations is positive and­ additive­. Lineal process gradient in minimum temperature is more than other­ maximum and average temperature. Less amplitude more variance and standard aviation and­­ data ­predictability is more. According to present article adaptive Neuro – fuzzy inference system mostly has acceptable function through anticipation of monthly minimum, maximum and average temperature in the stations of Ardebil province.

Rainfall is one of the most important components of the water cycle and plays a very important role in the measurement of climate characteristic in any area. Limitations such as lack of sufficient information about the amount of rainfall in time and space scale and complexity of the relationship between meteorological elements related to rainfall, causes the calculation of these parameters using the conventional method not to be implemented. One method of evaluating and forecasting of rainfall in each region is time series models. In this research, to predict the average annual rainfall synoptic station at Mahabad, Uromiya and Mako in West Azarbayejan provience during 1984-2013, linear time series ARIMA was used. To investigate model static, Auto Correlation Function (ACF) and Partial Auto Correlation Function (PACF) was applied and with differencing method, the non-static data transformed to static data. In next step, stochastic models to estimate the annual rainfall average were used. With regard to the evaluation criterion such as T, P-VALUE < 0.05 and Bayesian Information Creterion (BIC), ARIMA (1,0,0), ARIMA (0,1,1) and ARIMA (0,1,1) models was determined as a suitable model for predicting annual rainfall in the three selected stations at Uromiya, Makoo and Mahabad. In the following, the annual rainfall for 3 (2013-2016) years is forecasted which based on rainfall data in that time, the adjusted model was acceptable.