Predicting temperature is one of the most important phenomena studied in climatology studies that from the user's perspective to many human activities, especially agricultural activities linked. Planning against the dangers of this phenomenon is necessary to studies on forecasting methods and the effects of climate signals on the minimum and maximum temperature taken. Due to limitations such as insufficient data available, low accuracy and high error in Hakol statistical methods in this study using fuzzy inference nervous system and genetic algorithm in MATLAB software boxes used as an efficient method to predict temperature. The model used in this study includes a hidden layer and an output layer, fuzzy system used in this study is Sugeno model. In this method, non-linear relationships between variables are assumed. In this study, we tried to predict the minimum and maximum temperatures in the city of Khorramabad (using the variables of sunshine, and climate signals) are necessary. For this purpose, the capabilities of fuzzy neural network and genetic algorithm were used to make the prediction. Monthly and daily statistical model inputs of signals in the area of climate and sunshine period (2014-2008) and output data minimum and maximum temperature. The neuro-fuzzy model, in the period (2014-2008) in estimating the minimum was trained and the maximum temperature is conducted using a genetic algorithm in 945 years. The results indicate that the fuzzy neural network with genetic algorithm capable of more and high accuracy to predict the minimum and maximum daily temperature and monthly than usual statistical methods as temperatures with reasonable accuracy predict with a confidence level of 90%.

A. Jain, R.W, Mc clendon, G, Hoog en Boom, R, Ramyaa, (2003) prediction of frost for fruit protect tian using artificial neural networks, American society of Agricaltural Engineers, ASAE paper, 3073-3075.

Agha Moradi, Bisotoni, O, (2015) present a hybrid model based on genetic algorithms and artificial neural network to measure the credit risk of customers real Bank of Tejarat (branch of Tehran), University of Arak

Ahmadi, Ismail, (2003), classified Bushehr precipitation changes using model-based self-organizing neural networks ANN (SOM) Master thesis, University of Teacher Education, Department of Geography.

Ashrafi, KH, Shafipour Motlagh, Majid, Bokhar Arabi, B, Ghasemi, Laden, (2009) predicted a rise in temperature due to climate change in Iran using neural networks, NWP Conference, 80, Institute of Meteorology, Tehran

B.A, smith, R.W, MC clendon, G, Hoogeboom, (2009) Artifical neural networks for automated year- round temperature prediction, computers and Electronics in Ag ricul-ture,68,52-61.

B.A, smith, R.W, MCC lendon, G,H hoogenboom, (2006) Improving air temperature pre-diction with artificial neural net worles, Intelligence 3 ,179-186.

Davoudi, S.M.M. (2014). Parame terization scheme utilizing a on pimentional cloud model, monthly weather Review

Fernando, C, kampis,G,and Eors, S, (2000). Evolvability of Natural and Artifical systems, the European future technologies conference and Exhibition, 73-76.

Ih shaish, H, cortes, A, senar, M, A, (2012) paraller multi-level Genetic Ensemble for mumerical wather prediction Enhancement, procedia computer science, 9,270-285.

Kia, M., 2008, neural networks in MATLAB, publications Qian green computer

Mehdi Ebrahimi, Sh, Bashari Seghale, M, (2011) modeling and prediction of monthly discharge current case study River, the fourth Iran Water Resources Management, Amirkabir University of Technology, Tehran

Rahim Zadeh, F., (2011), Statistical Methods in Meteorological Studies, Tehran, 1

Rahimzada, F, Asghari, Ahmad, (2004) a view on the difference between the minimum and maximum rate of increase in temperature and decrease in diurnal temperature range in Geographical Research, 2, 155

Shakiba, Hanieeh, (2013), to examine and forecast annual and monthly minimums studied using artificial neural networks Karaj

shyi, mch, senior , M, Jeng, R.H, (2000) temperature prediction using fuzzy time series, IEEE TRAWS sactions on systemes, man, and CYBERNEtics,2,30.

SU,Z,prieto,D.F,Timmermans, J, chen, X, Hunger shoefer, k,Roe beling, R, Schroder, M, schulz,J,stammes, P, wang, p,wolters,E, (2014) first results of the earth observation water cycle multi-mission observation strategy (wacmos), International Journal of Applied Earth observation and Geol imformation,26,270-285.

Zahiri, R., (2013) industrial application of fuzzy logic and neural networks, 2001, Ayzairan Institute Press, 107