---

Long time series are needed for analysis of time variation, trend of extreme events, risk estimation and possible events. One of the most important time series in geographical and climatic science is daily maximum and minimum temperature. These two parameters use daily evapotranspiration estimation, determination of water balance and climate change study. Maximum and minimum temperature are measured in meteorological stations. However, different statistical years, deficiency in statistical data and error of measurement cause variation in time series. Therefore, reconstruction of time series is very important. This research evaluates reconstruction of daily extreme temperatures to nearest neighbor and artificial neural network methods for five stations in the west of Tehran Province. In the nearest neighborhood method correlation between respective maximum or minimum temperature is used. Whilst in the artificial neural network using meteorological stations network the minimum and maximum daily temperature are reconstituted. Neural network used in this research is a multilayer feed forward network with back propagation algorithm and hidden layer. Results show that artificial neural network method had least mean absolute error for all stations compared to the nearest neighbor method. With increasing distance of the station the estimated error increases in the nearest neighbor method. Accuracy of the two methods in estimating daily maximum is more than the daily minimum temperature

---

This study aimed to identify factors leading to slope instability, Maps preparation, determine potential areas mass movements and risk zoning in the Upper Basin Komanaj Chay. That is one of the important basins in the northern city of Tabriz, by Using logistic regression models and artificial neural network done. This basin due to topography, tectonics, geology, stratigraphy, and the climate is prone to a variety of slope instability, this phenomenon always occurs. According to the study variables such as altitude, slope, aspect, type of formation, distance to fault, distance from the river, land use, distance from the road, as the independent variable And distribution of unstable slopes as the dependent variable using logistic regression models and artificial neural network was analyzed .The results showed that the most important factors in the occurrence of slope instability in the basin are as follows: Elevation, distance from the river, lithology, faults, slope and aspect More than 50 percent of instability range in height from 1850 to 1520 in the study area dip 32-17 degrees, at a distance of 200 meters from the canal and 500 meters from the fault occurred. According to the results of a very high percentage of areas the risk of neural network and logistic regression models respectively 5.6 and 8.3 percent is the mainly areas close to the drainage network which includes the lithology of these areas are located in areas with lower resistance. Statistical methods logistics showed a lot of reflects of faults and lithology in this areas is based Landslide. Evaluation ROC indicator showed that the model was assessed using logistic regression model is 0.894 and neural network models is 0.826. In fact, both models show a high value and suggest that mass movement and slope instabilities observed a strong relationship with probability values derived from logistic regression models and artificial neural network model. The results of this study can be useful risk management slope instabilities and control is deteriorating factors.