---

Change detection is a basic requirement in management and evaluation of natural resources. Landuse change map which is the result of land change processes can be obtained from multi-temporal images.Various techniques have been presented for landuse/lancover change detection. In this study, images of landsat TM) 1988 and landsat (ETM+) 2001 were analyzed using 4 change detection techniques in 80470 hectares in Daresher region, Ilam Province. Change detection techniques considered were standardized and non-standardized principal component analysis (PCA) differencing, applying Canonical component analysis (CCA) differencing and Tasselled Cap (KT) differencing that all are in transformation group. Since these methods require determining threshold, therefor, statistical methods for determining the threshold level was used being achieved from the change threshold. In this study, threshold level was set at ±1 standard deviation from the mean. After determing optimal threshold, areas having decreasing change increasing change and no change were determined. Based on ground data and field work, aerial photo of 1:20000 and Google Earth, accuracy assessment of change detection techniques was carried out using overall accuracy and Kappa coefficient. According to the results, PC1difference image of CCA transform with overall accuracy of 98 and Kappa coefficient of 0.97 showed the largest accuracy among applied change detetion techniques in the Daresher region

---

Desertification assessment tries to set the most important components of desertification in each region, and finally provides the desertification potential map by evaluating indexes in each working unit. Given the importance of these maps, despite the development of techniques and quantitative methods in recent years, having the methods with less error, more reliability and with higher quick and ease are still important. Since the desertification process results by interaction of multiple variables over time, a method for zoning should be used that can maintain accuracy, speed and ease of access to the result. The purpose of this study is to evaluate the accuracy of ''principle component analysis model''. In order to reduce the aspects of the studied problem and the ease in achieving results, this method can consider the principle components of the problem and then removing the other components. Also by using the software it can increase the accuracy, speed and ease of zoning process. Analytics in the study area showed in terms of the desertification potential, 9.35 % of study area in Class VI or very high, 25.6 % in class IV or high and 41.85 % in class II or relatively moderate which are allocated the largest in the study area. Also the quantitative value of desertification potential in whole study area from all of the components was obtained as 3.29 (relatively High).

---

The Central Zagros cold season with abundant snowfall that other event such as climate, influenced by the atmosphere circulation patterns and distribution of surface pressure of Earth. In this study, to determine weather patterns and dynamical conditions of heavy snowfall in the mountain roads, daily data of synoptic station: Borougen Branch, Koohrang and Lordegan for the year 1987- 2010 of Iran Meteorological Organization received. In the following, days of heavy snow to use of index measure rainfall more than 15 mm and below-freezing temperatures and check the monitor code 70-75 (Code scout snow), 136 days of heavy snow was determined. In order to determine weather patterns, principal component analysis matrix array S on 500 hPa geopotential height data was used. The results showed that heavy snowfall in the mountainous roads of Zagros cause to seven synoptic patterns. As trough of the east Mediterranean is west of Iran and study area is close to the region's extreme volatility. At the same time low pressure gradient in north and south of the study area Caucasus is severe, respectively, associated with strong positive vorticity in the study area, and strong negative vorticity on the East of Oman in the south and Caucasus area in north. However, low pressure center and the North East with strong positive vorticity and high pressure of Siberia to the eastern border of Iran is the continuation and sustainability under the dynamic conditions in the study area. During heavy snowfall strong high pressure of Siberia combined from the north of Iran and the Caspian Sea with high-pressure of Caucasus in relation to Polar vortex in the middle levels of the atmosphere Caucasus cold air streams in the study area. The humid currents from the Black Sea and the Mediterranean by the cyclone flow in the West of Iran through the Persian Gulf region flows to the Zagros Mountains. In all atmospheric patterns, the temperature of zero degrees in the south on the Persian Gulf region and the arrival of masses of cold and wet down to widths And heavy snowfall in the roof of Iran.

---

Evaporation is one of most important parameters which are affected by many variables such as rainfall, wind velocity, sunny hours, and relative humidity etc. Evaporation estimation is important for any area with surface water resources because of its effect on dam lakes, precipitation-runoff modelling, river area performance, water management – calculating amount of water that plants need and planning for watering and so on. Evaporation can have significant effect on water balance of a river or a reservoir and it may be cause water level to decrease.

Due to hydraulic system complications caused by statistical information imperfection and determining all parameters involved, complete hydraulic system modelling is impossible. At such circumstances using al mathematical modelling system will be considered. 

Matherials & Method

In this study we tried to estimate pan evaporation using two models including Artificial Neural Network (ANN) and Support Vector Machine (SVM) with data preprocessing (gamma test and principal component analysis) to determine affective inputs into two models. For this matter data gatherd from three synoptic stations at Astara, Kiashahr and Talesh at Guilan province has been used. Synoptic stations data includes evaporation, wind velocity at two meter altitude, temperature (minimum, average and maximum), humidity (minimum, average and maximum), sunny and rainy hours. Statistical period of data for Astara and Talesh synoptic stations were 1384 to 1393 and for Kiashahr were 1385 to 1393. 80 percent of meteorology data were used for calibration and other 20 percent were used for model validation. In this study we used multilayer perceptron artificial neural network with sigmoid tangent function and 1 to 20 neurons for hidden layer and support vector machine with radial based kernel function.

Calculations has been made in to section with two data preprocess methods. At first section input variable has been selected by gamma test and pan evaporation estimation was made by both models. At second section modelling has been pulled out by input variables selected by principal component analysis.

Discussion of results

At gamma test section pan evaporation estimation parameters were as follows: minimum temperature, maximum humidity, minimum humidity, rainfall and sunny hours for Astara station; maximum temperature, minimum temperature, minimum humidity, rainfall and sunny hours for Kiashahr station and maximum temperature, minimum temperature, maximum humidity, average humidity, rainfall and sunny hours for Talesh station. According to principal component analysis results on Astara, Kiashahr and Talesh stations, five, five and four principal component were used in modeling these stations respectively. At first section input compound determined by gamma test to estimate Pan evaporation of the selected stations were used. Pan Evaporation estimation results shows that at Astara station GT-ANN model has less root mean square error than GT-SVM model and beter performance. Pan Evaporation estimation at Kiashahr station was done suitably with both models. At this station GT-SVM had a better performance with root mean square error of 1.295 compared to GT-ANN model with 1.356.

At Talesh station both models had close results but results for GT-SVM were more accurate compared to GT-ANN. Nash Sutcliffe coefficient attained for Astara and talesh stations acknowledges their  excellent results and for Kiashahr station shows the satisfactory results.

At second section modelling were done by using selected inputs by PCA preprocess method. Accordint to results, PCA-ANN model had better performance estimating pan evaporation at Astara and talesh stations than PCA-SVM model as its root mean square error was lower. Value of Nash Sutcliffe coefficient shows the suitable performance of both models at both stations. PCA-SVM model had better performance estimation pan evaporation than PCA-ANN with lower root mean square error at Kiashahr station. Nash Sutcliffe coefficient of PCA-SVM model was 0.666 and for PCA-ANN model was 0.634 which shows the satisfactory performance of both models.

Conclusions

Results shows the good performance of preprocessing methods (principal component analysis and gamma test). Actually performance of GT-ANN, PCA-ANN, GT-SVM and PCA-SVM models performance estimating pan evaporation of each one of the stations are very close to each other. This similarity is caused by performance of gamma test and principal component analysis preprocessing methods. Principal component analysis converts input variables to independent principal component using linear relation between input variables. Actually this method reduces the effect of the variables with similar information by giving them lower factor. But in gamma test method consider to gamma factor attained from various input compounds, variable that has a negative effect on output will be determined and eliminated from final input compound. As we said before, nature of none linear Gamma and linear PCA methods are different but when PCA method decreases the factor that is eliminated in gamma test to a small value, inputs determined by both methods will be close to each other. This can be one of the reasons that close the estimating models results to each other. So we cannot recommend one preprocessing methods better than the other. We can conclude that for estimating pan evaporation at these stations both preprocessing methods are suitable.

According to results PCA-ANN for Astara and Talesh and GT-SVM model for Kiashahr station had better performance than others.

Although both models had acceptable performance estimating pan evaporation of stations but SVM model results were better than ANN model.

---

Attention to Ardabil province is one of the important centers of wheat cultivation, determining the level of cultivation will be of particular importance in economic and political planning and can ensure the country's food security, but in the past, most traditional methods, such as field measurement, etc., have been used to determine the level of crop cultivation, which has many errors, In this study, we tried to use Landsat 8 satellite imagery, Vegetation Indices (NDVI, SAVI, DVI, GVI, IPVI, RVI), Principal components analysis (PCI), Optimum Index Factor (OIF), and classification algorithm to estimate the maximum probability of wheat cultivation area in the study area. Based on the results of main components analysis, more than 99% of data variances were explained in three main components and the best color combination of the OIF index was determined by bands 5, 6, and 7 with a numerical value of 8383.73. Also, the results showed that wheat cultivars under cultivar 94-95 in the studied area with kappa coefficient is 0.87 and the general accuracy of 95.2% were 59203.07 hectares and According to the statistics of agricultural Jahad official in Ardebil province, which is about 62480.21 hectares, In other words, the difference is 5.24% or about 3277.14 hectares which seem to be acceptable. Therefore, it can generally be concluded that Landsat 8 images, Principal components analysis, and Optimum Index Factor are highly effective in determining the level of wheat cultivation.