فصلنامه سنجش از دور و GIS ایران
سال سیزدهم شماره 2 (پیاپی 50، تابستان 1400)

Drought evaluation is important in terms of spatial and temporal for planning to reduce damages in the Kordestan province. In this research, Standardized Precipitation Index and the Enhanced Vegetation Index have been used from the extracted satellite images for determinants of drought. so, the statistical data of Meteorological stations including maximum monthly temperatures, total annual precipitation and the images of MODIS sensor have been employed. By comparing meteorological parameters such as average annual temperature, rainfall and the comparison of maps of the Standard Precipitation Index and Enhance Vegetation Index, the condition of drought has been investigated in the region in a 17-year period. The results of the two SPI and EVI indices indicate that the drought is due to rain changes have in the west-to-east direction. This phenomenon is more severe in the eastern regions whereas vegetation sensitivity and the fluctuation of its variations have been affected by precipitation changes in the north-to-south direction over the region. In this way, the southern regions have shown higher sensitivity. Southern regions are generally more vulnerable to droughts, especially in the south-east of the province. Regions with high drought sensitivity make up about 10 percent of the area regarding the regions in the province, whereas 91 percent of the area of regions with very high drought sensitivity is places where the landuse involves growing wheat with rain water.

Albedo is one of the parameters needed in environmental and climate studies. Therefore, examining its temporal and spatial behavior can be a tool for understanding environmental changes. The MODIS sensor produces Albedo the surface of the earth continuously on a global scale with low spatial resolution and provides free access to the public. In this study, for measuring the Analysis of Barriers to Albedo Observations in Iran, The first daily data of Albedo MODIS Sensor in the kernel of Iran was downloaded from the MODIS website during the period from 2000/03/20 to 2018/12/31 for 6867 days. After mosaic tiles, based on 48 billion observations, the long term frequency of land surface Albedo Iran was calculated separately for each season. The results showed that the limiting factors of satellite view were different at times and places. Humidity has a limiting role in summer, especially on the coast of Oman. In the winter, especially in the Alborz and the Zagros Mountains, cloudiness is a limiting factor. In addition to the humidity and cloudiness factors, Dust storms are also known to limit albedo harvest. Surveys of 394 ground stations proved that more than 70 percent of the factors listed were reported when the satellite was unable to measure albedo.

The development of automatic road and building detection systems in aerial imagery are always faced with challenges such as the appearance of buildings, illumination changes, imaging angles, and the density of roads and buildings in urban areas, to name a few. In recent years, employing multi-layered approach in artificial neural networks, known as deep neural networks, has attracted many researchers in this field (and the other fields alike), achieving stunning results. However, the use of fully connected layers in this approach, significantly increases the average processing time and results in an overfitted model. In addition, in most of these methods, a single-class approach has been considered. That is, detecting the roads and the buildings from natural scenes is not possible at the same time, and therefore, it is necessary to build separate binary models for each of them. The main goal of this research is to design a new architecture by which the produced model can be able to simultaneously detect roads and buildings from natural scenes, and thus minimizing the complexity of the classification process. In addition, in the proposed architecture, excluding all fully connected layers from the traditional multi-layered architectures is considered in order to reduce the average processing time. The results of the experiments performed on the Massachusetts dataset, show that the proposed architecture performs 38% faster than the other deep neural network-based methods, and also increases the accuracy by an average of 2%.

The basis for proper planning and management is to have accurate and timely statistics and information. One of the most important statistics of the agricultural sector is the annual production rate of each crop, which also depends on the area under cultivation of crop and its efficiency. One of the tools that can calculate the area under cultivation in the least time, with low cost and with high accuracy is remote sensing science and technology. In this study, two classification methods including artificial neural networks and support vector machine with different kernels are used and the area under cultivation of major crops in the region consisting of 8 classes is estimated. According to the results, the overall accuracy of the artificial neural networks and support vector machine was 97.74% and 97.96% with a kappa coefficient of 0.97 for both methods, indicating that both methods are good for separation and classification of agricultural lands in the area. Based on the overall accuracy, it can be concluded that the two methods of classification have almost the same results in the region. Also, based on the results of the user's accuracy for the four crops including Alfalfa, Rice, Onion and Melon, the support vector machine method performs better than the neural network method and also for dry and water Wheat, Sorghum, and Pasture, the neural network method out performs the support vector machine in the region.

Today's, one of the impacts of human activities in the form of land use change is the lack of attention to environmental constraints that impact the appearance of the environment, and have devastating impacts on natural ecosystems such as National Parks and Protected Areas. Therefore, identifying the trend of changes in land surface features is essential to understand the relationship between humans and the environment. In this study, with the aim of evaluating the trend of land use changes through Landsat TM satellite images in 1989 and 1999, +ETM in 2009, and Landsat OLI_TIRS in 2019, using multi-spectral data capabilities and digital image processing. Land use of the area was classified into five classes, constructed lands (residential, commercial, industrial, and pathway), water land use areas, agricultural and garden lands, high-density pastures, and low-density pastures. According to the results, low-density pastures in 2019 compared to 1989 has been associated with an increasing trend. Therefore, results indicate that during, studied years, the most trend of changes in high-density pastures have decreasing and low-density pastures due to the high number of nomads (destruction of vegetation due to excessive and untimely grazing of livestock), has an increasing trend. In addition, in this area, due to the lack of permanent settlements and legal restrictions, use of agricultural and garden lands has been facing a declining trend, and it is worth noting that agricultural operations in this area in some cases only to cultivate alfalfa along the river Lar is limited to provide forage for nomadic livestock. Among other existing land uses, water areas have been increasing years under the study, although in 1999 due to the increased presence of nomads in pastures, number of livestock over capacity, and in addition conservation status of area and, lack of protection restrictions (not upgrading area to a national park during this period), a decreasing trend can be seen in this land use. Other land uses in this area include built-up, in 1989, compared to 2019, there has been an increasing trend, one of the reasons for the increase in this land use is development of roads and increase of access roads to this area year under the study. Given that the animal and non-animal life in the area as well as soil survival against erosion depends on vegetations, the decreasing trend of vegetation and increasing soil degradation and erosion can serve as a warning to pay more attention to the biology condition in this area. Also, according to the results of the study of the most important factors affecting the trend of land use change in the area, the physical-environmental dimension with a weight coefficient of 0.465, economic-institutional dimension with a weight coefficient of 0.315, and demographic-social with a weight coefficient of 0.223, respectively.

The rail transport system consists of the interaction of a set of equipment and operations that determine the capability and capacity of a rail system in freight and passenger transport. For this purpose, it is important to calculate the capacity and predict how it will change, and knowing it will be of great help in improving the level of operation of the railway network. There are several methods for calculating capacity that can be used depending on the type of network and how it is used. To calculate the capacity, the capabilities of spatial information systems are used and with the help of a web-based spatial information system, the operational capacity of the rail network is determined in a new way and with more efficiency than conventional methods. For this purpose, a GIS-based environment that is connected to various databases of the Railway Company of the Islamic Republic of Iran, including the travel database, is used and while observing the current capacity of the network, through multivariate linear regression, the capacity of the rail network in It determines the future. The present study, through linear regression, predicts railway capacity in a case study in Iran for the three selected routes and identifies important blocks for investigating the effect of spatial parameters in determining the capacity of the railway network. Slowly Based on the available data of 1996 (extracted from the Railway Spatial Web Service), capacity forecasting was performed in 1997 in the GIS environment. The results showed that the capacity utilization of the selected routes for freight trains was 82%, passenger routes 56%, 62% return and 79% combined routes. Also, the accuracy of model prediction for freight trains is 35% better than passenger trains, which is due to the difference in speed change and maximum speed allowed for these two types of trains, and modeling accuracy is directly related to the type of part. Route (passenger, freight and combined), so in the passenger route, the modeling capacity of passenger trains was approximately 45% more accurate. Similarly, on the freight route, the estimation of the capacity of freight trains was associated with approximately 45% higher accuracy than that of passenger trains.

The purpose of this research is to determine the groundwater potential of areas and to prioritize the factors affecting it using the maximum entropy method and the new height above the nearest drainage index. In the present study, 14 effective indicators have been used for groundwater potential including topographic, geological, climatic, hydrological and land use factors as well as a new height above the nearest drainage index (HAND). First, the factors were divided into two parts including of topographic and other factors such as geology, climate, hydrology and land use, and groundwater potential map was prepared based on them. Then, with the integration of the indices, the final groundwater potential map was prepared. Of the 2547 springs, using the Mahalanobis distance method, 60% of the data was classified as test data and 40% as validation data. The results showed that according to topographic indices, other factors and the combination of all indicators, 38.5, 27.4 and 34.7 percent of the area have groundwater potential, respectively. Also based on Jackknife Diagram, the altitude, land use, slope, relative slope, HAND index and lithology were the most important factors influencing groundwater potential. The area under curvature (AUC) based on ROC diagram indicates accuracy of 83, 83 and 85% (very good) at the training stage and 82, 81 and 84% (very good) in the validation step based on topographic indicators, other factors and the integration of all indicators. Given that the HAND index has been an effective factor of groundwater, it has a crucial role in identifying areas with groundwater potential.