object-oriented classification

In recent decades, land use and land cover changes information has been successfully derived from remote sensing data at various levels, from local to global scale. Accurate and frequent monitoring of these changes is required for urban planning, precision agriculture, and sustainable management of land resources. The availability of remote sensing data by providing different levels of spatial details, as well as the development of satellite image classification algorithms, has made object-oriented approaches more useful in land use and land cover (LULC) classification compared to traditional approaches. Therefore, in this study, an object-oriented approach using a combination of GLCM, SNIC, and machine learning algorithms is presented to classify the LULC of a part of the lands of North Mahabad, West Azerbaijan, in 2019 using satellite images in Google Earth Engine.

For this purpose, after preparing the initial dataset, which contains the bands of Sentinel-1 and Sentinel-2 images, the ALOS digital surface model, and NDVI, BSI, SAVI, and total scattering power (TSP) indices, two pixel-based and object-oriented approaches, as well as the random forest algorithm, were used to classify land use and land cover, and their results were compared to explain the best approach in terms of the accuracy of the various classes. In the object-oriented approach, textural measures were extracted by applying the GLCM matrix to the initial dataset. Due to the increase in the number of bands, the PCA method was used to reduce the dimensions of the image. Finally, by combining the PC1 layer and the segmentation layer obtained from the SNIC algorithm, the random forest algorithm was considered to produce land use and land cover maps of the study area.

According to the research findings, the object-oriented approach performed better than the pixel-based approach in classifying various land use classes in the study area, with an overall accuracy and kappa coefficient of 86.40% and 0.8307, respectively, compared to 82.73% and 0.8028. The results of the accuracy evaluation criteria showed that the producer accuracy of most of the classes except for corn, fall irrigated vegetables, wheat, and barley irrigated in the object-oriented approach was higher than the pixel-based method, and their classification accuracy was more than 90%. Additionally, water, build-up, corn, and sugar beet classes have the highest user accuracy in the object-oriented LULC map.

The findings showed that the appropriate determination of the super-pixel size of the SNIC clustering algorithm and the use of GLCM texture criteria effectively improved the performance of the proposed approach in land use and land cover classification

This study analyzes the relationship between land use changes over different time periods and land cover metrics using data from the Barandozchay watershed in West Azerbaijan Province, Iran. To achieve this goal, Sentinel-2 satellite images for the years 2016 and 2022 were obtained from the European Union's Copernicus website. Pre-processing techniques were applied using various software tools, and the images were classified through knowledge-based and object-oriented methods in the eCognition software environment. Land use maps were generated, and land cover metrics were quantified and calculated at landscape and class levels using Fragstats 8.2 software.The results at the class level showed that the split index (SPLIT) had the highest value for the blue area, while the cohesion index (COHESION) had the lowest value in both years. The grassland class exhibited the highest SHAPE-MN and LSI indices, indicating patch disorder. If protective measures are not implemented, further degradation of grasslands in the Barandozchay watershed could occur in the coming years.At the landscape level, the results revealed a decreasing trend in most indices related to watershed connectivity. The ENN_MN index, representing the mean Euclidean distance between nearest neighbors, the CONTAG index, representing contagion, and the COHESION index, representing patch cohesion, all showed a decline from 2016 to 2022. Conversely, the LSI and NP indices displayed an increasing trend, indicating greater irregularity within the area.The findings also showed that the blue area experienced the highest level of fragmentation, whereas dry farming exhibited the least. Additionally, grassland patches demonstrated the highest connectivity, while dry farming patches had the lowest. At the landscape level, the results indicated a uniform distribution of patches in the Barandozchay watershed. The increasing number of patches, extended margins, and reduced patch size led to fragmentation and the formation of smaller, isolated patches.These outcomes highlight the ongoing land use changes and their impact on the structure and connectivity of the landscape. They provide valuable insights for land use management and conservation efforts in the study area, ensuring the sustainability of natural resources for future generations.

The plant and animal reserve of Zagros vegetation area has always been threatened and destroyed by fire in dry seasons. The lack of advanced surveying facilities has caused the location and extent of fire destruction to be recorded, as well as their impact on plant and animal species. Fire records are a good source of information in terms of reproducibility, fire-prone species, and the extent of restoration of damage caused by fires to be used in fire risk zoning and fire range expansion modeling. In this research, the methodology of discovering the traces of old fires has been discussed. This process has been done using Landsat 8 images. Various object-oriented algorithms and fuzzy membership functions have been used in image classification to detect fire damage. The accuracy of the classification is evaluated with the new QADI index. The introduction of the combined use of the near-infrared change percentage index and the NBRI47 burn index along with the use of Large, MS-Large fuzzy functions as the best classification method is one of the findings of this research. Kappa value in this method was calculated as 0.96, overall accuracy as 0.98, and Cadi value as 0.01. The area of the map resulting from the best classification showed the occurrence of a fire with an area of 62.75 hectares, which was confirmed by NASA fire detection systems and ground data. The methodology and results of this research, in addition to the possibility of being used in the scientific community of remote sensing, are also important for experts and planners of natural resources and the environment.

The water level reduction in Lake Urmia and its effects on the surrounding environment has been among the important national and international challenges in the past two decades. Therefore, this study aimed to investigate the current status and predict the future state of land use in the Gadarchai watershed, located in West Azerbaijan Province, which is one of the important sub-watersheds of the Lake Urmia basin. For this purpose, Sentinel-2 satellite images for 2016, 2020, and 2022 were obtained from the European Union's Copernicus website. Then, preprocessing methods were applied in various software environments, and the relevant images were sent to the eCognition software environment. In this environment, using various basic and object-oriented methods (especially segmentation and production of different coefficient layers), the nearest neighbor classification method was implemented, and land use maps were produced. Finally, the Markov chain model was used to predict changes in land use in future years. To verify the accuracy of the Markov chain model, the predicted land use change map for 2022 was compared with the 2022 classification map. The research results showed that with the application of basic methods, especially nearest neighbor classification, it is possible to produce land use maps with high accuracy (90% kappa coefficient). Also, by applying the Markov model, land use change maps with an acceptable accuracy level (around 80%) are possible. The final results indicate that by the year 2028, agricultural land use (13.89%), dry farming (14.1%), residential areas (0.33%), and salt pans of Lake Urmia (26%) will increase. It should be noted that the soil use class will decrease by 10.26%, and pastures will decrease by 5.35%. Overall, the final models demonstrate the high accuracy of basic and object-oriented methods and the suitable performance of the Markov model in the process of studying land use changes.

In this study, the effects of land use changes with surface temperature of karaj cityand spatial autocorrelation have been discussed using the moran index. for this purpose, landsat OLI- TM satellite imagery has been used in 2000 and 2018. first, the images were taken and the required images were applied. then classification using object orinted method and nearest neighbor algorithm was developed and the earth surface temperature was extracted with split window algorithm (imagery). The results showed that the arid land has the highest temperature in 2000 and 2018, respectively, due to the lack of vegetation, the high capacity of absorption of heat by barren soil, and the use of blue zones in 2000 and 2018 respectively, has a temperature of 38 - 25 (° C), which is دفع and has lower heat temperatures. also, the results showed strong relationship between land use and temperature. finally, the hot and cold clusters of karaj city heat islands were extracted using the hot spots analysis index (hotspot). Space autocorrelation analysis with global Moran's indices showed that the Earth's surface temperature was cluster - like. the analysis of hot spots confirmed the focus and cluster of the heat islands of karaj city in space with increasing periods of time.

Urban green space is one of the important indicators in the fields of urban planning, environmental protection and sustainable urban development policies. Knowledge of the location, amount and distribution of urban green space is a necessity. The available green space is decreasing for the purpose of developing residential lands. Today, with the progress made in the production of satellite images with high spatial and spectral resolution and remote sensing techniques, ARCGIS and image processing have made it possible to collect data and make quick and accurate decisions in environmental studies. The main goal of this research is to reveal the coverage of urban green space using object oriented processing. In order to carry out this research, IRS, Sanjande (Liss) satellite images in 2017, as well as Sentinel 2 images, bands 2, 3, 4, 8 (visible) with a spatial resolution of 10 meters were used. After making the necessary corrections, the images in the ENVI5 software environment.1 and eCognition processed that these processes include algorithms (SI, NDSI, NDVI, Brightness, etc.) to identify the area and object-based algorithms are used for evaluation. The results of this research showed that this method had a good accuracy for evaluation with an overall accuracy of 93% and a Kappa coefficient of 92%, and it was possible to detect urban green spaces using the object-oriented processing method, and it was determined that using Satellite images and object-oriented algorithms are possible to identify and investigate urban green space, and its results can be an efficient way to identify object-based algorithms and use them in future research studies

Climate diversity and land use / land cover change have a significant impact on hydrological regimes, especially in arid and semi-arid regions with critical water shortage problems. Therefore, estimating and evaluating climate change and land use and its consequences in each catchment is essential. This study examined the climate change of Kiwi Tea Basin using the data of four models of the Fifth Climate Change Assessment Report (CMIP5) under both optimistic and pessimistic scenarios (RCP8.5 and RCP4.5) using the LARS-WG6 microcirculation model. Changes in precipitation and temperature during three different periods (2040-2021, 2060-2041 and 2080-2061) compared to the base period (2019-1987) have been studied and for calibration and validation of LARS-WG6 model, observational data and output data of models with The use of F and T tests as well as RMSE, MSE, MAE and R2 indices were compared and evaluated. Based on the results of most of the models and the average of the studied models, in general, it is expected that the amount of precipitation and the minimum and maximum temperature in all the studied models will increase compared to the base period. Also, the results of evaluating land use changes with object-oriented classification showed that rangeland use with an area of 1224.18 and 1046.59 square kilometers, respectively, covered the largest area in both periods, while in 1987, residential use with an area of 3.66 square kilometers and in In 2019, water use with an area of 3.77 square kilometers had the lowest area. Also, the most modified use of rangeland use was dryland agriculture (181 square kilometers), which indicates thedestruction of rangelands

Human society and the natural environment have been affected by the phenomenon of urbanization and urban development. The physical growth of cities can have many environmental, economic and social consequences. Changing land use and land cover in cities causes many problems. The purpose of this research is to identify the urban growth and its effect on the thermal pattern using RS. The data used in this research are the images of satellites and Landsat 5 & 8, TM and OLI, TIRS sensors from 1990 to 2019, which were classified using the object-oriented classification technique and then to predict the expansion of Tabriz city for 2029. Markov model and automatic cells (CA-Markov) have been used, Split Window and Mono Window methods have also been used to extract the surface temperature. The results of the research showed that the air temperature of the residential areas has increased by about 1 degree and the highest temperature calculated for the residential areas is in the southwestern parts, which is more than 29 degrees Celsius, as well as the vegetation cover in 1990, 2000, 2010 and 2019 was 81, 44, 61 and 43 square kilometers, respectively, and urban lands were 54, 81, 100 and 128 square kilometers, respectively. which clearly shows the reduction of vegetation and the increase of residential areas, the analysis of the results of the expansion pattern of Tabriz city also showed that the most expansion was in the southern, southwestern and eastern parts.Human society and the natural environment have been affected by the phenomenon of urbanization and urban development. The physical growth of cities can have many environmental, economic and social consequences. Changing land use and land cover in cities causes many problems. The purpose of this research is to identify the urban growth and its effect on the thermal pattern using RS. The data used in this research are the images of satellites and Landsat 5 & 8, TM and OLI, TIRS sensors from 1990 to 2019, which were classified using the object-oriented classification technique and then to predict the expansion of Tabriz city for 2029. Markov model and automatic cells (CA-Markov) have been used, Split Window and Mono Window methods have also been used to extract the surface temperature. The results of the research showed that the air temperature of the residential areas has increased by about 1 degree and the highest temperature calculated for the residential areas is in the southwestern parts, which is more than 29 degrees Celsius, as well as the vegetation cover in 1990, 2000, 2010 and 2019 was 81, 44, 61 and 43 square kilometers, respectively, and urban lands were 54, 81, 100 and 128 square kilometers, respectively. which clearly shows the reduction of vegetation and the increase of residential areas, the analysis of the results of the expansion pattern of Tabriz city also showed that the most expansion was in the southern, southwestern and eastern parts.

the object-oriented method in preparing the land use map of Darre Rood catchment area using Landsat 5 and Landsat 8 images in a period of 30 years, from 1990 to 2019 and its effects on changes in Darre rood river discharge it placed. The images were classified into fourteen classes and the changes in the area of ​​the classes revealed that the classes of irrigated agriculture, rainfed agriculture, rocky areas, residential areas, gardens and lakes with increased area and barren lands, pastures, forest lands and riverbeds decreased They were. To find out the changes in the river flow trend, SCS method was used which was implemented in SWAT model and according to land use in 1990 and 2019 in SWAT model was determined according to the digital elevation layer of the basin and all the necessary parameters to the model. Which included soil layers and land use changes and climate data were called into the model and two separate scenarios for 1990 and 2019 were used. The results showed that with the change of land use, the amount of CN in the second scenario compared to the first scenario increased by 5% and increased from 02.70 to 5.73, which due to the change in land use in favor of the basin becomes more impermeable to rain. Compared to 1990. Also, due to the increase in the type of vegetation, the amount of deep penetration has decreased from the first scenario to the second scenario from 257.09 to 97.9.

The main purpose of this study is to investigate the groundwater level using remote sensing science and GIS and its relationship with land use. For this purpose, the relevant images were taken and the necessary pre-processing was applied on each of them. Then the images were modeled and classified. In order to study land use changes, the land use classification map for both 2000 and 2020 was used using the object-oriented classification method and then to study land use changes, the land use change map was extracted for a period of 20 years. After extracting the land use change map in order to select the best model, for 2000, the circular method for 2020, the Gaussian model, which were recognized as the most accurate method. The results showed that the 2020 land use map of the rangeland class had the most and then the residential area had the most area. Looking at the uses of the two years, the results show a significant difference that the use of gardens has decreased significantly, which indicates the lack of management and felling of trees and the destruction of forests and gardens and turning it into residential and agricultural areas and The use of the residential area also increased from 42187 to 69164 in 2000. By adapting the land use map to the groundwater level map, it showed that the highest average water level in 2000 was recorded for agricultural use at 64.50 meters and the lowest average water level was recorded for barren land use at 26.00 meters. Considering the land use map and groundwater level map of 2020, the highest average water level in this year belongs to agricultural use with 61.19 meters and the lowest average water level recorded is related to soil use with 28.00 meters. The level of water level accelerates the destruction of these natural resources and will lead to terrible dangers, the most important of which is the issue of land subsidence.

Temperature is one of the main factors influencing urban planning because it guides the type of facilities available in cities and even determines the urban structure, shape and texture. On the other hand, increasing vegetation cover is one of the most effective strategies to reduce urban climate impacts. In the present study, the land energy balance algorithm was used to achieve land surface temperature and the soil vegetation index of Nazarabad city was used to estimate plant poisoning. For this purpose, Landsat satellite images (TM-OLI), years (2000-2019) were used. First, the relevant images were obtained and the necessary preparations were made. Then, the object-oriented classification was performed. Linear regression analysis was used to estimate the correlation between surface temperature and vegetation. Surface temperature results showed that vegetation areas such as agriculture and rangelands averaged 32 and 34 ° C for 2000 and 2019, respectively. However, during these years, vegetation-free areas such as urban and wilderness areas that were devoid of vegetation have averaged 36 and 39 degrees Celsius, indicating the effect of vegetation on surface temperatures. Also in estimating the correlation between vegetation and land surface temperature, it can be said that there is a strong correlation between the data. Independent variables have been explained which show high value and the model is significant with 0.95% confidence and is able to express changes based on available data so it can be concluded that this model has high accuracy for this study.

Land surface temperature is an important indicator in the study of ground energy balance models on a regional and global scale. Due to the limitations of meteorological stations, remote sensing can be a good alternative to estimating surface temperature. In the present study, the relationship between different land uses and ground surface temperature in Kosar city and spatial autocorrelation has been investigated using Moran index. Landsat 8 (OLI) and Landsat 5 (TM) satellite images were used for this purpose. The present study was carried out in four main stages: a) preparing images for 1987 and 2015, b) making the necessary predictions, c) preparing a classification map using the object-oriented method, and d) extracting the earth's surface temperature with Separate window algorithm. The results showed that dryland and rangeland agricultural uses in 1987 and 2015 have higher temperatures than other uses, due to the dryness of selected agricultural products in the selected period (June), which caused the temperature to rise. Is. In contrast, the use of water areas due to their high heat capacity in these years have the minimum average temperature. In addition, hot and cold clusters of Kosar thermal islands were extracted using the hot spot analysis index (Hotspot). Finally, the analysis of spatial autocorrelation with global Moran indices showed that the surface temperature of Kosar city has a spatial structure and is distributed in the form of clusters.

Accordingly, the study of land use change, given the significant effects that this phenomenon has on human life and the environment, seems necessary. At present, remote sensing as an ideal resource provides users with the necessary and sufficient facilities to be aware of land use changes and human land use, by extracting and updating land cover maps. Accordingly, the present study was conducted to investigate land use changes by object-oriented classification in the Quchan-Shirvan catchment, located between the provinces of North Khorasan and Khorasan Razavi during the years 1998 to 1397. For this purpose, first, TM and OLI images of Landsat 5 and 8 satellites have been prepared for the desired years, and through these images, land cover maps of the study area with object-oriented classification method in six classes of residential areas, irrigated lands. , Rainfed lands, fallow lands, water levels and pastures were obtained. Finally, through land use maps, land cover changes during the studied years in terms of area quantity, spatial distribution and trend of changes were examined using the LCM model. The results of this study showed that during the study period, fallow and rainfed land uses have a decreasing trend and residential uses, irrigated lands, rangelands and water levels have an increasing trend; As the most changes related to rainfed land use decreased by 23,729 hectares, and pasture land use increased by 35,935 hectares, are among the major changes in the study area.

Surface temperature, including soil, water, snow, and vegetation, are among the variables used in a wide range of earth science and environmental studies. Ground surface temperature is usually monitored at a point in a limited number of points, which are usually measuring stations. When spatial distribution of surface temperature over a wide area and simultaneously is required, remote sensing technology has many capabilities. Due to the capability of remote sensing techniques in the study of physical properties of the earth, in this study, to evaluate the relationship between surface temperature and land use, using the Landsat8-TIRS image, the surface temperature was calculated using the Split Window method. And the land use pattern was extracted by object-oriented classification method in an area of 22218.33 square kilometers, located in northwestern Iran. The results show that the surface temperature is strongly affected by surface moisture and vegetation density, so that surfaces with low humidity and low density vegetation show the highest temperature on thermal images. In the study area, barren lands with a temperature of 33.9 ° C and water levels such as; The lakes behind the reservoir dam, with a temperature of 27.11 ° C, have the highest and lowest surface temperatures, respectively, among the existing land uses. The results of this research can be used for environmental planning.

Classification is one of the most important methods of extracting information from digital satellite images, and today image classification using object-oriented processing using various techniques is widely used. In this research, the object-oriented method in preparing the land use map of Darrehrood catchment area using Landsat 5 images with TM sensor and Landsat 8 with OLI sensor in a period of 30 years, from 1990 to 2019 and its effects on Changes in the discharge of the Darrehrood River were examined. Landsat satellite images are atmospherically corrected with Envi5.3 software and in ecognition software by object-oriented method and nearest neighbor technique using four spectral indices (NDVI, GVMI, EVI, CIG) and average bandwidth characteristics and luminosity characteristics. The image and shape of the objects The images were classified into fourteen classes and the land use of the basin was extracted in the two periods of 1990 and 2019. Object-oriented classification with a kappa coefficient of 93% and based on the overall classification accuracy of 0.9235, The result of the classification by object-oriented method is more accurate and the classification accuracy is at an acceptable level, which among the parameters that were considered to achieve this accuracy can be parameters such as, class neighborhood, band values and Use of spectral indices used to separate units and the number of repetitions of classification operations. According to the changes in the area of the classrooms in the 30-year dimension, it was found that most of the uses are primarily related to the rangeland class, which occupies an area of approximately 1391.42 square kilometers. Then, the use of rainfed and fallow agriculture with an area of 850.55 square kilometers and barren lands with an area of 665.40 square kilometers are the most common areas. These land uses have the most areas in 2019, with the difference that the land use of the rangeland has an area of 1137.06 square kilometers and dryland agriculture has an area of 1013.08 square kilometers, and barren lands have been reduced to an area of/2015 / 35 square kilometers, and instead the area Irrigation has increased from 45.69 to 387.82 square kilometers. Gardens and forests in 1990 occupied an area of 59.79 and 8.78 square kilometers, respectively. In 2019, garden lands will increase to 65.50 square kilometers and forest lands will decrease to 5.49 square kilometers. Increasing the residential land area compared to 1990 has been associated with a decrease in rangelands, which indicates the destruction of rangelands and the creation of residential areas. Eastern was prepared. Rainfall histogram method was used to enter the data into the model. In order to evaluate the land use change in the runoff of Darrehrood catchment in HEC-HMS model, SCS method was used which was implemented in HEC_HMS model and Darrehroud catchment was divided into four sub-basins of Mashiran, Horand, Sambor and Buran and then in the environment. ArcGis software was drawn digitally and the physical properties of the basin and sub-basins were used as parameters required in the present study. Using the SCS method, a soil hydrology group map is required to estimate the CN curve number. Therefore, the map of soil hydrology groups was prepared by the Natural Resources Organization of East Azerbaijan Province to be used to calculate the CN curve number. According to land use in 1990 and 2019, the CN curve number and runoff delay time of sub-basins along with K and X coefficients were introduced to the model and implemented. In Buran sub-basin, there will be a decrease in water permeability and consequently a decrease in initial rainfall losses and an increase in runoff, while in Mashiran, Horand and Sambor sub-basins, a decrease in water permeability and an increase in initial rainfall losses and a decrease in rainfall will decrease. Runoff will be observed. The result of these changes on the runoff of the basin was obtained using the HEC_HMS model. In Darrehrood catchment simulation in HEC_HMS model, calibration of the basin in four sub-basins was calibrated based on runoff peak and runoff height and runoff volume per year. The calculated results with the observed results on average in the runoff height element of 93.15 Percentage and in the runoff peak element 94.35% and in the runoff volume element 94.95% show the correspondence of the correct implementation of the model on the basin, which includes the acceptability of the results (the results showed that the runoff peak in the sub-basin of Mashiran with Reduction of 7 cubic meters and reduction of 8.5 mm of runoff volume in Horand sub-basin with reduction of 8.6 cubic meters of runoff peak and reduction of 12 mm of runoff volume and sub-basin of Sambor with reduction of 2.2 cubic meters of runoff peak and reduction of 12 mm of runoff volume While in the Buran basin, unlike the previous three sub-basins, the increase of runoff peak by 10 cubic meters per second and the increase of runoff volume by 9.6 mm has been estimated.

Today, the preparation of land use maps using remote sensing data is one of the most important methods for producing land use maps and land use assessment together. Lack of proper infrastructure, non-observance of land development capability in selecting land uses and its unprincipled management leads to the phenomenon of soil erosion. The purpose of this study is to prepare land use maps using object-oriented method and to prepare soil zoning maps of Zarrineh Rud catchment for 2000 and 2018 Landsat satellite using WLC method. The results showed the detection of changes from object-oriented classification The highest rate of change in rainfed and irrigated agricultural land uses has been faced with the largest increase in area in the region. The trend of changes in barren land uses, rich and medium rangeland, has been decreasing over time, so that the area has decreased by 14.04, 10.66 and 5.73 percent, respectively. Man-made use has been increasing almost uniformly over time, which has grown by 2.47% over 18 years. The results obtained from the erosion zoning maps produced in 2000 and 2018 showed that there are two very high-risk and high-risk classes, each covering 15.29 and 27.51 percent of the area. These classes are mostly located in rainfed, irrigated, barren and medium range agricultural uses.

The main purpose of this research is to monitor the groundwater level using remote sensing science and satellite images and its relationship with land use. For this purpose, the relevant images were taken first and the necessary pre-processing was applied on each of them. Then the images were modelled and classified. In order to study land use changes, the land use classification map was extracted for 2002 and 2018 years using the object-oriented classification method and then to study land use changes, the land use change map was extracted for a period of 16 years. The highest rate of change is related to the use of rangeland to rainfed agriculture, rangeland to irrigated agriculture, forest to irrigated agriculture and rainfed agriculture to irrigated agriculture. Also, among the modified land uses, forest land use has the lowest increase. After extracting the land use change map in order to select the best interpolation model from different models, all models were evaluated and the Kriging method was more accurate than other methods, which among the different modes of the kriging method Also, K-Bessel model for 2002 and Circular model for 2018 have the highest accuracy. The results of groundwater survey showed that the highest and lowest average water level in 2002 belongs to rainfed agricultural use and water use and in 2018 rainfed agricultural use has the highest average water level and forest use has the lowest average water level.

The land surface temperature is the highest layer of the earth's surface and depends on the level of surface emission, vegetation and the types of ground cover. Earth's surface temperature provides important information about the physical characteristics of the Earth's surface from local and global scales, and plays an important role in many applications. From Earth's surface temperature to study water resources management, agriculture, resource management, drought, environmental geochemical processing, meteorological research, global changes in land surface temperature, weather forecasting, hydrology, ecology, plant status survey, urban climate, studies Environmental and geophysical variables such as evaporation-transpiration and soil moisture are used. In general, temperature measurements at ground level are performed by meteorological stations, including synoptic and climatological. It should be noted that meteorological stations are only able to measure the temperature at specific points that have already been installed there. What is considered to be a major flaw in ground temperature monitoring is the lack of sufficient meteorological stations to know the temperature values in stations without stations, which have been partially remedied today by remote sensing technology. Earth's surface temperature is one of the most important components in global studies, which is used as one of the important factors in controlling the biological, chemical and physical processes of the earth.

Moghan plain is located in the northwest of Iran and is subject to Ardabil province and is located in the northern part of the province. ParsAbad Moghan city is a relatively large plain with an area of 143494 hectares, which occupies about 14% of Ardabil area and is the northernmost city of the province. The data used in this study included the Landsat 8 satellite image, which used its OLI sensor to extract land use maps and its TIRS gauge used to extract the Earth's surface temperature for 2018, as well as the ETM + Landsat imager to prepare land use maps. Using visible and infrared bands and surface temperature using thermal bands for 2002. The city's meteorological data were also used to check the temperature recorded by the stations. The ENVI 5.3 software was used for atmospheric and radiometric corrections, and the ARC GIS 10.5 software was used to extract the relevant maps. In order to classify land use, object-oriented classification method was used in eCognition Developer64 software. In object-oriented classification, spectral information is integrated with spatial information, and pixels are segmented based on the shape, texture, and gray tone of the image at a specific scale, and image classification is based on these components.

The largest area in 2002 belongs to the rangeland class with an area of 58,138 hectares. The second area belongs to the dryland agricultural class, which has the largest area with 52369 hectares. The smallest area belongs to the use of water with 543 hectares. For 2018, rainfed agriculture had the highest area with 41906 and then pasture with 30943 had the highest area. Looking at the uses of 2018, the results show a significant difference that the use of soil has increased from 11143 in 2002 to 30943 in 2018, as well as the use of irrigated agriculture and residential areas and forests. However, the use of irrigated areas has decreased significantly from 543 hectares to 262 hectares, and the use of rainfed and rangeland agriculture has also decreased compared to 2002. The water temperature during 2018 was almost constant and did not differ significantly, and the lowest temperature in both years is 31 degrees. Due to the fact that water has a high heat capacity, water has a lower surface temperature to the soil has the highest temperature in both years with 40.80 for 2002 and 42.92 for 2018. Aquaculture in 2003 was 33.12. C, which in 2018 increased to 34.41. C. The rangeland use has had a high temperature in both years of study and has increased from 38.22 in 2002 to 39.26 in 2018.

In this research, in the first step, in order to classify and then examine the changes that occurred in a certain period of time in the city of ParsAbad, action was taken. For this purpose, in the first stage of this research, in order to classify and record changes in a 16-year period, object-oriented images were classified in eCognition software and in ArcGIS10.5 software, extraction maps were extracted. Was. The classification accuracy in 2000 has a total accuracy of 0.90 and a coefficient of 0.87. While the classification in 2018 with an overall accuracy of 92% and a Cape coefficient of 0.90 has provided a relatively higher accuracy. After classification, an attempt was made to examine the changes that occurred in the region over a 16-year period, and a map of land use changes was drawn up for the area under study. Land surface temperature is one of the main parameters in the study of cities. Because it is almost the same as the air temperature in the lower layers of the city, which is the energy balance of the surface and determines the climate between the buildings and affects the life and comfort of the urban residents. Soil use has the highest temperature in both years with 40.80 for 2002 and 42.92 for 2018. Also noteworthy about residential areas is that residential use has increased from 34/51 in 2002 to 40/09 in 2018, which indicates that in 2018, with the expansion of the city compared to 16 years ago, the heat concentration will also increase. Increased. This use is due to the presence of man-made and heat-absorbing factors such as asphalt, concrete, the existence of various machinery and factories, as well as the creation of tall buildings that prevent heat from escaping around and prevent wind from moving into the city.

The study of changes in land cover and land use from the distant past on the surface of the earth, which usually occurs in two ways, the first type is changes caused by natural factors such as: erosion, tectonic forces or floods and the type The second is the changes that are imposed by humans on the earth due to the non-standard use of available resources. Land use is a description of the type of human exploitation for one or more purposes on a piece of land. Satellite data is one of the fastest and least costly methods for researchers to map land use. The analysis of these data can provide insight into human interaction with the natural environment. Investigations of land cover changes and land use have long been discussed at the ground level. Land use change is a process that enables the observation and detection of time series differences and phenomena, events and patterns of land surface. The present study is an example of applications of remote sensing technology in urban resource management in which land use changes in Urmia city were evaluated over a 9 year period (2018-2019). This research is a descriptive-analytical study and data collection was done by documentary method. To do this research, Landslide MTL satellite images of SPOT8 and SPOT 5 were used and image classification was performed by using object-oriented classification method. Then, in the Area ARC GIS environment, the user classification area was evaluated. Change detection method was used for land use change process. Evaluation of land use results shows that during the study period the area of Urmia changed from 1597.551296 km square in 2009 to 1678.3902 km square in 2018. The highest level of changes in percentage of land use in the period 2009 to 2018 was related to rangelands and the least changes were to saltwater.