Journal of Spatial Analysis

---

Introduction

Trend of increasing natural resource degradation in many parts of the world, is a serious threat to humanity. Desertification is one of the manifestations of the damage that has already suffered as a scourge of many countries, including developing countries are. At present, remote sensing is one of technologies with timeliness data and accuracy suitable for monitoring land use changes in the areas of natural resources. Desertification monitoring and tracking changes, which seeks to desertification that the change could be for any reason and also collect and analyze data from activities, projects, plans and programs that may desertification range condition assessment and reporting to provide them. The purpose of this study was to evaluate changes in land use on desertification monitoring using remote sensing techniques to the agricultural lands around zayandeh rood in the East region of Isfahan.

materials and methods

In this study, the image sensor of TM to date 1987, 1998, ETM⁺ to date 2002 and  OLI to date 2014 related to the Landsat 5,7 and 8 to obtain the land use map used and then was performed radiometric and geometric correction.Then was used the color combination, the main component analysis, vegetation index and supervised classification method for detection of complications and the maximum likelihood algorithm as the most appropriate method for supervised classification in classes 9 of land cover. After production the land use map correctness evaluating operations with calculation error matrix and then was performed detection operations for these maps. Finally, for desertification of monitoring, land use years 27 changes around zayandeh rood  using the comparison method  is paid changes to identify and was obtained the area of each use.

Results and discussion

For investigate the the process of desertification, land use changes in the period of 27 years. In order to select the appropriate bands in supplying the best color composite satellite images and operations classified in order to reconstruct the images, index optimization factor was applied. The results of accuracy assessment shows that For all the images above the 80% overall accuracy and Kappa statistics indicate that almost 80 percent. Generally good agreement between the classification and classes of users on the ground there. By comparing bit images specified land use changes in the period of 27 years, riverbank has the greatest changes during this period. So during these 27 years the river high Zayandehrood degradation, which could be due to the expansion of agricultural activities in rivers. This degradation is generally represents gradual drying of the river and go surrounding cultivated by farmers. This degradation process in the margins of the river and the gradual drying of the river towards the desertification situation in the region shows.

Conclusion

In year 27 time period, Zayandeh Rood neighboring rivers has changed dramatically, so 86.43% of neighboring rivers was destroyed due to the expansion of agricultural activities vicinity of the river and drying river. Another significant changes, loss of agricultural land is notable such that 64% of this land has been reduced compared to 1987. Of reasons for the loss of agricultural land will be noted the region drought and Zayandeh Rood river drying up and Low rainfall, land use change and the proximity of the region desert. Also, has become about hectares 324.99 Of salt marsh lands to agricultural land. Moreover, the developed urban areas to its development contributed agricultural land and rangeland. Bayer lands around Zayandeh Rood Increase and also in region of rangeland lands Low and has increased Bayer lands  and somewhat until agricultural land which inappropriate use of this land shows in order to the agricultural. That this is the desertification progress in the region. Generally desertification process in this period years 27 has been a growing trend.Therefore multi-temporal and multi-spectral satellite data for enhancement, especially for desertification monitoring was large capability and classification after comparison method is helpful for determine the type and direction of changes occurred. Since the development of desertification, limited to a small area and is not recommended range is therefore more effective, in addition to work sheets, other sheets around the area also evaluate the process of desertification is to allow for planning and management in the field of combating desertification exist.

---

The effect of Urban Development on Watershed Hydrological Properties (case study: Tajrish Watershed)
Throughout the human history, societies and rivers have been closely linked, so that the human civilization began from the riverside (Stevaux et al. 2009 (. The quantitative and qualitative characteristic of river is vulnerable to land-use changes (Kang et al. 2010). Natural and urban watersheds are influenced by the rapid land use change due to urban development (Furusho et al. 2013). Hence the importance of land use as an environmental variable have made its changes as a major issue in environmental changes and sustainable development) Verburg et al. 2009).
The development of urbanization and industrialization of cities and communities have undesirable effects on the hydrological response of watersheds. It increases the magnitude of runoff and contamination, reduces the base flow and the groundwater recharge. Hence, urban authorities are urged to pay more attention to the environmental damaging effects of the urbanization process and the increase of construction. In this regard, attention should be paid to the effect of type of land cover and land use on urban runoff and hydrological changes in surface flow. Tehran as the largest metropolis in Iran has ascending trend of land cover and land use changes due to the growing population.
In this research, the effect of urban development on the hydrological characteristics of the Tajrish sub-watershed (in Darband watershed) located north of Tehran has been investigated. Results of this study indicated that the river Darband is exposed to hydrological hazard due to human need for space and land use and land cover changes. The studied area is affected by decreasing pervious area, increase of runoff coefficient, and change in water quality parameters.
Darband River watershed consists of two streams of Darband and Golabdareh which are considered as the major rivers of the Tehran-Karaj Basin. This river originates from the mountains of the Tochal located in northern Tehran. The catchment area of Darband River in the studied area is 39.88 square kilometers.
In this study, aerial photos of years 1345, 1358 and also   and IkONOS images in year 2011 were used to detect the changes in land cover and land use in the Tajrish watershed. Pas-Ghale sub-watershed in upstream of Tajrish was selected as benchmark since its land use doesn't affected by human interventions. SCS-CN method developed by the United States Department of Agriculture (USDA) was used to estimate the quantitative changes in surface storage and runoff volume. Man-Kendall test was used for temporal trend detection of discharge and chemical parameters of surface water and also. The change of water type was identified annually using the Piper diagram in the aqQA software. Frequency analysis was carried out for peak discharge data using the weibull’s empirical method.
During three considered periods, the curve numbers (CN) and runoff coefficient (C) in Tajrish watershed significantly increased. Significant trend was also observed for the chemical parameters of surface flow in Tajrish. While the surface storage and initial abstraction ratio (λ) indicate decreasing trend.  Relationships of CN and λ with rainfall depth (P) were also computed for both studied watersheds. According to the Piper diagram, the distribution of ions in the cation diagrams at both Maghsudbeik and Pasghaleh stations is generally more directed toward sodium. In the triangles of anions, both of the stations studied tend to show more calcium biocarbon content. Presence of sodium ion in the surface water is due to igneous formations in the watershed. The surface water in Pasghale station, indicate a neutral type of water. Whereas, saline water type is detected in the Maghsudbeik station. The increase of urban utilization over the past three decades could be the main cause of changes in the hydro chemical characteristics and water type along the Darband River.
Investigation of land use changes in the Darband watershed indicate that the impervious surface has increased during years of 1996 to 2011. Results also indicate that the CN and λ values in Pas-ghale watershed are more correlated to Pin compared with ones observed in Tajrish. The results also reveal that hydrological modeling in watersheds undergoes land use changes and urbanization will result in imprecision results.
 Many chemical parameters of the water quality of Darband River have been increasing at the Maghsudbeik station such as Chlorine, sulfate, sodium, electric conductivity and TDS and in the coming years, it can be considered inappropriate in terms of agriculture in the water class.
 
Keywords: Darband River, land cover and land use, Piper diagram, SCS-CN.
 
 

---

Abstract

Urban heat island (UHI) is one of the environmental phenomenon which has made difficult environmental conditions for citizen. This study aims to evaluate the spatial and locational variability of Esfahan urban heat island according to the role of land use. Thus an area about 190.2 square kilometers (km2) in Esfahan, as the microclimate, was studied. In order to analyze the relationship between land use and land cover changes on Esfahan urban heat island, the images of Landsat 7 (TM and ETM +) and Landsat 8 (OLI / TIRS) on 20 July 1989, 17 August 2005, 18 August 2014 have been used. The results show that the urban areas has experienced 31% changes in positive direction; while the agricultural sector and green space havehad a reduction of 25% in their area. The analysis of the intensity of heat island show that heated cores are related topoor and barren lands with about 37/33 and 36/5. Although the most area of thermal classwere related to warm thermal class in 1989 and 2005, the average thermal classes were about 63/8%in 2014. Moreover, the locational variation distribution of Esfahan heat island shows that the locationof the heat island has gradually changed. For example in 2014 it included small parts in the south of the city, military zones and barren lands in the south, some parts in the north west and north east areas and small areas in the east of Esfahan. This means that urban development isn’t the main factor of the surface temperature increase and urban heat development, but rather the type of land use has influenced the decreasing or increasing of air temperature.

.

---

 

 
Ecologically-based Management Factors and criteria of River-Valleys in Tehran metropolis-Case Study: River-Valleys of Kan
 
Abstract:
Iran has seasonal rivers because of dry climate, low rainfall and different topography. These river- valleys have main role in forming, genesis, and sustainability of human settlements and provide different ecological services. The main services include beauty, store of green spaces, water supply, reduce and create temperature differences, local air flow and natural ventilation which are part of the functions. Tehran is roughly the same area as 730 square kilometers and its population is 8.7 million people. It is located in51^° and 17^´ to 51^° and 33^´ east longitude and 35^° and 36^´ to 35^° and 44^´ north latitude. The height of this city is 900 to 1800 meters. The north and north east of this city are located in peculiarity range of the southern part of the middle Alborz. This city includes 7 river valleys to the names Darabad, Golabdareh, Darband, Velenjak, Darakeh, Farahzad and Kan. The ecological role of these river valleys is reduced because of non- ecological axis developmental interventions by urban management and citizens. These interventions have changed river valleys to high risk space of skirt movements and flood. Kan is the most important river valley because of the breadth of the basin and permanent water discharge rate. The part of this river valley has changed to park (Javanmardan) by municipality. The purpose of this research is that to provide factors and criteria of ecosystem based management to organize this river valley.
ANP has been used in this research. To use this method for analyzing   factors and criteria of ecosystem based management to organize this river valley, firstly, these factors have been identified by library studies and scrolling. These factors include 4 criteria (natural: 15 sub criteria, social: 3, management:  6, economic: 2). the books, journals, reports, maps, aerial photos, satellite images and internet sites have been studied in library studies. In site studies, some information from library studies have been edited. After that, the findings of these two methods in form of questionnaire called factors and criteria of ecosystem based management to organize Kan River valley, was in charge academics and professionals. They were elected among pundits of urban management science, urban planning, geography and environment in Tehran. At first the number of them was 30 people came to agreement in two process about 4 factors and 18 criteria and determined importance and priority by Delphy method. Findings in Delphy method were analyzed through ANP and SUPER DECISIONS. In this process, firstly, a conceptual model and relation inter and intra clusters and nodes determined. These relations in this process are very important because paired comparison depends on this process. Assumption of equality of effects and similar relations in these factors is illogical because there are the grading of effects and relations in this research. Second, the factors have been compared to each other to create a super matrix based on paired comparison. Generally, in this process decision makers compare two different factors to each other and paired comparisons have grading of between1to9. In double- sided valuation, each factor is used to show initial inverse comparison. Inconsistent rate in paired comparison must be less than 0.1 like AHP. Third initial super matrix is created. It is the weights created from paired comparison and identified the importance of each factor in each cluster. Forth, the weighted super matrix was created. The weights of clusters was calculated in this process to identify the weight of final super matrix. Fifth, limited super matrix was created. The weighted super matrix reached for infinity band each row convergenced to a number and that number was the weight of factor. By this way limited super matrix was reached.
Based on ANP and table 1, management: 46%, natural – ecological: 26% and economic and social factors: 14% are important respectively in ecosystem based management to organize Kan River valley. Based on reached results, inconsistent rate is 0.003 and it shows that the weight is valid and review is not necessary. Among sub criteria in management factor, organizational pattern: 32%, method of management: 23% and policies: 21% are the most important respectively in ecosystem based management to organize Kan River valley. Among sub criteria in natural- ecological factor, flood, domain movements and building and texture of soil are the most important respectively 23%, 18% and 11.5% also in social factor, participation, security and public trust have the importance respectively equal to 49% 31% 19%. In economic factor, environmental assets and stakeholder’s economic participation have the same importance.
Based on this research, management factor (organizational pattern and the method of management) is the most important in ecosystem based management. But this approach, the management pattern and intervention to organize this river valley, need comprehensiveness and integrity of the subject (nature, society, management and economic), purpose (protection, resuscitation and use), factors (government, city council, municipality, private sector and people), duties (policy making, planning, designing and perform), method (collaborative), tools (knowledge, skill, rule, program, budget, machinery and materials) and management domain. Use of these factors and criteria need some infrastructure and reforms. The most important reform is reform of management structure, production of subject matter and topical program special to organize river valleys by ecological approach to release Kan of loading and contradictory grabbing.so this management can follow protection, resuscitation, sustainable use and continuity of ecological services.
 
Key words: ecosystem, ecosystem based management, analytic network process, river valley of Kan
 
 
 

---

---

Evaluation of hot spots changes in Tehran city and satellite based on land use and its role in urban heat hazards
Expanded abstract
Problem statement:
Urbanization and human activities affect the urban climate and clearly affect the air temperature close to the surface. In Tehran and its satellite, factors such as climatic region, season, time of day and wind regimes, topography, urban environments, population density, residents' activity, vegetation structure and urban physical form play an important role in the formation of urban heat islands. The purpose of this research is to determine the type of spatial distribution of heat islands of Tehran metropolis and satellite cities using land use and land cover. Replacing natural land cover with impervious surfaces due to urban development has negative environmental, social and economic impacts, in addition to beneficial aspects. Most of the albedo belong to the built areas and the bare land and the smallest of the Albedo belong to the aquatic areas and vegetation. In this research, the hypothesis is whether the suburbs may have higher temperatures than urban areas depending on the type of land use? In fact, it is examined the spatial distribution of the heat island of Tehran and its satellites, in which the use of land and land cover are analyzed as a factor contributing to the creation, intensification or reduction of the thermal island.
Methodology:
Extraction and preparation of imagery data through the Landsat 7 Satellite ETM + sensor over the years 2001-2015 and selection of June as the hottest month of the study area. These images were extracted from Route 164 and Row 35 of the USGS. An assessment was carried out through the accuracy of ground surface temperature data by Landsat satellite images and obtained temperatures from the weather stations in the area based on the Taylor diagram. In order to investigate the spatial structure of the cells obtained in each map, each containing surface temperature and heat island extraction, it used the methods of world spatial autocorrelation (high and low clustering, spatial correlation) and local (Cluster and Outlier analysis, hot spot analysis). The high and low clustering statistics show how the concentration of high or low values ​​in the region. In the next step, the results of analysis of Anselin Local Moran and hot spots were compared in map format. Hot spots were analyzed in all studied regions and in all 7 cities. The area of ​​hot spots was investigated over the course of 15 years and the results were presented in table and diagram form.
Land use was surveyed for every 7 county. In the last section were studied, the relationship between hot spots in each city and type and land use changes over 15 years.
Surface spatial analysis of the surface temperature of the area showed that the cells follow a cluster pattern and their trend towards clustering. Any kind of land cover and land use will create special features in a place that can be increased or decreased with a specific microclimate.
Explaining and results:
After selecting the years 2001, 2005, 2010, and 2015 as the sample and survey of the temperature of each land use in that year, it was determined that artifact, pasture, bare lands, forest, aquatic areas, agriculture and green spaces were respectively have the highest to the lowest temperature in the area. On the other hand, in the area of heat island in a region are Rabat Karim, Ray, Islamshahr, Tehran, Shahriar, Karaj and Shemiranat, respectively.
In spite of the reduction of aquatic areas and even bare lands, because of the large impact of green space or agricultural land was reduced the extent of heat islands during the statistical period, and on the contrary, the reduction of green space and agricultural land in places where even their forest areas have grown, has increased the levels of heat islands. This suggests that the dispersion and extent of green spaces has a more effective role in reducing the heat island compared with the creation of limited forest and planted surfaces in one place. Hence, in Tehran despite the significant growth of artifacts, due to the increasing growth of green space, the heat islands has been reduced compare with the Ray, Robatkarim and Islamshahr cities, which are exactly on its suburbs.
 
Keywords: Heat Island, hot spots, land use, Tehran, satellite cities.
 
 

---

Evaluation of land use changes in coastal cities of Khuzestan province using GIS and RS
 

Abstract:
Today, the expansion of human societies and greater environmental dominance have led to faster and wider environmental change than ever before. The speed and variety of this change in urban environments is greater than in other areas. The purpose of this study was to investigate the temporal and spatial variability of four coastal cities of Khuzestan province (Bandar Imam Khomeini, Bandar Mahshahr, Abadan and Khorramshahr) using land use measures over a period of 20 years 1997-2009 to accurately determine spatial-temporal pattern of changes. is. The method of the present research is quantitative and its dominance is dichotomous. To extract the land cover map data through Landsat satellite imagery from 1977 and 1998 taken by OLI and MSS5 sensors, the images were divided into four main classes (residential), vegetated areas, wetlands (rivers). And Bayer were categorized. After preparing land cover maps from TerrSat software was used to analyze land use changes and finally using the Markov chain to predict urban development trend in the study areas. The results show that Abadan and Khorramshahr have the most changes in vegetation use, while in the two cities of Imam Khomeini (Rah) and Mahshahr the most changes were related to the use of Bayer. Added to the timeline.
Keywords: Spatio-temporal changes, Land use, TerrSat software, Coastal citie
 

---

Introduction
Land use reflects the interactive characteristics of humans and the environment and describes how human exploitation works for one or more targets on the ground. Land use is usually defined on the basis of human use of the land, with an emphasis on the functional role of land in economic activities. Land use, which is associated with human activity, is undergoing change over time. Land use information and land cover are important for activities such as mapping and land management. Over time, land cover patterns and, consequently, land use change, and the human factor can play a major role in this process. Today, satellite-based measurements with geographic information systems are increasingly being used to identify and analyze land-use change and land cover. With regard to the problems of changes and transformations in the studied area, remote sensing can allow managers to categorize images and evaluate land use changes, in addition to saving time and costs, which allows planners to make plans based on changes, more resources are lost. To be prevented.

Materials & Methods
In order to classify and detect the marginal land of the river, TM and OLI image images were selected for a specific month (August, August) for the years 1987 and 2017. The purpose of this study was to investigate the changes occurring in the studied area with an emphasis on agricultural lands. To do this, the images before processing in the ENVI software took radiometric, atmospheric and geometric corrections on them. After that, the main components of the river route were extracted. Five basic algorithms were used to classify the base pixel, but eCognition software was used to classify the object. Supervised classification identifies homogeneous regions with examples of land use and land cover, in which pixels are assigned in known information classes. Education is a process that determines the criteria for these patterns. Learning output is a set of spectral signatures of proposed classes. The first step in object-oriented classification is the segmentation of the image and the creation of distinct objects, consisting of homogeneous pixels. The main purpose of image segmentation is to combine pixels or small objects to create large image objects based on the spectral and spatial characteristics of the image. In order to evaluate the accuracy and compare the resulting maps, the overall accuracy and Kappa coefficient are used. When the sampling of pixels is done as a spectral or informational class pattern, the evaluation of the spectral reflection of classes and their resolution can also be done. An algorithm with the highest accuracy and accuracy will be the basis for the detection. Detection of changes, which leads to a two-way matrix and shows variations of the main types of land use in the study area, was carried out in this study. Pixel-based cross-tabulation analysis on pixels facilitates the determination of the conversion value from a specific user class to another user category and areas associated with these changes over the given time period.

Results & Discussion
The results showed that the object-oriented method is more accurate than the base pixel algorithms for providing user-defined maps. The amount of accuracy in the method based on object-oriented classification depends largely on choosing the appropriate parameters for classification, defining the rules, and applying the appropriate algorithm to obtain the degree of membership. The Kappa coefficient for each image is approximately 0.90. So these maps are the basis for the discovery of change. According to the results, the agricultural and residential lands have been increased and this increase has been accompanied by a decrease in rangelands. A general overview of this 30-year period shows that the arable and dry farming, respectively, increased by 2418.79 and 719.61 hectares and the rangelands had a decrease of 2848.86 hectares. However, the residential class and human effects show an increase of 428.88 hectares or a growth of 178.87%, which indicates the importance of agriculture in the studied area.

Conclusion
Identifying and discovering land cover changes can help planners and planners identify effective factors in land use change and land cover, and have a useful planning to control them. For this reason, maps are needed with precision and speed, and object-oriented processing methods make this possible with very high precision. The results of this study, in addition to proving the precision and efficiency of object-oriented processing in land cover estimation, between 1987 and 2017, have witnessed a decrease in the area of rangeland lands and, on the other hand, agricultural and residential lands, which is indicative of the overall trend Destruction in the area through the replacement of pastures by other uses such as rainfed farming.

Keywords: Land Use, Gamasiab, Object Oriented, Pixel Base, Kappa Coefficient
 

---

Soil erosion is one of the environmental problems that is a threat to natural resources, agriculture and the environment, and in this regard, assessing the temporal and spatial amount of soil erosion has an effective role in management, erosion control and watershed management. The main aim of this study was to estimate soil erosion in Amoqin watershed and its relationship with well-known vegetation-based and topographic-related indices. The meteorological data has been used to determine the rainfall erosivity. The rainfall erosivity index was calculated using the modified Fournier index during the 10-year available recorded rainfall data. The value of LS factor has been calculate using digital elevation model. Meanwhile, C and P factors were determined based on the utilization scheme and condition of the study area. Data were analyzed and processed using ArcMap 10.1, ENVI 5.3, and Excel software. In this study, RUSLE model was used to estimate soil erosion, in GIS environment. According to the results, the amount of factor R in Amoqin watershed varies from 12.32 to 50.52 MJ/ha/h per year. The variation of soil erodibility index (K) over the study area is between 0.25 to 0.42. The amount of LS factor varies between 0.19 and 0.38, which is more in high slopes, especially around the waterways and uplands of the study area. The variation of C factor was estimated to be around -0.18 to 0.4. In general, it can be said that the central part of Amoqin watershed has less C value due to the greater area of agricultural activities and the highest amount is related to western areas, especially southwest areas because existing the rangeland areas. Due to the lack of protective measures in the study area, the amount of factor P was considered as unity for the whole region. The base layers of RUSLE factors were obtained and overlayed in GIS to calculate the soil loss in tons per hectare per year. The map of annual soil loss indicate that the erosion amounts varies between 1.21 to 5.53 tons per hectare per year in different parts of the study area. According to the results, the vegetation factor with a coefficient of determination 0.47% had a significant correlation with soil loss. The stream power index with the coefficient of determination of % 0.07% had the lowest correlation with soil erosion values.

---

Introduction:
The growth rate of urbanization during the recent decades of metropolises has had many destructive effects on the urban environment, among which we can mention the change of temperature of surfaces and local climates. The increase in the urban population, the rapid growth of industrialization and the increase in the concentration of pollutants in the lowest level of the atmosphere have affected the severity of the city's heat islands. Land surface temperature (LST) is a key variable to control the relationship between radiant, latent and sensible heat flux. Analyzing and understanding the dynamics of LST and identifying the relationship between it and changes of human origin is necessary for modeling and predicting environmental changes. The heat of urban surfaces is affected by various characteristics of urban surfaces such as color, surface roughness, humidity level, possibility of chemical compounds, etc. In addition, the changes between LST in a city and its surrounding area are due to surface changes, heat capacity and topography. Since the surface temperature regulates the temperature of the lower layers of the atmosphere, it can be considered as a weather indicator and an important factor in the urban environment. Changes in land use by changing the features of the surface cover such as the shape of the constructed areas, the amount of heat absorption, building materials, surface albedo and the amount of vegetation lead to changes in the temperature of the earth's surface. Barren lands with soil cover, on the contrary, increase the surface temperature of the earth. Climatic characteristics at the time of satellite image imaging also play a role in the extent and intensity of urban cold islands, so that satellite imaging in the middle of hot summer days shows urban cold islands better. The innovation of the research is in the large area of the investigated area, which includes eight urban areas, in order to examine the pattern of temperature changes on a wider level.

Materials and methods
Considering the rapid development of urban and industrial areas in the Ardakan-Yazd plain in recent decades, this study aims to investigate changes in the surface temperature pattern using Landsat 7 and 8 satellite images for both winter and summer seasons. It was done in 2002 and 2019. In addition, the relationship between land use/land cover and surface temperature was also investigated. Geometrical correction of satellite images was done using topographic map 1/25000 of Mapping Organization and atmospheric correction using FLAASH method in ENVI software. Algorithms used to obtain land surface temperature for Landsat 7 images were single-window method and for Landsat 8 images, the Landsat Science Office model was used. Land use/land cover layers related to the years 2002 and 2019 were used, and central statistical profiles and LST distribution were extracted for pasture, agricultural land, blown sands, industrial areas, rock outcrops and cities. In addition to examining temperature changes in different uses, it is also possible to compare over time.

Results and discussion
The results of this study showed that the area of cold islands and thermal islands in winter and summer of 2002 is not much different, so that in winter 10.8 percent and in summer 10.4 percent of the area were cold islands and thermal islands in winter 9.02. It was 8.5% of the region in summer, while this difference is huge in 2019. Thus, 9.4% of the area in winter and 12.1% in summer are covered by cold islands, and thermal islands are 8.3% in winter and 1.6% in summer. Changing land use and increasing the size of urban and industrial areas and reducing agricultural land is one of the main reasons for the increase in cold islands. The survey of land use/land cover changes between these years showed that the extent of urban areas increased from 22,045 to 23,714 hectares, and industrial areas also grew by about two times, from 4,615 in 2002 to 8,187 hectares in 2019. However, during this period, the area of agricultural land has decreased from 1161 hectares in 2002 to 793 hectares in 2019. Also, the results show that the percentage of heat islands is higher in winter than in summer. The main reason for this can be the much less vegetation covers in the winter than in the summer, because the vegetation cover acts as a moderator of the earth's surface temperature. Cold islands are formed in the built-up areas in the winter and summer. From 2002 to 2019, the extent of cold islands decreased in winter and increased in summer, while the extent of thermal islands decreased in winter and summer. Also, the results of the validation section of the single-window method and the model of the Landsat Science Office in calculating LST showed that for both summer and winter seasons, Landsat 8 has a higher accuracy than Landsat 7, and the LST estimation model is based on the exclusive method of this The Landsat series of satellites (Landsat Office of Science model) has a higher efficiency than the single-window method.

Conclusion
The results showed that cities play an important role in changes in the temperature pattern of the earth's surface, and the phenomenon of urban cold islands is not exclusive to big cities in hot, dry and semi-arid regions, but also occurs in medium-sized cities. The temperature variability of eight cities located in the Ardakan-Yazd plain with the land use/cover of the suburbs also showed that the cities are colder than the suburbs in both winter and summer seasons. This study showed the role of vegetation in hot and dry areas in reducing LST and also provided evidence for the change in the degraded state of pastures in this area.

Keywords: Urban climate, Land use, Land surface temperature, surface urban cool island (SUCI), ‎ surface urban ‎heat islands (SUHI)‎


 

---

---

---

---

---

Nowadays, deep learning as a branch of artificial intelligence acts as an alternative for human with hopeful outcomes. Open Street Map as the biggest open source data is used as a complementary data sources for spatial projects. It is notable that is some advanced counties the accuracy of VGI data is higher than governmental official data. This research aims to use artificial intelligence to produce and subsequently promote completeness of OSM data. Res_UNet architecture was utilized to train landuse categories to the network. The result shows that IoU metric is about 83 percent that implies a high accuracy paradigm. Then, united-based method was used to calculated completeness of OSM data. The unit-based results show that completeness of building blocks, forest, fruits garden and agriculture land are: 3.6, 9.7, 90.4 and 81.88 respectively. It shows the low volunteer  participation rate to produce OSM data. On the other side the high accuracy achieved by deep learning leads us to complete OSM data by artificial intelligence instead of human prepared data. The advantage of using machine rather than human may be utilized in undeveloped countries or low density population regions as well as inaccessible areas.