نشریه اطلاعات جغرافیایی (سپهر)
پیاپی 126 (تابستان 1402)

The growing importance of housing is not hidden from anyone in terms of the profound and significant effects it has on the various social, political, and economic dimensions of countries; Therefore, accurate and reliable price estimation definitely facilitates policy-making in this field. Hundreds of factors may affect property prices in different situations as a subset of structural, spatial, and socio-economic factors. Therefore, considering these factors, property pricing should be done efficiently. Due to the complex nature of the real estate market, research has used common deep learning algorithms such as DNN, RNN, CNN, etc., but these algorithms are not very suitable for tabular data. On the other hand, the deep learning models in property pricing are also completely definite and do not take into account data uncertainty.

In this article, we have tried to pay attention to the tabular structure of real estate data in applying deep learning methods. The TabNet deep new architecture is used for this purpose. In addition, at the same time as the learning process, it makes feature selection fully interpretable. In this study, also using existing combination techniques, fuzzy logic is combined with deep learning algorithms to learn complex problems faster and more accurately, to overcome the shortcomings of the certainty of deep learning models and not consider the inherent uncertainty of the data in this models. In this study, using the existing combination techniques, also using spatial information system (GIS) to provide a clearer evaluation to ensure full visualization of the spatial pattern of property properties as well as the relationship between these properties and pricing and spatial variables are included in the valuation model. In order to evaluate the proposed methods, real estate data of District 5 of Tehran were used.

The order and prioritization of the impact of features on the pricing of Tehran residential properties by the TabNet algorithm indicate the significant impact of spatial factors. So that in this ranking, after the area, the two spatial characteristics of latitude and longitude have the second and third ranks, respectively. Basically, latitude and longitude indicate the criteria of neighborhoods and the type and prestige of different places in the city, and the social class of different streets and neighborhoods in the city, which is clearly a factor in influencing the price. Finally, TabNet, DNN, CNN, RNN, LSTM, Autoencoder algorithms as well as XGBoost machine learning algorithms were used for the  Tehran data set, and RMSE, MA and  evaluation criteria were compared, which according to the  criterion, a 5% improvement in accuracy was achieved by using TabNet. Finally, the RMSE of the FuzzyTabNet hybrid algorithm for Tehran data decreased by 4/65% compared to the basic TabNet algorithm. The fuzzy Autoencoder network also improved by 5/52% compared to the common Autoencoder network.

Alteration is the simplest, cheapest and most suitable means of mineral exploration. The best way to find changes is to use satellite data processing.
Asadi and Tabatabaei (2007) have used band ratio processing methods and false color images by using selected principal component processing (PCA) to identify the range of variations in different regions on Aster images. Gomez et al. (2005) visualized the lithological units of Namibian using the PCA algorithm on Aster data.
The exposed rock units in Muteh mining area include a series of sedimentary, volcanic, and volcanic-clastic metamorphic rocks that extends from the green schist facies to the border of green schist and amphibolites along the northeast-southwest direction. These units have been repeatedly penetrated by alkaline intrusions, especially acid and granite (Rashidenjad, Omran et al., 2002).
In general, the controlling elements of mineralization in Muteh area include structural factors (faults and fractures), alteration, and deformation. Field observations indicate the occurrence of vein mineralization and gold sulfide deposits in mylonite shear zones and fault zones in felsic to mafic metavolcanic host rocks.
Gold mineralization is mainly concentrated in highly altered metariolites containing iron and copper sulfides and within fractures as veins and deposits. Alterations in silica, sericite, and carbonation are also observed along with these sediments, which are studied as exploration keys (Moritz et al., 2006).
In this area, according to the lithology and distribution of alteration zones and the type of mineralization in Muteh gold mine, gold orogeny-type mineralizations are expected, which can be indirectly identified by recognizing the above alteration.

In this study, Aster satellite images have been used to identify, discover and separate alteration zones in ENVI 5.3 software. Also, Landsat 8 satellite images have been utilized for general investigation and identification of hydrothermal alteration zones and expansion of iron oxide minerals, and Sentinel 2 satellite data due to better spatial and radiometric resolution than the above data has been applied to increase the spatial resolution of these data and the spatial accuracy of the map from the extracted changes.
In order to validate between the field observations and spectral analysis, 24 rock samples were taken from the place of alteration, especially siliceous, argillic, and sercitic alteration around Senjedeh and Chah Khatoon deposits. 11 samples were sent to Zarazma laboratory for XRD analysis, and five samples were sent to Zarkavan Alborz Company’s laboratory for chemical analysis of 41 elements by ICP-MS method and gold element by Fire Assay method.

Considering the relationship between alteration zones and metal mineralization, it is very important to know and map these areas in the exploration of these deposits.
The results and images show that the methods used in determining and separating the altered areas in Muteh exploratory area are acceptable and the optimal and effective methods in this research, SAM and MF, have been introduced.
According to the field observations and surface sampling around Chah Khatoon and Senjedeh mineral deposits, as well as the investigation of changes, it was found that the most important changes in the region are: silicification, kaolinization, sericization, chlorination, alonation, pyrite, carbonation and so forth. This wide range shows the difference in intensity of alteration in different parts of the mineral reserve, which can be attributed to the system of joints, fractures and faults in the region.
According to the available evidence, the metariolite rock is highly silicified in the tensile zones or in places with dense seams, and the pyrite particles in the context of these rocks have turned into iron hydroxide.

By using satellite data processing, various data and information can be identified and extracted. Satellite data processing is done in two ways: visual and digital processing. By combining these two methods, the desired effects can be detected more accurately than the accuracy of satellite images. The visual method consists of preparing images of different color combinations by placing spectral bands in the red, green, and blue channels. Digital satellite image processing methods include band ratio, principal component analysis, least square regression method (Ls-Fit), spectral analysis, spectral angle mapping (SAM), and adaptive MF filter. The selection of the above methods was based on the type of information requested to extract data from images.
Aster sensor images have no blue band (spectral range 0.4-0.5 µm) and the color composition of its VNIR bands is a standard RGB (1,2,3) false color composition. In this color combination, vegetation is seen in red. Since the study area is located in a relatively arid environment without vegetation, vegetation cover was avoided in the spectral analysis.
The use and processing of Aster satellite data is one of the main features of this sensor; the use of unique spectral reflectance curves of alteration indicator minerals helped to identify and highlight these altered areas as well as finding the potential of areas prone to metal mineralization. Due to the high ability of Sentinel-2A images in identifying gossan and iron oxide ranges, the processing of these data was used to highlight these areas better.

According to the agreement of the results of geochemical and XRD studies with the distribution map of the alteration zones identified from the reference spectrum (USGS) and the spectral library (JPL), with the distribution map of lines and structural fractures of Muteh exploratory zone outside the pre-identified areas, new alteration zones were also introduced that require field research to confirm the results of stereo data processing.

In today's world, advances in science and technology have led to the emergence of the information revolution and advanced cognitive tools. Space satellites are capable of capturing the entire surface of the earth in great detail. At the same time, the development of electronic warfare, including long-range and guided missiles of mass destruction, remote-controlled weapons and war robots, has posed serious threats to the security and survival of societies. For this purpose, defense-security planning has been designed as an effective solution against the existing threats. The purpose of this study is to organize the defense and security of Khuzestan provinces in order to identify threats and use potential defense and security capabilities. In explaining the relationship between land management and defense-security indicators, the important issue is that in the planning projects that have been discussed so far in the country, only demographic, economic, political, cultural, physical issues are considered and the issue of defense and national security and less considered areas. Is located; Therefore, the relationship between land use planning and defense-security indicators can be examined from different perspectives.

The research materials included basic maps obtained from the surveying organization as well as the geographical organization, including maps of critical, critical and important points. In addition, geological maps and other thematic maps have been used.

This research is applied in terms of purpose and descriptive-analytical in terms of method. The study area was Khuzestan provinces and the research period was 2016 to 2021. The statistical population of the study was the population of Khuzestan provinces according to the population and housing census data of the Statistics Center in 2016. There was no sample size in this study. The method of data collection was using documentation and survey. Research data for economic and social sectors were obtained from the Statistics Center. Data analysis techniques included frequency tables, descriptive graphs, spatial analysis methods, and spatial statistics techniques.

In this study, indicators were studied that can be considered as a representative for a large number of micro and macro indicators. According to these indicators, a picture of the security, defense and defense situation in Khuzestan provinces was shown. It is noteworthy that security cannot be achieved only with the tools of war and the use of military forces, and the threat is not only the existence of a foreign enemy. Rather, any tension that affects the comfort and well-being of the people is considered an insecure element and action must be taken to resolve it. Also, defense is not only the use of weapons and military forces, but also defense mechanisms must be prepared to deal with any insecure elements. Many sabotages in the country can happen without the attack of the enemy forces. In the field of defense planning, there is a need that any action and action for development and planning, must be accompanied by the principles of defense and the correct location of vital, sensitive and important elements. Also, the defense-security planning model showed that defense, security and defense planning pursue three main goals, namely deterrence, capability and self-sufficiency or self-reliance. According to the objectives of the powerful, safe and stable land as the three main arms in defense-security planning. A safe land is a security arrangement and a framework for understanding all the factors that disrupt order and security in the region. Powerful land indicates defense planning, which seeks to provide mechanisms to understand the maximum possible defense of the land and the region. Sustainable land targets defense planning. In this type of arrangement, the main purpose of camouflage is to hide and reduce the effects of possible attacks.

In the provinces of Khuzestan and Bushehr, it was found that in addition to military threats, there are other factors that have a civilian aspect; Therefore, in order to establish security and maintain stability in the provinces in question, it is necessary to consider various instances of security, defense and passive defense with a systemic view. Some of these factors have a natural aspect and others have a human aspect including social, cultural, economic, military, technological and political. Therefore, defense-security planning analyzes can consider the most important and effective scientific solutions to deal with military and civilian threats and to establish order and security.

The city, as human life, plays a fundamental role in creating a feeling of satisfaction, and in fact, it shapes the lifestyle of a person and determines the quality of his life. It should be noted that the quality of housing is directly related to the quality of life and the social and economic development of different communities; in such a way that the accommodation of families in inappropriate housing has become the basis of social problems and anomalies, which in turn, unfavorable social conditions will cause negative economic effects for societies. Quality of life studies can identify problematic areas, causes of people's dissatisfaction, residents' priorities. In life, the influence of socio-demographic factors on the quality of life and to monitor and evaluate the effectiveness of policies and strategies in the field of quality of life. According to the above, the purpose of this research was to measure the quality of life in Urmia city and five regions based on housing indicators. The originality and innovation of the current research can be expressed in the application of the new BWM (2015) and MARCOS (2019) models as well as the combined physical, economic, social and demographic indicators.

According to its purpose, this research is an applied research and according to the method of doing the work, it has a descriptive-analytical nature. The information was collected through library studies, field studies and census data of Iran Statistics Center in 2015. Thus, after studying the sources related to the research topic, 12 indicators have been selected to reach the research output, which include household density in a residential unit, population density in a residential unit, building age, building quality, building strength, land value, access to services. Education and treatment, housing ownership, plot area, infrastructure level, access to green space and residential density. Considering that each of the housing indicators used to model the quality of life has a different importance coefficient, therefore, in this article, the opinions of elites have been used to determine the weight of the indicators. In order to weight the indicators based on the BWM method, 10 questionnaires whose content is based on the pairwise comparison of indicators based on the preference of the best indicator over other indicators and the preference of other indicators over the worst indicator have been compiled. In the next step, the data of the questionnaires were entered into the GAMS software and were calculated and analyzed. The highest weight obtained is related to the building quality index with 0.201 and the lowest is related to the age of the building with an importance coefficient of 0.017. After calculating the weight of the indicators, in order to perform spatial analysis, first the information layers of the indicators were digitized and edited in the software of the geographic information system, and by converting the information layers into a raster and standardizing them based on the purpose of the research, the importance coefficient calculated from BWM in each of The indicators have been multiplied and the combination of the indicators has been discussed by applying weighting. In the last step, the MARCOS model was used to evaluate the quality of life in the five regions of Urmia.

Results & Disscussion:

After the 12 indicators of housing to measure the quality of life in the geographic information system software were classified and analyzed using the reclassification command and based on the research objectives, in order to model the quality of life in the city of Urmia by using the summation command and applying the obtained weights Based on the best-worst method, the indicators have been combined. The results of the combination of 12 housing indicators to model the quality of life in Urmia show that 23% of the city is in the very low quality of life zone, 34% in the low quality of life zone, 13% in the medium quality of life zone, 20% in the The quality of life is high and 11% is in the area of ​​very high quality of life. Based on the output obtained from the Marcus model, in Urmia city, region one, region five, region two, region three and region four are ranked 1 to 5 in terms of quality of life based on housing indicators.

The obtained results indicate that in general the quality of life in the eastern, northern, and northwestern parts of Urmia city is at an inappropriate level due to the presence of informal settlements, and the Shahrchai River border, which includes the 1st and 5th May areas. Due to the newly built area, it is in high quality. The results of the separate analysis of the indicators show that the quality of life in Urmia city based on the indicators of households in a residential unit, people in a residential unit, the strength of buildings, the area of ​​plots, access to educational and medical services and green space in a medium to high condition and based on the indicators The age of the building, the quality of the building, the value of the land, the level of infrastructure, housing ownership and residential density are in a medium to low condition.

 The best and most effective way to control wind erosion is to increase vegetation to cover the land surface. The roughness of the land surface is increased by vegetation. Because it increases the friction that causes a decrease in wind speed on the surface of the ground and the carrying capacity of sediments by the wind. By determining resistant species and more adapted to dry conditions, it will be possible to establish vegetation in these areas in different non-desertification projects to control and reduce wind erosion.

 In this research, in one of the critical centers of wind erosion in Gonabad County in northeastern Iran, investigated the performance of a biological project of non-desertification operations with Haloxylon aphyllum, Haloxylon persicum, Seidlitzia rosmarinus, Nitraria schoberi, Atriplex canescens and annual plants in different intensities of the drought for 2004 to 2021. At first, using the RDI index, drought intensities were determined in March, April, and May in the studied period. In the next step, the maximum, average, and minimum values of NDVI, TDVI, SAVI, and EVI indices were calculated using Landsat satellite images and data processing ENVI 5.3 software in each of the covered areas by desired specie in the studied months. In the final stage, the values of these vegetation indices were compared and analyzed for drought intensities in the areas and months.

 Based on the results, in all the indices, the area covered by Seidlitzia rosmarinus had a better condition than in other areas in the very dry drought intensity and with the highest value of 0.341 in the EVI index. But in the medium and mild drought intensities, the area covered with the Haloxylon sp had a better condition than in other areas and with the highest value of 0.456 in the TDVI index. However, all studied vegetation indicators did not show any significant difference between the planted areas. In March with the very dry condition, vegetation was more dependent on the intensity of dry conditions in February. The severity of the drought in February caused the values of all vegetation indicators in March in the studied areas to be negative, except in the annual species area. In March, the SAVI index, in April TDVI index, and in May TDVI and EVI indices had better ability to distinguish vegetation cover. The results of the Kruskal-Wallis test showed that in March, there was a significant difference between high, medium, and mild dry conditions only for the TDVI index at the level of 5% and the SAVI index at the level of 1%. In April, the NDVI and SAVI indices at the level of 1% and the EVI index at the level of 5% showed a significant difference between the three dry conditions. The results of the Mann-Whitney test showed that in May, only the SAVI index had a significant difference at the level of 1% between the moderate and mild dry conditions.

 The results confirmed the ability of vegetation indices obtained from Landsat satellite imagery to monitor the vegetation changes due to the drought. All the indices showed changes in the vegetation in the drought conditions, but no difference was seen between the vegetation areas. The resistance of the species to drought was one of the main reasons that caused there to be no significant difference between the vegetation areas, but the difference between the drought conditions was significant. Due to the adaptation and resistance of desert species to drought conditions, their sensitivity to drought in dry and desert areas is lower than in humid areas. In the condition that February is affected by drought, the cover conditions of annual plant species in the studied area in March were better than in other areas. But in March with very dry or moderate drought conditions, the cover conditions of Seidlitzia rosmarinus species were better coverage than in other areas. Based on the results, in the continuation and occurrence of moderate to high drought in April and May, the area of Seidlitzia rosmarinus showed a better cover than in other areas. In the condition of continued drought in March, annual plants do not have a chance to grow and the species that can use the moisture reserve in the deeper soil will have more opportunity to cover the surface of the ground, which this research showed that among the species in this area, Seidlitzia rosmarinus has more ability. Therefore, the principle of mixed planting and preventing single planting in the desert restoration and non-desertification projects should be emphasized and implemented.

The ionosphere extends from an altitude of 80 to more than 1000 km above the earth. Due to its electrical properties, this layer of the atmosphere has very important and fundamental effects on the electromagnetic waves passing through it. A parameter that can be used to study the ionosphere is the total electron content (TEC). This parameter is the sum of free electrons in a cylinder with a cross section of one square meter between the satellite and the receiver on the ground. The unit of TEC is electron per square meter (ele/m2). The TEC in the vertical direction is called VTEC. Usually, TEC is expressed in terms of TECU, which is equal to 1016 ele/m2.
Different methods have been developed to model the TEC. The simplest and most practical method is to use observations of two-frequency receivers. If there is a proper station distribution, it is possible to obtain accurate TEC and model the ionosphere. The main innovation of this paper is in the long-term prediction of TEC in the period of severe solar activity, as well as the modeling of the ionosphere time series with the long-short term memory (LSTM) neural network model in the Iranian region. This model is used for the first time in Iran to model and predict the time series of the ionosphere. To check the capability of the new model in prediction of TEC in the conditions of severe solar activity, observations from 2007 to 2016 are used for training and the TEC in 2017 is predicted. All the observations are related to the Tehran GPS station, which is one of the stations of the IGS network. To evaluate the accuracy of the model presented in this paper, statistical indicators of relative error, correlation coefficient and root mean square error (RMSE) are used.

Long-short term memory model
Long short-term memory (LSTM) neural network is a special type of recurrent neural network (RNN). RNN is a type of neural network that has internal memory; in other words, this network is a normal neural network that has a loop in its structure through which the output of the previous step, along with the new input, is entered into the network at each step. This loop helps the network to have the previous information along with the new information and can calculate the desired output based on this information’s. One of the problems of RNNs is the vanishing of the gradient when learning from long-term sequences, which reduces the ability to learn in the algorithm. LSTM networks are actually a type of RNNs that have had a change in their block (RNN Unit). This change makes LSTM recurrent neural networks able to manage long-term memory and not have the problem of gradient vanishing.

After the training step, using the trained models, the VTEC value for 2017 has been estimated and compared with the VTEC values obtained from GPS as a reference observation, GIM and NeQuick models. For the test step, the parameters of correlation coefficient, RMSE and relative error were calculated and presented in table (1). It should be noted that the average of all days of 2017 is showed in this table. Also, VTEC values obtained from GPS are considered as reference observations in this table.
Table 1. Statistical values of correlation coefficient, RMSE and relative error in the test step of 2017 for GRNN, LSTM, GIM and NeQuick models.
The correlation coefficient value of LSTM model is higher than other models. Also, the values of RMSE and relative error of LSTM model are lower than other models. This model has the ability to show the ionosphere time series variations with an accuracy of about 87%.

Analysis of the results of the correlation coefficient in 2017 for LSTM, GRNN, NeQuick and GIM models compared to the GPS-TEC was obtained as 0.84, 0.72, 0.77 and 0.71, respectively. The average annual relative error for these four models was calculated as 16.98%, 25.69%, 29.89% and 51.05% respectively. The results of the analysis showed that in the conditions of severe and quiet solar and geomagnetic activities, the accuracy and precision of the LSTM model is higher than the other models evaluated in this paper. The analysis of the coordinate components of Tehran station with PPP method showed that by using the model proposed in this paper, an improvement of about 5.19 to 56.23 mm can be seen in the coordinates of the station compared to other models.

Defense - security issues are always one of the most important factors in planning, and neglecting this important issue can have dire consequences in the national security of a country. So, Choosing the best location and defense-security locating of military bases has an important role in the process of providing security and fighting against the country's threats. In this context, identification of appropriate natural and human factors and criteria in defense-security positioning are important issues in this regard. Therefore, considering the importance of this issue, the purpose of this study is to analyze the defense-security locating of military bases with emphasis on the Holy Defense period in Kermanshah province.

The current research is applied in terms of purpose and its method is descriptive-analytical. The tools for collecting data and information are questionnaires and interviews. The statistical population is various military and security experts and experts in specialized fields related to security and political-military issues. Using targeted sampling, 50 experts were selected as samples. To analyze the data and answer the research questions, the exploratory unlimited cointegration rank test and the time series modeler method were used.

In order to investigate this, the factors and criteria for the defense - security locating of military bases, emphasizing the period of sacred defense, investigated two general categories of natural factors, which included 12 natural criteria, and human factors with 13 human criteria. The results of the research in the field of natural criteria affecting the locating of military bases in Kermanshah province showed that out of the 12 indicators considered for this, six criteria of faulting and seismicity of the region, geographical conditions of the region, topography of the region, unstable lands and occurrence The problems of creep and subsidence, land slope and land type have played an important role in the locating of military bases. In general, the results of the identification of natural criteria showed that the highest level of influence was related to the fault index and seismicity of the region and the lowest level of influence were related to the index of the number of frost days. The results of the research in the field of human criteria affecting the location of military bases in Kermanshah province showed that among the 13 indicators considered for human criteria; Six criteria of political and security considerations, the presence of transportation security in the region, distance from urban and rural centers, distance from international borders, lack of settlement in the vicinity of infrastructure and distance from the communication network of main roads play an important role in locating of the military bases. The results showed that the highest level of influence was related to the index of considering military-security considerations in the locating of military centers and the lowest level of influence was related to the index of distance from gas transmission stations and highways.

Finally, the results of the investigation of the general natural and human factors affecting the location of military bases in Kermanshah province showed that among the two groups, the role of the human factor is greater than the natural factor, and the human factors and And human factors and its indicators have been more important in locating military bases in Kermanshah province. Therefore, for the proper locating of military bases, it is necessary to pay attention to the natural and human factors and their criteria so that during the crisis or military attacks, the military bases will suffer the least damage And in order to ensure the security of military equipment and bases and to ensure the security of the entire country, less damage should be done to military equipment and bases. since Kermanshah province is a border province in the west of Iran And the country of Iran has been attacked many times from the region of the western borders, and the most recent one was the war imposed by Iraq against Iran, which is known as the period of sacred defense, Compliance with the principles of defense-security planning is one of the necessities that should be considered more than other non-border provinces.

One of the most important issues that has always threatened human societies throughout history has been the occurrence of natural hazards. Hence, urban thinkers and planners seek to develop approaches to reduce urban vulnerability and increase resilience. District 1 of Tehran Municipality is considered as one of the most dangerous and vulnerable areas of Tehran metropolis with its North Tehran fault, Niavaran fault, Mahmoudieh fault. Zone one is also constantly exposed to floods due to the high slope in the northern parts and the presence of runoff. High density of impermeable surfaces and high volume of runoff in zone one, as well as being at the foot of the mountain, are the main reasons for flood-potential in the study sample (Salmani Foumani et al., 1398: 51). The question is what is the vulnerability of district one of Tehran municipality against natural hazards (floods and earthquakes)? To identify the current situation, prioritize the necessary management and planning actions and planning in the face of a possible crisis of future risks.

The present study is applied in terms of purpose and descriptive-analytical in terms of method. First, using library and documentary studies, such as the study of texts related to the subject and previous research, and the use of expert opinions in this field, effective indicators on vulnerability in cities were identified. The raw data of the research are extracted from the statistical blocks of Tehran Region 1 and the GIS map of the study sample and for data analysis, reverse hierarchical analysis or IHWP is used.

In this part of the research, documentary studies were used to extract the indicators for assessing the vulnerability of urban areas to hazards. These indicators include: population density; Maximum ground acceleration; Distance from the channel; Fault; Access to medical centers; Width; Access to fire stations; Access to open and green spaces; Distance from gas station and CNG; Distance from worn tissue; Sewage cover; Distance from bridges. In the last step, the final map is obtained by classifying the data into 5 distinct categories in terms of vulnerability and by overlaying the layers. According to the results, of the total area of ​​District 1 of Tehran Municipality, 14.95% of the area with very low vulnerability, 23.28% of the area with low vulnerability, 27.03% of the area with moderate vulnerability, 23.59 with high vulnerability And 11.14% have a very high vulnerability. As can be seen in Map 4, the center and west of the region are more damaged and the damage is reduced from west to east. 

Due to the climatic and physical conditions of the region, the plan to widen the passages for narrow passages of the city, especially in the center of the region, should be considered. The rivers Jamshidia, Darabad, Darband, Darkeh, Lark, Maghsoud Beyk, Velenjak and Golabdareh may be flooded, so the river area in this section should be controlled; At the same time, in this field, with proper planning and management, steps can be taken to eliminate the shortcomings and problems.

The importance of the issue of security has caused the protection of borders and the defense of border areas to be considered by the rulers in all historical periods, and in a way, the protection of borders means the continuation of the governance system of each country. Throughout history, all countries have faced some degree of insecurity, chaos, crisis and border wars to stabilize their country. Many ethnic, racial, and religious groups have coexisted in turbulent political and social contexts in recent years and have lived on borders. Iran has been one of the countries whose borders have been in turmoil in recent years. In fact, Iran's borders have historically seen the most tangible state-nation conflicts; therefore, the issue of borders has always been one of the basic and important issues of governments. Iran's geographical location and the political situation of neighboring countries, along with the intervention of foreigners, have caused us to witness various tensions in the country's border strip in recent years, including Iran's eastern borders. One of the eastern border areas of the country that has faced tension in recent years is the borders of Khorasan Razavi province. In view of the above, the development of military infrastructure in the border strip of Khorasan Razavi province is very important. Due to the fact that the border strip of this province is not uniform in terms of environmental conditions, so the identification of areas prone to the development of military infrastructure, including military bases and observation posts, is very important in this study. Been paid.

In this research, in order to achieve the desired goals, descriptive-analytical methods as well as an integrated model of fuzzy logic and network analysis (ANP) have been used. The research data include a 30 m high SRTM digital model, 1: 50000 topographic maps and information layer related to the population points located in the study area. The most important tool used in this research is ArcGIS software. In this research, fuzzy logic and ANP models have been used to identify areas prone to military infrastructure development. According to the objectives, this research has been done in two stages. In this first stage, in order to analyze the role of geomorphological factors in the security of the border strip of Khorasan Razavi province, a map of elevation status and geomorphological units of this region has been prepared. In the second stage, using 8 parameters including slope, slope direction, field of view, altitude, distance from the river, distance from the communication road, distance from the border and distance from population points, as well as a combined model of fuzzy logic and ANP to identify areas prone to development. Military infrastructure (including military bases and reconnaissance) is discussed.

The study of the geomorphological status of the border strip of Khorasan Razavi province indicates that the border strip of this province has a high geomorphological diversity. The border strip of Khorasan Razavi province consists of 4 units of mountains, slopes, plains and alluvial fans, as well as hills. The mountain unit mostly includes the northern border strip of this province, which leads to the border of Turkmenistan. Due to its high altitude as well as being difficult to cross, this unit can play an important role in controlling the border strip as well as monitoring other areas. Therefore, one of the strengths of the northern borders of Khorasan Razavi province is the existence of a high mountain range and difficult to cross. Mahour hill unit is scattered in the border strip of this province, which has a lower height and slope than the mountain unit. Due to fewer obstacles and more visibility, this unit has a high potential for the establishment of military facilities, including military bases. The slope unit is located between the mountains and the plain, which has a high potential for military purposes, including various defense sites, because a large part of these slopes have eastern slope directions. However, the plain and alluvial fan unit, which is mostly located on the border with Afghanistan, can be vulnerable due to fewer geomorphological obstacles. Although this unit has a high potential for military transport and other military purposes, it is more vulnerable than other units. According to the mentioned cases, the border strip of Khorasan Razavi province has a great variety of geomorphology and each of its parts has different potential for different purposes.

The results of the study of the geomorphology of the border strip of Khorasan Razavi province have shown that this province has a high geomorphological diversity and this issue has caused the defense capability in different areas of the border strip of this province is not the same. Also, based on the results, the border strip of this province has a big difference in terms of environmental parameters, so the potential of each region for different military and civilian activities is different. Considering that in this research, the identification of areas prone to the development of military infrastructure has been considered with emphasis on military bases and observation posts, so the desired parameters have been defined in accordance with the objectives of the research and based on these parameters have been identified as areas prone to the development of military infrastructure. Based on the results, parts of the border strip of Khorasan Razavi province have a high potential for the development of military infrastructure and parts of it have a high vulnerability. According to the results, the northern regions of the border strip of this province, due to having a wide field of view, high altitude, the presence of slopes and directions of the eastern slope, have the highest potential to establish military bases and observation posts, as well as middle areas. Due to the lack of a wide field of view, low altitude and being located in the plain unit, this province has little potential for the development of military infrastructure (military bases and observation posts). Due to the above, the middle areas of the border strip of Khorasan Razavi province have a high potential for vulnerability, so it is necessary to make the necessary plans to control and monitor these areas.

UHI is a phenomenon whereby urban regions experience warmer temperatures than their rural surroundings. UHI influences well- being and welfare Average energy consumption and consequently, pollution and social equity of cities. Many factors contribute to urban heat island formation, as time (day and season), synoptic weather (wind, cloud), city form (materials, geometry, greenspace), city function (energy use, water use, pollution), city size (linked to form and function), geographic location (climate, topography, rural surrounds). Due to UHI adverse impacts on urban metabolism, ecological environment, the favourable living condition of cities and overall livability of cities, it has been an important research topic across various field of study and scholars gave more and more attention to it.  UHI has been studied for a long time, it was first described by Luke Howard in the 1810s. During the last decade Significant research efforts have been performed to evaluate the urban heat island phenomenon's impact on the urban environment. According the literature review the main goal of this study is; exploring the effect of Urban Morphology on UHI, in the Tabriz city.

This study is a correlation one. Be. In this research, ArcMap, ENVI and SPSS software have been used to generate data and apply relationships. To conduct this research, Landsat 8 images of OLI sensors at different dates for summer and winter have been used. In this study, to evaluate the UHI and influenced area of the city, the satellite images of land sat 8 OLI/ TIRS (thermal band 10) were used. The land sat 8 OLI/TIRS images that covered Tabriz summer and winter in the year of 2014 to 2019 were provided by USGS.
To perform radiometric correction of images from ENVI 5.1 software using FLAASH method. Flash is the first atmospheric correction tool that corrects visible wavelengths and infrared and infrared wavelengths of up to 3 micrometers. In the flash method, the Meta Data file is used to correct the desired bands, which include multispectral bands and thermal bands. For multispectral bands, radiance and reflection operations were performed, but for thermal bands, only radiance operations were performed. In this context, the Lowest and Highest  Position, Spatial Autocorrelation, Hot and Cold spots and finally multivariate Regression analysis were used.

The results of this study showed that the high temperature is most widespread in suburban areas especially in north west and south east rather than central parts of the city. According to the research findings, the average temperature of Tabriz in summer for the studied periods is equal to 37.7 ºC. also the average temperature varies in different years and does not show a specific trend. The average temperature of the city during the study period in winter is equal to 11.8 ºC. But according to the finding, the average temperature of the city in summer and winter is low compared to the surrounding areas. The average temperature difference between the city and surrounding areas is 33.7 ºC and 22.5 ºC in winter. Findings related to the autocorrelation pattern of Moran spatial analysis also show that the distribution of UHI in the city of Tabriz is clustered. The present study also showed that urban morphology can affect the intensity of Heat Islands. 
Based on the findings of regression analysis and calculated F (17.65) and the coefficient of significance obtaind at the level of 0.00, the predictor varizbles can well satisfy the behavior of the research dependent variable in the summer. For winter, the whole model can be generalized according to the calculated F (9.36) and significance coefficient (0.00).  on the other hand, the present study showed that the distance from the green space has an effect on the intensity of UHI, so that based on the findings of the study and calculated F(7.596) and significant level(0.00) this can be confirmed.

The present study sought to investigate the effect of urban morphology on the intensity of UHI. For this purpose, we used Landsat 8 satellite images and the technique of separate window algorithm to estimate the surface temperature. Spatial statistical analyzes such as Moran and Hot & Cold spots and multivariate linear regression were also used for analysis. In line with previous studies conducted in Iran, this study also showed that the temperature inside the city is cooler than the surrounding temperature and in a way in a city like Tabriz, we are facing cold islands instead of heat islands. The reason can be related to the compactness and high density of buildings in the cities, which requires further research. This study also showed that the surface temperature is affected by urban morphology and distance from green space. The research opens new field for future researches.