جستجوی مقالات مرتبط با کلیدواژه « geographically weighted regression » در نشریات گروه « جغرافیا »

The COVID-19 epidemic is considered a geographical phenomenon, and its impact on decision-making and daily life is significant. Geographic information systems (GIS) and spatial techniques play crucial roles in analyzing the spread of COVID-19 globally. Studies using spatial analysis have highlighted the importance of social and health variables in infection and mortality rates, despite existing uncertainties about the effects of meteorological variables. Given Iran's climatic diversity, it is valuable to identify the key spatial factors influencing COVID-19. Therefore, this study aims to model and determine the factors affecting the COVID-19 epidemic based on available data.

This study investigated the factors influencing the distribution of COVID-19 infection rates using global and local spatial regression methods. Seventy-three cities were selected, with data on COVID-19 infections available from March 10 to June 20, 2019. The factors considered were altitude, population density, average age, the ratio of the population over 55 years to the total population, and meteorological parameters, including humidity, temperature, pressure, and wind speed. Their relationships with the disease were analyzed using spatial statistics methods. Stepwise regression identified population density, air pressure, average age, and wind speed as significant predictors, and the occurrence of the disease was modeled using the Ordinary Least Squares (OLS) technique. Due to the unstable relationship between the independent and dependent variables, the Geographically Weighted Regression (GWR) technique was used. Principal Component Analysis (PCA) and SPSS software were employed to address spatial variability and multicollinearity.

The results showed that the OLS model was statistically significant, with variance values explained by the model being non-random. However, the explanatory variables had an inconsistent relationship with the dependent variable in both geographic and data spaces. The residual distribution deviated somewhat from normal, indicating model instability. Thus, the GWR technique was applied for modeling. PCA addressed multicollinearity (due to a cluster pattern in meteorological variables), reducing meteorological factors to one component, explaining nearly 70% of the variance. The model improved by consolidating the average age and the ratio of the population over 55 into one factor. Subsequently, population density, meteorological factors, and age demographics were utilized as predictive variables in the GWR model. A 10% increase in the adjusted R-squared of the GWR model (63%) demonstrated its relative improvement over the OLS model. Moran's spatial autocorrelation test indicated that, while the cluster pattern of residuals was less pronounced in the GWR model than in the OLS model, it remained significant at the 99% confidence level. Hot spot analysis at the 95% confidence level identified the western parts of Kurdistan province and the northern and western parts of Khuzestan province as hot spots (areas of significant underestimation), and the eastern parts of Hamadan province and the northern parts of Bushehr province as cold spots (areas of significant overestimation). Thus, at least one variable affecting disease occurrence was not considered. Other potential factors, such as cultural, health, and genetic variables, were not included due to unavailability or measurement difficulties.

This study highlights the importance of demographic and environmental factors in COVID-19 infection rates and provides a foundation for further research in the study area.

Forecasts indicate a significant increase in population in urban centers. Larger urban centers and metropolitan areas, such as magnets, often attract this population through various forms of migration. This growing flood of migration to large cities, which is usually faster and more intense in third-world countries, creates many problems at the source and destination, including the need for more urban and public services in the destination and the shortage and loss. One of the main destinations of immigrants from villages and small towns is to move to the city center of the province, a big city that acts as a metropolis in the region.One of the provinces in Iran where such migration flows are observed is the West Azerbaijan province, where research on the trends and reasons for the migration of its cities to the center of the province seems necessary. In this research, the following questions have been answered:What has been the process of emigration to the province's center during the period of 85-90 and 90-95?Spatial distribution of migratory data on which of the following spatial distribution patterns was consistent?What factors affect the emigration of the city population to the center of the province?

The present study is a descriptive-analytical research with an applied approach. The data used from library resources such as statistical yearbooks of the province were extracted from the Statistics Center of Iran, and in their analysis, spatial statistics and inferential statistics were used. Spatial statistics analysis is performed in the ArcGIS software environment. In this regard, first, the immigration رده بندی maps of the cities were drawn according to the statistics published by the National Statistics Organization in the two periods of 85-90 and 90-95.Data analysis was performed in two parts: trends and causes of migration. Regarding the migration process of cities to the center of the province, first, by Moran spatial autocorrelation statistics, the type of spatial distribution of migration data was investigated and hot spots of migration were identified by using hot spot analysis. Then, the factors affecting the migration of cities to the center of the province in the form of independent variables were modeled using geographically weighted regression (GWR) analysis.

Salmas city, with 3776 people, had the highest, and Takab city, with 333 people, had the lowest number of emigrants to the center of the province. The rate of emigration from other cities was between these two cities.According to the value obtained for the Moran index, which is positive and significant, the migration data of cities have spatial autocorrelation and cluster spatial distribution pattern and are not randomized or scattered. Hot spot analysis was used to identify places with high-value clustering or hot spots. The results showed that in the period of 90-95, high amounts of emigration in Khoy and Salmas counties had formed hot spots.However, the correlated t-test showed no statistically significant changes in the rate of emigration in the mentioned period. The variables considered and related to the theoretical foundations and research background in the form of geographically weighted regression analysis have been affected by the dependent variable, the migration rate to the province's center. In this regard, five variables of population density, distance of origin and destination, the number of urban services, the urbanization coefficient at the origin, and the number of job applicants at the origin entered the regression model. The model's results were evaluated with goodness of fit (GOF) indicators. The value of R2 for the whole model is 0.773438, and the value of Local R2, for other complications (cities), varies from 0.772427 to 0.773186, which is close to the value of 1, and in general, shows the goodness of the regression model.The regression model has been able to explain about 65% of the changes in the dependent variable. In the next step, by performing Moran autocorrelation analysis on the residual values of the regression model, the residual spatial distribution pattern was investigated; the value of Z obtained for the residual distribution is negative, and no cluster distribution is observed in the residuals, and the residues follow the pattern of random spatial distribution.The effect of each variable on the dependent variable of the migrant was evaluated; the effect of the population density variable in the northern cities of the province was more than in the southern cities of the province. The effect of the origin and destination distance variable is more evident in the south and southeast of the province than in the north. Changes in the effect of the variable number of job applicants at the origin, from northwest to southeast of the province, have an increasing trend. The effect of the urbanization coefficient variable at the origin from north to south of the province shows a decreasing trend. Contrary to the effect of the variable of having urban services at the origin, the trend is increasing from the north of the province to the south and southeast of the province.

In this section, the main research questions were answered. Migrant data has a clustered distribution pattern. The trend of migration of cities to the center of the province during the periods of 90-85 and 90-95, in general, does not show statistically significant changes.Regarding the causes of migration to the center of the province, it can be said that the five variables of population density, a distance of origin and destination, level of urban services, urbanization coefficient at the origin and the number of job applicants at the origin, explain 65% of the dependent variable changes.

The significant increase in urbanization along with excessive population density and activity in cities and its growing trend in terms of functional and physical diversity has increased the importance of the issue of urban vulnerability against natural hazards such as floods. Using 54 key indicators in the framework of the MOVE model, this research has determined the level of social-physical vulnerability in the areas of Tehran. Then the results are spatially analyzed and the degree of vulnerability of each dimension as well as the final index has been determined. MOVE and GWR models have been used in this research. The results showed that in the final index, the southwest and northeast neighborhoods of Tehran had the most unfavorable conditions, and on the contrary, the central areas of Tehran had the most suitable conditions. Regions 18, 19, 20 and 4 had the most neighborhoods with medium to very high vulnerability status. Also, the neighborhoods located in regions 8, 6, 10 and 7 had the best conditions, respectively. Also, the results of the geographically weighted regression model showed that the sub-indicator of exposure had the most impact, and the sub-indicators of lack of resilience and susceptibility were placed in the next ranks, respectively. In the meantime, according to the R2 coefficient that is close to the average in total for all sub-indices, it can be said that the final index obtained had a great impact on the high vulnerability of the residents of the studied neighborhoods.

The purpose of this research is to select temporary accommodation centers after the earthquake crisis to meet the needs of the victims. Therefore, this research has tried to identify temporary accommodation sites in District 22 of Tehran with the help of effective criteria. The required data has been obtained from the Tehran Disaster Mitigation and Management Organization and the results of the general population and housing census of 2017. The novelty of this research is to present a new combination approach to determine the effective criteria for locating temporary shelter sites. In this regard, the combination of geographically weighted regression (Gaussian and tri-cube kernels) with a binary particle swarm optimization algorithm was used. The recommended combination method is suitable for spatial regression problems because it is compatible with two unique properties of spatial data, i.e. spatial autocorrelation and spatial non-stationarity. The best value of the fitness function (1-R2) for Gaussian and tri-cube kernels was obtained at 0.04616 and 0.0097, respectively, which indicates the high compatibility of the tri-cube kernel with effective criteria. According to the obtained maps, Chitgar Park and Azadi Sports Complex are some of the widest and most suitable areas for the construction of temporary shelter sites after the earthquake crisis in the case study. By identifying temporary shelters, relevant organizations can provide the appropriate infrastructure for these selected centers so that there is no need to spend time to provide these services in the event of an earthquake.

Water is one of the critical needs of human life and living things. Therefore, proper planning is important for its consumption all over the world, especially in Iran. This study was conducted to evaluate the impacts of land use change on water yield in the Teraz watershed, Khuzestan province, Iran, from 1990 to 2050. Water yield was evaluated using integrated valuation of ecosystem services and tradeoffs (InVEST) tool and land use was mapped using the maximum likelihood classification in the ENVI 5.3, and CA-Markov in the TerrSet environment. Moreover, the relationship between water yield and landscape metrics, including the number of patches (NP), patch density (PD), landscape shape index (LSI), and Largest Patch Index (LPI), was considered based on the Geographically Weighted Regression (GWR) method in the Arc GIS 10.5. The results showed that the area of ​​forest and rangeland in the studied area decreased in the last 30 years, by 3199 and 1611 ha, respectively, and the area of ​​agriculture and construction land uses increased by 4388 and 387 ha, respectively. It is predicted that in the next 30 years, 2442 ha of forests will decrease and the area of ​​agriculture, rangeland, and construction land uses will increase by 1651, 687, and 102 ha, respectively. It was found that the total volume of available water yield in the region is equal to 26.5 Mm3 in 2020, on average of 857 m3 ha-1, and based on that, the ranking of land uses is as follows: 1. Construction, 2. Rangeland, 3. Forest, 4. agriculture. The results of GWR confirmed that water yield had a significant and negative spatial relationships with the NP, PD, and LSI metrics (R2>=0.83, p-value>0.05), while its relationship with the LPI metric was a significant and positive relationship (R2>0.84, p-value>0.05). It can be concluded that the landscape features and land use pattern can determine the production and yield of water in the study area.

Due to the increase in the occurrence of floods, especially in the cities, and the emergence of human, financial, and environmental risks due to its increase, the flood zoning areas are of great importance. Therefore, in this study, it was tried zoning the areas of floods with the help of determining effective criteria. The criteria used in this research include Modified Fournier Index, Topographic Position Index, Curve Number, Flow Accumulation, Slope, Digital elevation model, Topographic Wetness Index, Vertical Overland Flow Distance, Horizontal Overland Flow Distance, and Normalized difference vegetation index. The novelty of this study is to present a new combination approach to determine the effective criteria in flood hazard zoning (Maneh and Samalqan County). In this regard, the combination of geographically weighted regression (Gaussian and tri-cube kernels) and binary particle swarm optimization algorithm was used. The recommended combination method is suitable for spatial regression problems because it is compatible with two unique properties of spatial data, i.e. spatial autocorrelation and spatial non-stationarity. The best value of the fitness function (1-R2) for Gaussian and tri-cube kernels were obtained 0.0745 and 0.0022, respectively, which indicates higher compatibility of the tri-cube kernel than the Gaussian kernel. It was also found that the criteria used have a significant effect on the rate of flooding in the study area.

Nowadays, spatial models and techniques are widely used to analyze challenges at urban and regional levels. These models and techniques can identify the relations between different variables, evaluate their impact on spatial spheres, and thus aid urban planners and managers. Recently, solid waste and the amount of waste generated in urban areas have gained attention as a major global challenge and the World Bank has highlighted the importance of an acceptable global approach to the issue of urban waste in 2016 (World Bank, 2016). Urban waste impacts the city and its urban management system in different ways such as urban environment degradation, economic impacts and the challenges of urban landscape. Different factors impact urban solid waste generation and investigating the relation between these variables can help urban planners and managers formulate general plans and policies to reduce urban waste. But a mere examination of the relationship between factors affecting urban waste generation and the variables proposed by the World Bank cannot provide a good estimate of the future status, since spatial factors always impact the quantity of urban waste generated. Therefore, spatial models and artificial neural networks were proposed and discussed. Geographically Weighted Regression is one of these methods used to investigate the relationship between different factors affecting urban waste generation. Geographically Weighted Regression can investigate the relationship between different variables, examine their impact on the city and predict the relationship between different variable of urban waste generation and their impact on the city in the future. The artificial neural network was also used to assess the nature of data and predict the future status of urban waste.  

The study area consists of 22 districts, 123 zones (116 zone due to the availability of supplementary information of 2011-2012 regarding the districts of Tehran), 40323 statistical areas and 895247 land uses of Tehran. Data were classified in three stages.  The first phase includes the information collected from Tehran waste management organization regarding urban waste in 1996 to 2016. In the second phase, information was collected from statistical center of Iran regarding demographic segments and social components. Finally, data were collected from Tehran municipality in the third phase providing useful information about urban performance (Land use).  

Physical-environmental components and especially land use directly impact urban waste generation. However, results indicate that some land uses such as institutional and publicbuildings gradually stop the increasing process of urban waste generation due to a decrease in their population as compared to residential land use. Population density and income ratio are investigated as the first and second rank variables. These two variables have directly impacted the amount of urban waste generation in most districts of Tehran. From central areas of the 6th district to the southern areas of the 20th district, southeastern areas of the 18th district and eastern areas of the 4th district of Tehran were influenced by population variables. In other words, the amount of urban waste generation is increased with increased population density in these district. However, the amount of urban waste generation in the 22nd and 21st districts do not change with the above mentioned variables. Results indicate that different urban development plans and policies increase population and area dedicated to different land uses and thus, play an important role in urban waste generation. The 22nd and 21st districts are in a desirable status regarding variables such as area, population, and urban waste generation, but predictions indicate that they will reach a similar status and face challenges related to urban waste generation in 10 years. Spatial distribution pattern of urban waste generation in Tehran indicates that the eastern and southern districts produce the highest amount of urban wastes. This pattern is gradually moving from central to western and central districts, and without a plan to control the situation, the pattern will move from east to west and south to north of Tehran in the next 10 years. Based on the results of spatial autocorrelation and a comparison with the results of the least squares method, Geographically Weighted Regression was considered as a suitable method of predicting urban waste variables in Tehran. This indicates that spatial variables affect urban waste generation in Tehran. Moreover, artificial neural network is capable of predicting non-spatial nature of relations among different variables of urban waste generation and thus can predict the amount of urban waste generation in Tehran.  

Results not only identify (physical-environmental, economic and social) variables affecting urban waste generation, but also indicate superiority of Geographically Weighted Regression technique at spatial and non-spatial levels as compared to the least-squares regression and artificial neural network.

Spatial Analysis of belonging 'sense to a place in Restoration of Deteriorated Texture using the Geographically Weighted Regression in the region three of TabrizHassan Mahmoudzadeh1, Osman soufi Bobakran2, Sohaila Normohammadi31. Associated Professor of Geography & Urban Planning, Tabriz University, Tabriz, Iran.Email: [email protected] Tel: 091431492522. MSc of Remote Sensing and Geographical Information System (GIS), Faculty of Planning and Environmental Sciences, University of Tabriz, Tabriz, IranEmail: [email protected] Tel: 093826399093. MSc of Remote Sensing and Geographical Information System (GIS), Faculty of Planning and Environmental Sciences, University of Tabriz, Tabriz, IranEmail: [email protected] Tel: 09335409265IntroductionThe sense of belonging is a dimension of the totality of the sense of place and the positive attachment that is created between the individual and the place. In the meantime, worn-out textures and old neighborhoods, as the dominant beating heart of cities, are the most important public spaces that need to be taken care of and kept by residents within the texture. Today, the revitalization of these textures has been the focus of many planners and designers by prioritizing the needs of residents and communicating with the physical space as well as issues related to location. Considering the issues raised, attention to worn-out urban contexts, both spatial and psychological, seems to be essential to increase residents' satisfaction. For example, worn-out urban contexts are one of the problems that, outside of the legal system, have diminished the appearance and quality of urban life, and have created many roads and densities of services, infrastructure, and urban facilities. The issues raised indicate that the need to intervene in aging tissues to improve their quality of life is crucial. In Tabriz, worn-out textures account for one fifth of the city's total area of 2,530 hectares, making it the second largest city in terms of worn-out textures. According to the latest estimates, 400 to 500,000 Tabriz citizens live in these areas. Studies show that the rigid regulations of urban planning, lack of adequate financial resources, lack of ingenious and strategic management in the worn-out textures over time, swallows Tabriz. On the other hand, the worn-out texture of Tabriz as a vibrant, vibrant urban location has obvious physical, semantic, and functional differences among its neighborhoods, which has had a significant impact on the sense of belonging. Therefore, based on many scientific studies, research on the subject involves the use of numerical and statistical information that is influenced by the concept of space and environment. Spatial data are therefore the most basic and important data used by environmental and geoscientists in their research.MethodologyThe conventional global regression method assumes a constant relationship between spatial variables for modeling the area that does not take into account spatial instability of the variables. The major advantage of GWR geographic weighted regression over conventional regression models is its ability to investigate spatial instability. Spatial instability indicates that the measurement or estimation of relationships between variables varies from place to place. The GWR method is a regression technique that significantly improves ordinary regression for use in spatial data. Therefore, the maps generated from these analyzes play a key role in the non-stationary spatial description and interpretation of the variables. In this method, the coefficients of the explanatory variables are estimated using weighted matrices. The weight of each variable in this method is determined based on the distance of each observation to the estimated position of the variables. One of the methods of estimating model parameters when there is dependence between observations of each point in space is GWR. The main idea of geographic weighted regression is that the study of independent and dependent variables in the study area is done in places where their position is known.Result and discussionSince different indices can be used in regeneration of worn-out tissue, in this study, sense of location is considered as dependent variable and other parameters in three social, physical and environmental indices as independent variables. They have also been used to obtain goodness of fit indices (R2). The VIF index was used to determine the linearity of the independent variables. VIF is a feature used to know whether or not there is a linear relationship between independent variables. This index shows the intensity of the linearity between the independent variables (multiple linearity).In fact, the index indicates how much of the change in the estimated coefficients for each end. The minimum value of this positive index is one and its maximum is infinite. As an empirical rule, if the VIF value is greater than 7.5, it represents a high multiplicity of linearity. Based on the results, the VIF index for the variables used is not so much that they cannot be involved in modeling (VHF> 1, VIF)

Rainfall is amongst the most important climatic elements with a lot of spatial and temporal changes; in contrast to the other climatic phenomena, rainfall features more notable movement complexity. The studies performed in this regard indicate that such a climatic element as rainfall features a non-stationary behavior with a vast part of this non-stationariness being the result of the rainfall’s being influenced by the spatial properties and the complex pattern of the spatial organization causes the emergence of complex behaviors in the precipitations. The importance of the rainfall as the country’s water resource and the daily increasing reduction of the country’s water reservoirs demands the study of the rainfall’s behaviors. In the present study and by the assistance of the methods of spatial statistics, the spatial pattern of the spring rainfalls in the northwest of Iran will be elaborated. 
Data and

The study area of the present study is the regions in the northwest of Iran (Azerbaijan-e-Gharbi, Azerbaijan-e-Sharghi, Ardabil, Kurdistan and Zanjan Provinces) and, to perform the study, use has been made of the monthly precipitation data acquired from 121 synoptic stations as well as climatological investigations and precipitation studies for a period between 1994 and 2014.In order to perform the spatial analysis of the precipitations, use has been made of the digital map of the elevation in the environment of ArcGIS software for extracting slope and dip. In the next part and in order to analyse the spatial structure of the rainfall and investigate the degree of similarity between the data acquired from 121 station points, use has been made of the half pseudo-variance spatial correlation index. The Semivariogram has been estimated based on the arithmetic mean of the intervals.In the present study, use was made of the longitude and latitude of every station point and the rainfall rates of every point for delineating the empirical Semivariogram for three months, namely April, May and June in the environment of Variowin Software, version 2.2; then, various theoretical models were estimated in terms of their goodness of fit and the exponential model was selected as the best model for every month.In order to analyse the spatial factors influencing the spring rainfalls in the northwest, the balanced geographical regression model was estimated in terms of its goodness of fit with its output being the indicator or indicators influencing the occurrence of spring rainfalls according to the explanatory variables of slope, dip, elevation and latitude.

Following the investigation of the data related to April, it was made clear that the effect of the elevations on the rainfall variations is significant in this month in the entire parts of the region. The highest significant effect of the elevation has been in the central parts of the region for such a reason as the large density of the mountainous masses in this part and the passing of precipitation systems from these regions. In parts of the region’s north (north of Azerbaijan-e-Gharbi, Azerbaijan-e-Sharghi and Ardabil), the significance rate of elevation is reduced because these regions are plains and plateaus and lower in elevation than the other areas. Latitude has been found having a significant effect in the southwestern sections of the region (south of Azerbaijan-e-Gharbi, Kurdistan and Zanjan) and, in a more scattered manner, in the north of Urmia Lake and it seems that the reason for such a significance is the passing of the precipitation systems from the southern sections of the region.As in April, the effect of the elevation on the rainfall has been also found significant in all the sections of the region in May. The highest rate of significance has been found centered in the western and central sections of the region (particularly in the central parts) and this is completely due to the existence of the mountainous air masses. Considering the gradual displacement of the western winds towards the northernmost parts of the region and the vertical irradiation of the sunlight onto the sun-facing foothills, the role of the elevations becomes more accentuated in the creation of convectional rainfalls and the regions with lower elevation would receive lower precipitations. In June, as well, except the south-eastern section of the region (eastern half of Zanjan Province), the other regions have been found with the significant effect of elevation on the creation of rain. In this month, the conditions fit the occurrence of foothill convection in the studied area. The highest effect of the rising and falling lands on the creation of the rain has been evidenced for the north-western sections and this is in match with the path through which the western winds pass on these days; that is because the rain-causing winds are present in this section in this month and, considering the region’s elevations, cause the occurrence of rainfall. The effects of latitude in June is like those in May and the presence of the western winds and setting of the ground for the foothill convention causes rainfalls in the northern and central section of the study region.

Elevation has been found influential in the entire studied region on the rainfall because the high density of high grounds causes the ascension and condensation of the humid air that causes rainfall. Besides elevation, the dip also influences the rainfall in Kurdistan and south of Azerbaijan-e-Gharbi because the orientation of the foothills in this section sets the ground for the dynamic ascension of the humid air. In Ardabil and north of Azerbaijan-e-Sharghi, slope is also an effective factor. The high slope of these regions causes the acceleration of the humid air masses’ ascension. The effects of the latitude on rainfall during spring are different and mostly related to the presence of the western winds; in April in Kurdistan and in May and June in Azerbaijan-e-Sharghi, latitude has been found with the highest effect on the rainfall.

In recent decades, Tabriz metropolis as the largest city in the northwest of the country has faced with increasing population growth and development of industrial, commercial, services and residential structures. Increasing development along with failure to comply with land use planning criteria has led to an increase in air pollution. Current study has been carried out in order to understand factors causing pollution in Tabriz city. Research method is descriptive analytical and the type of the information is documental- library. Eight indicators, i.e. floor area ratio, population density, intersection density, bus stop density, industries density, green spaces density, distance from industries and elevation were used as predictor variable. NO2 concentration was used as dependent variable and wind flow was used as an emission factor. In order to analyze the data, ordinary least squares and geographically weighted regression was used. According to the results of ordinary least square, the relationship between predictor variables and dependent variable is significant. So that the concentration of nitrogen dioxide increases with increase in floor area ratio, population density, intersection density, bus stop density, and industries density. In fact, there is a direct correlation between these variables and the concentration of nitrogen dioxide. By increasing the elevation and the distance from industries, the concentration of this pollutant decreases, which indicates an inverse correlation between these two variables and the dependent variable. Based on the results of geographically weighted regression model, considered variables account for 62% of air pollution in the city. Finally, maps of spatial variations of independent variables were drawn by using geographic weighted regression in the city of Tabriz.

The rapid development of Tehran has increased air and noise pollution which lead to the unsustainable development. Since most vulnerable groups are more exposed to pollution due to the disproportionate distribution of air and noise pollution, the main objective of this research is to investigate the relationship between socioeconomic factors and air and noise pollution distribution in order to evaluate urban environmental justice of Tehran. In order to analyze the spatial distribution of mentioned pollution, air and noise pollutants have been studied. Pollution by stationary and mobile sources were analyzed in 22 districts of Tehran using geographically weighted regression model. The results reveal that geographically weighted regression model with local R2 was 0.94, 0.59 and 0.85for the amount of pollutant emissions from domestic consumption, vehicle and motorcycle ownership respectively, with acceptable accuracy for modeling between the socioeconomic rank and air pollution source. Findings from noise pollution revealed that the model with R2 0.43 does not strongly confirm the relation between the socioeconomic rank of areas with noise pollution. This study showed that the 1,3 and 6 regions, with higher rank in terms of socioeconomic status, have the highest air pollution production, while the 18, 19, 20 regions with the lowest socioeconomic rank are more likely exposed to air and noise pollution. Hence, more vulnerable groups face urban environmental injustice. Extended Abstract 1-Introduction Urban development, regardless of environmental and social benefits, has led to severe problems such as air and noise pollution which is considered as the most complicated environmental issue in the city of Teheran leading to urban unsustainable development. As revealed by different studies, cities that are closer to sustainable development standards have a higher level of social and environmental justice. Therefore, the fair distribution of facilities and environmental risks is an essential step to achieve sustainable development standards. Since air pollution is the most serious and complicated problem in Tehran, identification of the spatial pattern of air pollution emission and exposure risks with emphasis on environmental justice is of immense importance. Other conducted research on air pollution in Tehran has not focused on social and economic issues and environmental justice. Therefore, the aim of this study is to investigate environmental justice in urban districts of Tehran by determining the relationship between air and noise pollution variables and socioeconomic indicators in 22 municipal districts of the city to fill the gap in previous studies. 2-Materials and Methods Two categories of data were required to conduct this research: 1) Air and noise Pollution Concentration Data; 2) socioeconomic status Data. Residential per capita, the average per square meter price and Total land ownership, the job status indicator and the percentage of employers and managers, higher education attainment and illiteracy percentage were reviewed in each district. Finally, the socioeconomic status ranking map was obtained by overlaying the maps of the mentioned indicators for each district of Tehran. After preparation of data sets, each set is analyzed and mapped for each of the 22 districts of Tehran by using GIS and spss16 software. In this study, the geographical weight regression method has been applied in order to investigate the relationship between air pollution and socioeconomic status. 3-Results and Discussion In order to evaluate urban environmental justice, the final socioeconomic ranking map produced for urban areas show that district 3 and 18 have the highest and lowest ranks respectively. Based on results, there was no significant correlation between air pollution monitored by air quality monitoring stations and socioeconomic status.  However, based on the modeling of air pollution, districts 1 and 3 of Tehran have higher socioeconomic status. Local R2 showed a significant relationship between the percentage of car ownership and pollutants from domestic consumption and socioeconomic rank. The results of modeling the pollutant emissions from domestic consumption, car ownership and motorcycle ownership with local R2 are 0.94, 0.59 and 0.85, respectively, with acceptable accuracy for modeling the correlation between the socioeconomic status and air pollution emission. The local R2 value was insignificant in relation to the concentration of pollutants recorded by Tehran's air pollution monitoring stations. 4-Conclusion  urban Environmental justice is one of the most crucial environmental issues in urban areas, although the importance of this subject has been ignored in Tehran. To fill this gap, the metropolis of Tehran has been selected because of its high population density, high volume of air pollution and also high social inequality. In this study, the correlation between emission of air pollutants in urban districts and socioeconomic status of the same districts was compared by quantitative spatial analysis using geographically weighted regression model. It can be concluded that the more disadvantaged and marginalized socioeconomic groups in southern districts suffer from the most air pollution risks, while groups with higher socioeconomic status in northern Tehran emit more air pollution than Southern residents. The novelty of this study was to explore the spatial correlation between socioeconomic status and air pollution, relying on the environmental justice approach. The Contribution of this research, compared to other similar studies, is considering socioeconomic issues related to air pollution by applying environmental justice approach by specialization the relation between socioeconomic status and air pollution in 22 municipal districts of Tehran.

The scattered growth of cities, besides the negative environmental and economic impacts, has high societal costs, with expanding and distancing urban neighborhoods from the city center and the formation of urban suburbs more and more. The first goal of this study is to analyze the urban dispersal effect on social capital of Maragheh township. The second goal is to compare the results of multivariate regression with geographical weight regression. The present study consists of three stages: urban dispersion, social capital survey of neighborhoods, and finally, measuring the impact of dispersed indicators on the amount of social capital in urban areas. The number of urban dispersal indicators was 6, and the number of social capital indicators in 5 main factors and 39 sub-indicators. The research method is descriptive-analytical, which has been used for surveying and documentary methods. Data gathering of dispersed indicators by studying the comprehensive city-specific layout developed using ArcGIS software. Social capital information was collected through 383 questionnaires. For data analysis, multivariate regression and geographic weight regression have been used. The results of the study show that the results of multivariate regression are less reliable than geographic weight regression considering the nature of spatial data.

Analysis of spatial patterns of deterioration and spatial relationships between deterioration and its influencing factors in order to better understand of effective factors and improve performance of urban renewal management is very impressive and significant. So this research uses spatial statistical methods to analyze the spatial pattern of deterioration and its influencing factors. The results of the application of Moran's index on the spatial distribution of deterioration, this coefficient is positive and equal to 0.314. Representing the spatial distribution of the deterioration is cluster. Since Moran index can not identify Spatial diverse patterns, General G statistic analysis was covered the defect. General G statistic showed that neighborhoods with high deterioration together and have a high concentration of the cluster. About 6.29 percent of the area of deteriorate devoted to hot high-cluster and consists of five neighborhoods. Since the deterioration dependent on the local and spatial variables, Geographically weighted regression (GWR) was used to investigate the influencing factors on the deterioration. The results showed that the model with R^2 = 0.92 and R^2 Adjusted equal to 0.84 has acceptable accuracy in modeling the spatial relationships of effective factors on urban deterioration as well as Moran’s I of residuals GWR refers to insignificant autocorrelation. The results shows that impermeability, microlithic, the quality of infrastructure, dependency ratio, leasehold property and land prices variables have increasingly effect on deterioration. So these findings can scientific basis for policy in order to reduce deterioration and its effective.

Financial and credit centers, especially banks, are assumed as the most important economic activity in the urban space. The significant role of these centers in offering services to the citizens on one hand, and the competition between these centers on the other hand confirms the necessity of investigations about the optimum place for their site selection (Rahnamaee et al., 1391: 48). In such studies, the amount and the way that the space would effect is of importance. And, neglecting the effect of the space would lead to consequent errors in estimating, forecasting, and projecting (Soltani et al., 1389: 100). Multiplicity of effective variables in site selection in urban spaces has made the spatial decision makings complex, and modeling spatial relations necessary. Modeling these relations requires spatial methods due to the spatial nature of these factors.
In most studies about identifying the optimum place for installation sites of various activities and services, methods are used that are based on experts’ ideas. Also, multi-variable decision making techniques in geographical information system are widely used. While in these researches the spatial relations between the variables are not identified and modeled with respect to the current distribution pattern and the current situation are not used for further prediction.

The purpose of the current study is to provide a spatial climate-based model to measure the performance of apple tree via geographical weighted regression model. To this end, cognitive climatic factors were selected on 9-year spans (1996-2005) in line with statistical length of apple tree performance in the stations under study. Thereafter, these factors were entered into geographic information systems in the forms of positioning data layers. Spatial climate-based models were produced with the minimum variance of inflation factor by means of the application of climatic elements with the maximum spatial correlation as independent variables. The optimal model of performance was developed according to the statistical indexes of coefficient of determination, the lowest value of remains, and the lowest percentage of error. The output of the final model indicates that the most important factor in explaining the yield performance of apple tree is the average temperature of December whose role in the North and North West of our country is contrary to South and South East directions and it has a direct relationship with apple performance. Average minimum temperature in March has the second preference in the apple performance whose positioning role is negative in north, west and northeast of the country is direct and in the southern half of the country is opposite. Finally, the local coefficients of total sunshine hours was chosen as the third effective variable. The coefficient of determination (R2) of the model with maximum space explained.

House price which have very important effect on the Social and economic welfare of the city And the various factors have affect on it، is The most fundamental variable in housing sector. Therefore، this study analyzed the spatial distribution of housing prices in the city of Mashhad and its Affecting Factors have been explored using geographically weighted regression. The sample consists of 1000 houses (About 628 villas and 372 flats)، collected during 1389 from the real estate and Khorasan newspaper sites، and then digitizes based on Mashhad’s Map. In This description study which using ArcGIS software and geographically weighted regression، the house price is dependent variable and 1. Distance from City Centre، 2. Distances to healthcare facilities، 3. Distance to the transportation networks، 4. Distance to the city''s development area، 5. Region’s population، 6. Average household Income، 7. Percentage area of downtown and 8. percentage of slum area are independent variable.