Geographic Information System (GIS)
Abolfazl Ghanbari; Mostafa Mousapour; Habil Khorrami hossein hajloo; Hossein Anvari
Abstract
Extended AbstractIntroduction:The urban space is the most important human-made spatial structure on the planet earth. The history of urban development shows the path of human development, political system evolution and technological, technical and industrial developments. The physical development of ...
Read More
Extended AbstractIntroduction:The urban space is the most important human-made spatial structure on the planet earth. The history of urban development shows the path of human development, political system evolution and technological, technical and industrial developments. The physical development of urban areas is one of the main drivers of global changes that have important direct and indirect effects on environmental conditions and biodiversity. In the process of physical development of the city, due to the transformation of natural and semi-natural ecosystems into impermeable surfaces, it often causes irreversible environmental changes. One of the new approaches in urban planning is the use of remote sensing techniques and geographic information system. The emergence of remote sensing and machine learning techniques offers a new and promising opportunity for accurate and efficient monitoring and analysis of urban issues in order to achieve sustainable development. The process of processing satellite images can generally be divided into two approaches: pixel-based image analysis and object-based image analysis. The pixel-based analysis technique is performed at the level of each pixel of the image and uses only the spectral information available in each pixel. On the other hand, the object-based analysis approach is performed on a homogeneous group of pixels, taking into account the spatial characteristics of the pixels. One of the basic problems in urban remote sensing is the heterogeneity of the urban physical environment. The urban environment usually includes built structures such as buildings and urban transportation networks, several different types of vegetation such as agricultural areas, gardens, as well as barren areas and water bodies. Therefore, in the pixel-based processing approach, the existence of heterogeneity in the urban biophysical environment causes spectral mixing and also spectral similarities in the classification operation of satellite images in such a way that in a place where a pixel is If the surrounding environment is different, it causes Salt and Pepper Noise. Therefore, according to the problems in the pixel-based processing approach, the aim of this research is to compare the accuracy of machine learning algorithms based on object-based processing of satellite images in extracting the physical development area of Hamedan city using Sentinel 2 satellite image.Materials & Methods: The remote sensing data used in this research is a multi-spectral satellite image with a spatial resolution of 10 meters from the Sentinel 2 satellite, including bands 2 (blue), 3 (green), 4 (red) and 8 (near infrared) related to the date is the 23 of August 2023 in the city of Hamadan. The image of the Sentinel 2 satellite was downloaded from the website of the European Space Agency. In ENVI software, the pre-processing operation was performed on the satellite image. Then, in the eCognition software, the segmentation process was performed based on the appropriate scale, shape factor, and compression factor with the aim of producing image objects. After segmenting and converting the image into image objects, using machine learning classifiers based on object-oriented processing of satellite images including Bayes classification algorithms, k-nearest neighbor, support vector machine, decision tree and random trees, the classification process was carried out and maps of urban physical development area were produced. After the segmentation operation and the production of visual objects, three classes of built-up urban land, vegetation and barren land were defined, and some of the built objects in the segmentation stage were selected as training points and some were selected as ground Truth points.Results & DiscussionAfter downloading the satellite image from the website of the European Space Organization, in order to apply the radiometric correction of the image and also with the aim of matching the value of the gray levels of the image with the value of the real pixels of the terrestrial reflection, the gray levels are converted to radiance and then, using atmospheric correction, to coefficients. They became terrestrial reflections. In order to apply radiometric correction, Radiometric Calibration tool was used, and to apply atmospheric correction, FLAASH model was used in ENVI software. In order to classify the satellite image based on machine learning algorithms based on object-based processing, eCognition software was used. The satellite image of the study area, which was pre-processed and saved in TIFF format, was called in the environment of this software and saved as a project. In order to produce visual objects, segmentation operations were performed in different scales, shape factor and compression ratio to reach the most appropriate segmentation mode. In this step, the multiple resolution segmentation method was used to segment the image. The most appropriate segmentation included the scale of 100 and the shape factor of 0.6 and the compression factor of 0.4. Because in scales higher than 100, the construction of the visual object was not done correctly, so that several distinct complications were placed in one piece, and in scales less than 100, in some cases, one complication was placed in several pieces. In order to classify the generated image objects, machine learning algorithms were defined separately and after training each algorithm, the classification operation was performed. In this step, the classification was done based on the nearest neighbor method and by selecting the average and standard deviation parameters for each image band. After producing a map of the city physical development range through machine learning classifiers based on object-based processing of satellite images, the classification accuracy of each of the used algorithms was calculated. In order to calculate the accuracy of the above algorithms in eCognition software, using selected ground Truth control points, the overall accuracy and kappa coefficient were calculated for each of the algorithms.Conclusion:Based on the results of the research, it is possible to produce a map of Hamedan's urban physical development using machine learning algorithms based on object-based processing of satellite images with acceptable accuracy. Also, among all the algorithms used in this research, k-nearest neighbor with overall accuracy of 97% and kappa coefficient of 0.96 provided more accuracy.
Abolfazl Ghanbari; Sadra Karimzadeh; Sedighe Taraneh
Abstract
Extended AbstractIntroductionDespite higher standards of living in urban areas, rapid growth of urbanization has caused some problems such as development of dense and unplanned residential areas, environmental pollution, lack of access to services and amenities, increased gap between social classes and ...
Read More
Extended AbstractIntroductionDespite higher standards of living in urban areas, rapid growth of urbanization has caused some problems such as development of dense and unplanned residential areas, environmental pollution, lack of access to services and amenities, increased gap between social classes and etc. Manifested as severe differences between living standards in different parts of cities, these affect the quality of urban life. Quality of life is considered to be one of the most important dimensions of sustainable urban development. The desire to improve the quality of life in a particular space, for a particular individual or group is one of the main concerns of planners. Failure to identify factors affecting the quality of life in various human settlements will have unexpected and unfortunate consequences. With a decrease in citizens' life satisfaction, society will gradually lose its productive and capable labour force. The present study primarily seeks to find a way to objectively study and evaluate the quality of life in urban areas using remote sensing technology and GIS. Therefore, it investigates the quality of life in Zahedan and identifies possible factors improving life quality. Methods and MaterialThe present study applies a descriptive-analytical methodology. Statistical data were collected from census data of Iranian Statistics Center and maps were retrieved from Zahedan detailed plan-related service centers. Satellite images were also used. The present study applies four indicators to study the quality of life: economic, social, and environmental indicators along with access to service providing centers. Cronbach's alpha method was used in SPSS to determine the reliability of the questionnaire resulting in a coefficient of 0.723 for the previously mentioned indicators which shows high reliability of the instrument. The validity of the questionnaire was also investigated using experts' opinions. Collected data and factor analysis for economic and social variables were performed using SPSS. Criteria were weighted using Super Decision software and ArcGIS was used to combine and model the layers. Satellite images were retrieved from Google Earth Engine. Results and DiscussionIn order to investigate the socio-economic inequalities affecting quality of life, 16 parameters were extracted from the available census data and used to assess the socio-economic situation in the study area. Correlated parameters were combined using factor analysis to represent a single index. A specific name was then assigned to each factor. Indicators were normalized and aligned for the modeling stage. Fuzzy membership functions (Large, Small and Liner) were used to normalize the indicators in ArcGIS. Each index is then multiplied by the weight obtained from ANP method, and integrated using GAMMA fuzzy command. Spatial distribution of urban blocks in the central parts of the first district ranked higher in terms of economic and social indexes of life quality. Environmental indexes and access to service providing centers have a more desirable status in the second district. Parameters such as economic participation rate , housing status, air pollution and health centers had the largest impact on quality of life. Moran's spatial autocorrelation index shows a cluster pattern for quality of life in the study area. ConclusionFinal results show that access to service providing centers has the largest impact on quality of life. In general, the second district ranks higher than the first district in terms of quality of life. This city faces various economic and social limitations, while having access to many facilities: Recent droughts, universities and higher education institutions, mutual borders with neighboring countries and a large number of immigrants from Afghanistan. It is also facing hot and dry climate, a decrease in vegetation cover and an increase in temperature level. The freeway located in the western part of the study area, urban expansion toward the western parts, increased constructions and increased urban density due to proximity to university centers and finally heavy traffic have caused air pollution. Also, public service centers are not evenly distributed. These are some of the most important causes of low quality of life in the study area.
Geographic Information System (GIS)
Abolfazl Ghanbari; Vahid Isazadeh
Abstract
Extended AbstractIntroductionAir pollution is a major problemin large industrial cities and affects the life of urban citizens.Due to population growth,significant increase in the number of motor vehicles as well as the concentration and accumulation of industries, Tehran is in the grip of an air pollution ...
Read More
Extended AbstractIntroductionAir pollution is a major problemin large industrial cities and affects the life of urban citizens.Due to population growth,significant increase in the number of motor vehicles as well as the concentration and accumulation of industries, Tehran is in the grip of an air pollution crisis. Previous studies have indicated that once every three days, Tehran faces increased levels of pollutants and air pollution.Ozone is produced through photochemical reactions between hydrocarbons in carexhaust and nitrogen oxides in the atmosphere. Producedthrough reactions between atmospheric pollutants,this pollutant is not primarily released into the environment by a specific sourceand thus, it is called a secondary pollutant.Concentration of ground-level ozone has doubled over the last century.Exposure to this pollutant is very harmful for human health, especially those who exercise outdoors because it severely damages their lungs.Therefore, increased concentration of pollutants has become a major challenge for the management of metropolises such as Tehran. Having information about the spatial distribution of pollutants allows urban managers to take appropriate measures and reduce pollution related risksfor areas and people in danger.Due to excessive concentration of industries and factories inside the geographical boundaries of Tehran, along with its specific geographical condition, topography and climate, Tehran has become one of the seven most polluted cities of the world.The present study seeks to model the spatial and temporal changes of ozone and nitrogen oxidesin Tehran metropolis. Methods and MaterialsIn this cross-sectional descriptive study, spatial analysis of pollutants (ozone(O3) and nitrogen oxides)is performed based on data measured by Tehran air quality monitoring stations for the 2008, 2009, and 2018reference periods. For 2008 reference period, data were collected on a monthly basisfrom the website ofTehranair quality control company,while for 2008 and 2018, data were collected annually. Arc GIS 10.5 released by ESRI was usedfor spatial analysis, and Microsoft Excel 2013 was usedto drawdiagrams and perform other analysis.Inverse distance weighting (IDW) model was used for spatial analysis of ozone and nitrogen oxidesin Tehran metropolitan area inthe three reference periods. Finally, the reference periods were compared and the most polluted one was zoned using the IDW model. In the second method, Google Earth Engine was used to model the spatial distribution of ozone and nitrogen oxides. In this method, Sentinel-5p NRTI O3: Near Real Time Ozone product was used to model ozone and nitrogen oxideson an annual basis (11/01/2018 and 28/03/2020).This is the date in which sentinel has started monitoring ozone and nitrogen pollutants. As the most important product available for measuring the average rate of change,column of ozone and nitrogen oxides’ changes in the atmosphere (O3_Column_number_density) was used in this study. Annual average concentration of ozone and nitrogen pollutants in Tehran was compared with the Sentinel-5 product in Google Earth Engine. Results & DiscussionIn 2018, average annual concentration of ozone and nitrogen oxides in studied stations equaled 12.7 ppb. The accuracy of modeling was also calculated using the coefficient of determination(R2) or coefficient of detection (CD). The average annual concentration of ozone and nitrogen oxides in 2008 was also measured for all air quality control stations to determine their correlation.All independent variables used in this model had an acceptable level of significance (P.> 0.001).In other words, all parameters improved the performance of the model in estimating the concentration of ozone and nitrogen oxidespollutants. The model was developed and R2 rate for 2008 monthly average equaled 0.9188%.The coefficient of determination (R2)for ozone and nitrogen oxides’ concentration in 2009 equaled 0.9134%, but the annual average of 2018showed a much lower R2which equaled 0.476%.It should be noted that not all stations have been evaluated in this study, because the concentrations of ozone and nitrogen oxidesin some air quality monitoring stations equaled zero. Thus, only stations showing a greater than zero value have been used in this study. ConclusionAs previously mentioned, various models have been proposed for modeling the concentration of ozone and nitrogen oxides, each showing a different result. In the present study, the inverse distance weighting (IDW) model was used for three reference periods (2008, 2009 and 2018), and the concentrations of ozone and nitrogen oxides in the atmosphere were also modeled using the variables related to air quality monitoring stations.Ozone concentration modeled by inverse distance weighting method was compared with the average annual change of ozone concentration derived from Sentinel-5 product in Google Earth Engine. Results obtained from the concentration of ozone and nitrogen oxides in the three reference periods were investigated using thecoefficient of detection.The resulting coefficient of determination for ozone concentration in 2008 and 2009 equaled 0.9188% and 0.9134%, respectively. The lowest coefficient ofdetermination for ozone and nitrogen oxidesconcentration was obtained for 2018 which equaled 0.476%. Regarding the spatial distribution of ozone and nitrogen oxides in 2008, the highest concentrations were observed inMasoudiyeh, Punak, Rose Park and Aqdasiyeh stations, and the highest concentration of nitrogen oxides was observed in District4, Crisis Management Headquarterand Sadr Expressway(District 3). In 2009,the station in Rose Park (District 22) showed the highest concentration of ozone and nitrogen oxides.In 2018, IDW modelling and spatial distribution of ozone and nitrogen oxidesshowed a different result. In this reference period, the station in district 4 received the highest annual concentration of ozone and nitrogen oxides, and north eastern areas ofTehran was regarded as the most polluted areas based on the concentration of these pollutants. But stations in16th, 19th and 20th districts and Masoudieh station (15th district) had the lowest annual concentration of ozone and nitrogen oxides. In general, it can be said that spatial modeling with Sentinel-5 product has been able to model the concentration of ozone and nitrogen oxides inall stationsof Tehran on a pixel by pixel basis.