Classification Of Urban Areas Research Articles

Spatial classification of urban land by speculative land value, and MSI satellite imagery using K-MEANS, in Huancayo, Perú

The city of Huancayo, like other intermediate cities in Latin America, faces problems of poorly planned land-use changes and a rapid dynamic of the urban land market. The scarce and outdated information on the urban territory impedes the adequate classification of urban areas, limiting the form of its intervention. The purpose of this research was the adoption of unassisted and mixed methods for the spatial classification of urban areas, considering the speculative land value, the proportion of urbanized land, and other geospatial variables. Among the data collection media, Multi-Spectral Imagery (MSI) from the Sentinel-2 satellite, the primary road system, and a sample of direct observation points, were used. The processed data were incorporated into georeferenced maps, to which urban limits and official slopes were added. During data processing, the K-Means algorithm was used, together with other machine learning and assisted judgment methods. As a result, an objective classification of urban areas was obtained, which differs from the existing planning.

Classification of Urban Regeneration Activation Areas by the Levels of the Population Extinction Risk : A Case Study of Gyeongsangbuk-do

Classification of Urban Regeneration Activation Areas by the Levels of the Population Extinction Risk : A Case Study of Gyeongsangbuk-do

An integrated machine learning model for automatic road crack detection and classification in urban areas

ABSTRACT Cracks in the asphalt are the first and most common deterioration type of roads that generally threaten the safety of roads and highways. In recent years, automated inspection has been considered due to the high cost and error of manual methods. For this purpose, different machine learning techniques have been developed. In this study, an integrated model is proposed, which involves the following steps: image segmentation, noise reduction, feature extraction, and crack classification. In the first two steps, heuristic algorithms are proposed, and then in the third step, the Hough transform technique and the heuristic equations are used to extract the main features of cracks. In the fourth step, six different classification models, including neural network, SVM, decision tree, KNN, Bagged Trees, and a proposed hybrid model, are implemented. Experimental results show that the proposed hybrid model can achieve more accurate results with 93.86% overall accuracy.

The Modified Normalized Urban Area Composite Index: A Satelliate-Derived High-Resolution Index for Extracting Urban Areas

The accurate and efficient extraction of urban areas is of great significance for better understanding of urban sprawl, built environment, economic activities, and population distribution. Night-Time Light (NTL) data have been widely used to extract urban areas. However, most of the existing NTL indexes are incapable of identifying non-luminous built-up areas. The high-resolution NTL imagery derived from the Luojia 1-01 satellite, with low saturation and the blooming effect, can be used to map urban areas at a finer scale. A new urban spectral index, named the Modified Normalized Urban Areas Composite Index (MNUACI), improved upon the existing Normalized Urban Areas Composite Index (NUACI), was proposed in this study, which integrated the Human Settlement Index (HSI) generated from Luojia 1-01 NTL data, the Normalized Difference Vegetation Index (NDVI) from Landsat 8 imagery, and the Modified Normalized Difference Water Index (MNDWI). Our results indicated that MNUACI improved the spatial variability and differentiation of urban components by eliminating the NTL blooming effect and increasing the variation of the nighttime luminosity. Compared to urban area classification from Landsat 8 data, the MNUACI yielded better accuracy than NTL, NUACI, HSI, and the EVI-Adjusted NTL Index (EANTLI) alone. Furthermore, the quadratic polynomial regression analysis showed the model based on MNUACI had the best R2 and Root-Mean Square Error (RMSE) compared with NTL, NUACI, HSI, and EANTLI in terms of estimation of impervious surface area. It is concluded that MNUACI could improve the identification of urban areas and non-luminous built-up areas with better accuracy.

Optimal segmentation parameters prediction using a orthogonal decomposition approach for geographical object based classification of urban areas

Good image segmentation produces objects that are internally homogeneous and distinct from their neighbors. Several approaches are used to assess the quality of segmentation parameters including visual observation of multiple segmentation results and techniques, which calculate measures of intra segment homogeneity and inter segment heterogeneity. Some of these techniques have been reported without considering under and over segmentation; occurrences and others exhibit some mathematical formulation instabilities when dealing with very heterogeneous areas. Moreover, the majority of segmentation assessment techniques focus on the evaluation of the scale parameter and give little attention to the influence of other parameters, such as compactness on the performance of the scale parameter. To the best of our knowledge, no existing approach can predict the optimal compactness thresholds that would enhance the performance of the scale parameters, or predict which scale parameter will perform best under certain compactness constraints. This paper proposes three spatial autocorrelation models, which identify the optimal parameters for single scale and multilevel segmentations of urban environments. Tested using a GeoEye satellite image of the City of Cape Town (South Africa), results reflect that the best combination of parameters to optimally segment the area and those that would poorly perform were successfully identified.

Quality Assessment of Heterogeneous Training Data Sets for Classification of Urban Area with Landsat Imagery

Quality assessment of training samples collected from heterogeneous sources has received little attention in the existing literature. Inspired by Euclidean spectral distance metrics, this article derives three quality measures for modeling uncertainty in spectral information of open-source heterogeneous training samples for classification with Landsat imagery. We prepared eight test case data sets from volunteered geographic information and open government data sources to assess the proposed measures. The data sets have significant variations in quality, quantity, and data type. A correlation analysis verifies that the proposed measures can successfully rank the quality of heterogeneous training data sets prior to the image classification task. In this era of big data, pre-classification quality assessment measures empower research scientists to select suitable data sets for classification tasks from available open data sources. Research findings prove the versatility of the Euclidean spectral distance function to develop quality metrics for assessing open-source training data sets with varying characteristics for urban area classification.

Relative Total Variation Structure Analysis-Based Fusion Method for Hyperspectral and LiDAR Data Classification

The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has a wide range of applications. This paper proposes a novel feature fusion method for urban area classification, namely the relative total variation structure analysis (RTVSA), to combine various features derived from HSI and LiDAR data. In the feature extraction stage, a variety of high-performance methods including the extended multi-attribute profile, Gabor filter, and local binary pattern are used to extract the features of the input data. The relative total variation is then applied to remove useless texture information of the processed data. Finally, nonparametric weighted feature extraction is adopted to reduce the dimensions. Random forest and convolutional neural networks are utilized to evaluate the fusion images. Experiments conducted on two urban Houston University datasets (including Houston 2012 and the training portion of Houston 2017) demonstrate that the proposed method can extract the structural correlation from heterogeneous data, withstand a noise well, and improve the land cover classification accuracy.

Classification of Rural Areas in Serbia: Framework and Implications for Spatial Planning

The classification of rural and urban areas presents an important topic both in scientific research and in the practice of spatial planning, regional policy making, and territorial governance. Taking into account the multidimensionality of these areas, this paper aims to provide a classification framework design for rural areas in Serbia. After selecting the relevant indicators, which were included to reflect the main demographic, economic, and physio-geographical characteristics of the Serbian rural areas, multivariate analysis (principal component method and factor analysis) was used to determine the main factors in the delimitation and classification of rural and urban areas. The last step of the conducted methodology used cluster analysis (CA) that identified six types of areas with similar characteristics. The results of this study and applied methodology can improve the existing rural–urban classifications and help planners and policy makers in the adaptation of strategic development documents.

Classification of Urban Functional Areas From Remote Sensing Images and Time-Series User Behavior Data

Urbanization is accelerating at a rapid rate, which has introduced many challenges, especially in the field of urban planning. Under the backdrop of global urbanization, some cities are particularly vulnerable to climate change and natural disasters that are influenced by unplanned urban expansion. Rational planning of urban functional areas needs to be strengthened to improve the scientific approach of urban planning and urbanization. In this study, the classification of urban functional areas based on dual-modal data (i.e., remote sensing image and user behavior data) was implemented using machine learning (ML) algorithms. After the set test, the classification accuracy of urban functional areas reached 82.45%. Through analysis, it could be concluded that the use of data of two modalities achieved a higher classification accuracy than that achieved by using data of a single modality. The data of the two modalities complement each other, and the use of ML algorithms to train such data can yield good results.

Measurement of Polycentric County-Level Areas in a Rapid Urbanization Region from a Public Service Perspective

Despite various studies regarding polycentric development at metropolis or even larger spatial scales, there is little systematic analysis regarding the rapid urbanization area at the county-level scale. Therefore, this study explored polycentric development in 52 county-level administrative units in Zhejiang Province, China, from a public service perspective. Based on point-of-interest data, our analysis detected the intra-county urban centers and measured their polycentric characteristics. According to the number, scale, and equilibrium value of intra-county polycentricity, the 52 county-level units were classified into three types using a two-step cluster algorithm method. The empirical results suggest that polycentric characteristics vary in the rapid urbanization area, and the spatial distribution of typological units is characterized by agglomeration. Topographical condition, fixed assets investment, public transportation, and residential consumption ability are highly associated with the classification of polycentric urban areas. The conclusion of this study would help local governments initiate better urban development policies and provide potential research directions for further studies about the relationship of inter-county urban centers.

Hyperspectral Image Classification Based on Multiscale Spectral–Spatial Deformable Network

Image classification plays a fundamental role in hyperspectral image (HSI) analysis. Since the mixed pixels of the urban areas are generally more complex than other areas, the following two problems remain to be considered while dealing with urban HSI classification: 1) due to the fact that the spectral feature of different mixed pixels varies greatly in the same class, HSI classification of urban area is susceptible to the representativeness of the training samples and 2) since the urban area is densely packed with objects of different size, the comprehensive use of the spatial and spectral features to classify the objects is a difficult problem. To tackle these problems, HSI classification based on multiscale spectral-spatial deformable network (S^2-DNet) is proposed. First, a k-means clustering method is adopted to cluster spectrum of each class, and representative samples are selected from the spectrum after clustering to reduce the impact of intraclass variation. Second, a spectral-spatial joint network is designed to extract the low-level features, including spectral features and spatial features. Third, the deformable network is introduced to extract high-level features of the object. Experimental results demonstrated that the proposed method outperformed the state-of-the-art methods on two widely used HSI data sets.

CLASSIFICATION AND CHARACTERISTIC OF SOILS IN URBAN AREAS (ON THE EXAMPLE OF ODESSA CITY)

The purpose of the research – 1) establishment of classification and diagnostic characteristics of soils under different functional using of the city territory; 2) parameterization of the structure, composition and properties of anthropogenically transformed and anthropogenically created soils; 3) development of a classification scheme, taking into account its use in cadastral and economic grouping. General scientific (systematic, analysis, synthesis, generalization, statistics) and traditional (soil-genetic, profile-morphological, laboratory-analytical and cartographic) research methods were used to study the genetic characteristics of soils of Odessa and their classification. The ecological-profile-genetic classification of soils of urban areas, which combines profile-genetic and factor-ecological approaches, is proposed. Within the city there are natural, anthropogenically transformed and anthropogenically created soils. Soils during cadastral and economic grouping are united into two groups of transformed and technological soils of human settlements and other territories with anthropogenically transformed soil cover, are distinguished. According to cadastral and economic grouping, within Odessa the area of transformed soils is 11,915.6 ha, technological soils is 1922.5 ha. The proposed scheme of soil classification of urban areas includes 2 supertype levels, 3 types and 13 subtypes of soils, which are divided according to their genetic profile and combined according to the characteristics of natural and anthropogenic factors of soil formation. For urban cadastre, organization, planning and implementation of land management, economic activity, a scheme of supplementing the list of agricultural soils of Ukraine with cadastral and economic grouping of soils of urban areas was proposed. The grouping of soils includes two associations: 1) transformed and 2) technological (artificially created) soils - a total of 14 cadastral and economic groups

Exploring indigenous ethnic inequities in first episode psychosis in New Zealand – A national cohort study

IntroductionFirst episode psychosis (FEP) disproportionately affects rangatahi (young) Māori, the Indigenous people of New Zealand, but little is known about factors contributing to this inequity. This study describes a cohort of rangatahi Māori and young non-Māori with FEP, and explores ethnic differences in incidence rates, and the contribution of deprivation, urbanicity and substance use. MethodsMāori and young non-Māori, aged 13–25 at the time of the first recorded psychosis-related diagnoses, were identified from within Statistics NZ's Integrated Data Infrastructure (IDI), between 2009 and 2012. To estimate age-standardised FEP incidence rates, the population-at-risk was estimated using IDI-based usual resident population estimates for 2009–2012, stratified by ethnicity and single year of age. Poisson regression models were used to estimate ethnic differences in FEP incidence adjusted for age, gender, deprivation, and urban-rural area classification. ResultsA total of 2412 young people with FEP (40% Māori, 60% non-Māori) were identified. Māori were younger, and more likely to live in deprived and rural communities and be diagnosed with schizophrenia. Substance induced psychosis was uncommon. The unadjusted age-standardised FEP incidence rate ratio was 2.48 (95% CI: 2.29–2.69) for rangatahi Māori compared with young non-Māori. While adjusting for age, sex, deprivation and urban rural area classification reduced ethnic differences in incidence, rangatahi Māori were still more than twice as likely to have been diagnosed with FEP compared to young non-Māori. ConclusionsThis study confirms previous findings of elevated rates of psychosis among rangatahi Māori. The difference in rates between Māori and non-Māori were attenuated but remained after adjustment for deprivation and urbanicity.

INTEGRATION OF MULTITEMPORAL SENTINEL-1 AND SENTINEL-2 IMAGERY FOR LAND-COVER CLASSIFICATION USING MACHINE LEARNING METHODS

Abstract. Using space-borne remote sensing data is widely used for land-cover classification (LCC) due to its ability to provide a big amount of data with a regular temporal revisit time. In recent years, optical and synthetic aperture radar (SAR) imagery have become available for free, and their integration in time series have improved LCC. This research evaluates the classification accuracy using multitemporal (MT) Sentinel-1 (S1) and Sentinel-2 (S2) imagery. Pixel-based LCC is made for S1 and S2 imagery, and for a combination of both datasets with Random Forest (RF) and Extreme Gradient Boosting (XGBoost; XGB). The extent of the study area, is located in the south-east of France, in Lyon. Regardless of LCC using single-date or MT data, the highest classification results were achieved with integrated S1 and S2 imagery and XGB method, whereas overall accuracy (OA) and Kappa coefficient (Kappa) increased from 85.51% to 91.09%, and from 0.81 to 0.88, respectively. Furthermore, the integration of MT imagery significantly improved the classification of urban areas and reduced misclassification between forest and low vegetation. In this paper, in terms of the pixel-based classification, XGB produced slightly better results than RF, and outperformed it in terms of computational time. This research improved LCC with integration of radar and optical MT imagery, which can be useful for areas hampered by a frequent cloud cover. Future work should use the aforementioned data for specific applications in remote sensing, as well as evaluate the classification performance with different approaches, such as neural networks or deep learning.

Classification of Urban Area Using Multispectral Indices for Urban Planning

An accelerating trend of global urbanization accompanying population growth makes frequently updated land use and land cover (LULC) maps critical. LULC maps have been widely created through the classification of remotely sensed imagery. Maps of urban areas have been both dichotomous (urban or non-urban) and entailing of discrete urban types. This study incorporated multispectral built-up indices, designed to enhance satellite imagery, for introducing new urban classification schemes. The indices examined are the new built-up index (NBI), the built-up area extraction index (BAEI), and the normalized difference concrete condition index (NDCCI). Landsat Level-2 data covering the city of Miami, FL, USA was leveraged with geographic data from the Florida Geospatial Data Library and Florida Department of Environmental Protection to develop and validate new methods of supervised and unsupervised classification of urban area. NBI was used to extract discrete urban features through object-oriented image analysis. BAEI was found to possess properties for visualizing and tracking urban development as a low-high gradient. NDCCI was composited with NBI and BAEI as the basis for a robust urban intensity classification scheme superior to that of the United States Geological Survey National Land Cover Database 2016. BAEI, implemented as a shadow index, was incorporated in a novel infill geosimulation of high-rise construction. The findings suggest that the proposed classification schemes are advantageous to the process of creating more detailed cartography in response to the increasing global demand.

Satellite image based flood classification in urban areas using B-convolutional networks

Spatial features with spectral properties enhance the quality of satellite image while mapping complex land cover. These features are integrated with the proposed classification approach for improving classification results. The ultimate objective of this investigation is to provide high-level features to the convolutional neural network (CNN) for mapping flooded regions (before and after) using remote sensing data. Here, boundary-based segmentation is done to recognize the dimensions and scales of objects. Modeling a fully trained Convolutional network is feasible for training a huge amount of data in remote sensing studies. Fine-tuned CNN is utilized with slight modification for attaining classified Landsat images. Classification outcomes and confusion matrix are manipulated using B-CNN are compared with classifiers like SVM, random forest (RF) to compute B-CNN efficiency.

Urban land cover mapping under the Local Climate Zone scheme using Sentinel-2 and PALSAR-2 data

The spatial and spectral heterogeneity of urban areas makes land cover classification a challenging process. In this study, we highlight the potential of combined multi-spectral Sentinel-2 and fully polarimetric PALSAR-2 data for land cover classification in dense urban areas, based on the Local Climate Zone (LCZ) scheme. We classified differently combined spectral and back-scattering characteristics using the subspace method in comparison with the Support Vector Machine (SVM) and Maximum Likelihood Classifier (MLC) methods. Results show that, (i) the overall accuracy (OA) was 65.9% for the Sentinel-2 data, (ii) higher OA (71.9%) was achieved by adding four intensity images of PALSAR-2 to Sentinel-2, (iii) the inclusion of decomposed components increased OA to 72.8%, and (iv) the highest OA (73.3%) was achieved using all features. These results suggest that the inclusion of different backscattering characteristics disproportionately improved classification accuracy from using multi-spectral data alone. The results of comparison between different methods show that the subspace method performed better than SVM and MLC, particularly when high-dimensional data were used. The subspace method classified particularly well for some specific LCZ classes which are easily mixed between each other. It provides a promising option for LCZ mapping.

Assessing Machine Learning Based Supervised Classifiers For Built-Up Impervious Surface Area Extraction From Sentinel-2 Images

Urban development concept requires a way forward towards smarter and easier urban development. But due to unintended urbanization, which contributes to increased impervious surface areas with several environmental issues. There was a requirement to assess and map the urban built-up impervious areas for solving various socio-environmental issues. This work attempts to evaluate and implement machine learning (ML) based supervised classifiers to semi-automate the process for extraction, quantification and mapping of urban built-up impervious areas. The work emphasised on the usage of freely available open-source high-resolution satellite datasets acquired from Sentinel-2 mission. Three different machine learning-based supervised classification techniques were evaluated for a better understanding of feature extraction methods along with suitable classifier for classification of urban impervious areas. It is a well-known phenomenon that an increase in the impervious surface contributes to declining of green cover. Also, a zonal analysis of extracted built-up impervious surfaces was conducted to understand the spatial configuration of the pilot study area. This zonal assessment of urban built-up impervious surfaces can be used as a worthy tool for better sustainable smart cities development. These can serve as a valuable resource for restoring the required urban green cover for better sustainable urban development.

Methodology of the habitat classification of anthropogenic urban areas in Budapest (Hungary)

The vast majority of floristical and coenological studies focus on the natural vegetation and its remnants in urban environments; however, there is an increasing interest in the systematic exploration of built environments. This survey of the inhabited areas of Budapest launched in 2018 applied a new and detailed methodology. The territorial units of the survey were street sections, where the presence of vascular plants was recorded in ecologically different habitats separately. We laid down the foundations to establish new habitat categories for the habitat classification and mapping of urban ecosystems using a different approach than the Hungarian habitat classification system (ÁNÉR). The method enables us to study the flora of urban ecosystems in detail. We established 18 urban habitat categories, surveyed more than 27,000 survey units and registered 647 spontaneously growing plant species in Budapest. Our survey evinced the spontaneous occurrence of 193 alien species in Budapest, 81 of them are data deficient, while 10 of them are new introductions in Hungary. 53.9% of the aliens are cultivated frequently in Hungary.

Need for an Integrated Deprived Area “Slum” Mapping System (IDEAMAPS) in Low- and Middle-Income Countries (LMICs)

Ninety percent of the people added to the planet over the next 30 years will live in African and Asian cities, and a large portion of these populations will reside in deprived neighborhoods defined by slum conditions, informal settlement, or inadequate housing. The four current approaches to neighborhood deprivation mapping are largely siloed, and each fall short of producing accurate, timely, and comparable maps that reflect local contexts. The first approach, classifying “slum households” in census and survey data, reflects household-level rather than neighborhood-level deprivation. The second approach, field-based mapping, can produce the most accurate and context-relevant maps for a given neighborhood, however it requires substantial resources, preventing up-scaling. The third and fourth approaches, human (visual) interpretation and machine classification of air or spaceborne imagery, both overemphasize informal settlements, and fail to represent key social characteristics of deprived areas such as lack of tenure, exposure to pollution, and lack of public services. We summarize common areas of understanding, and present a set of requirements and a framework to produce routine, accurate maps of deprived urban areas that can be used by local-to-international stakeholders for advocacy, planning, and decision-making across Low- and Middle-Income Countries (LMICs). We suggest that machine learning models be extended to incorporate social area-level covariates and regular contributions of up-to-date and context-relevant field-based classification of deprived urban areas.