Identification of Urban Functional Areas and Their Mixing Degree Using Point of Interest Analyses

Seasonal urban surface thermal environment analysis based on local climate zones: A case study of Chongqing

The rapid urbanization has exacerbated the heat island effect, impacting city development and residents' health. This study, using Local Climate Zones (LCZ) as a framework, connects spatial structure, resource allocation, and thermal environment research. It investigates the spatiotemporal heterogeneity of the surface thermal environment and its driving forces, crucial for mitigating heat issues. Utilizing various data sources like remote sensing images, road network data, land use data, high-resolution street view data, and building data, the research employs the random forest algorithm to map LCZs in Chongqing's central urban area. Through mathematical statistics, equi-sector analysis, ring-layer analysis, and Pearson correlation analysis, the study examines seasonal variations in spatiotemporal heterogeneity and driving mechanisms of the surface thermal environment. Key findings include: (1) The central urban area of Chongqing is dominated by open-building and vegetation-type LCZs, with building-type LCZs showing a "clustered" distribution, while natural-type LCZs are mainly found in the suburbs with ribbon and block distribution in the urban area. (2) The surface thermal environment in the study area correlates strongly with surface cover and exhibits significant high temperature effects in summer. (3) The surface thermal conditions vary significantly among different LCZs and exhibit seasonal patterns, natural-type LCZs generally have lower temperatures compared to building-type LCZs.(4) The surface thermal characteristics within the same category of LCZs in different locations display distinct differences and seasonal variations. (5) The internal temperatures of LCZs are significantly linked to four surface attributes, each displaying seasonal fluctuations. Greenness, height, and wetness are inversely related to the surface thermal conditions, while brightness shows a positive correlation. Both seasonal variations and LCZ types differences have a noticeable influence on their respective driving mechanisms to some degree.

Exploring the predictive ability of the CA-Markov model for urban functional area in Nanjing old city

With advancements in sustainable urban development, research on urban functional areas has garnered significant attention. In recent years, Point-of-Interest, with their large volume of information and ease of acquisition, have been widely applied in research on urban functional domains. However, scholars currently focus on the identification of urban functional areas, usually relying on data from a single period, whereas research on the prediction of functional areas has not yet been well validated. Therefore, in this study, we propose a new method based on several years of POI data to predict urban functional areas. Taking Nanjing City, Jiangsu Province, as an example, we first identified the functional area distribution of the old city of Nanjing over several years using POI data and then designed multiple sets of experiments to explore the CA-Markov model's ability to predict functional areas from various aspects, including model overall accuracy, robustness, and comparison analysis between predictions and actual situations. The results show that (1) for mixed or single functional areas, the model's predictions over several years tend to be stable, and the accuracy of the predictions over many years indicates the robustness of the model in predicting urban functional areas. (2) For mixed functional areas in cities, model predictions largely rely on the distribution of the base years used for prediction, leading to inaccurate results; thus, it is still not applicable for simulating and predicting mixed functional areas. (3) For single functional areas in cities or primary functions within an area, the model's predicted degree of change was close to the actual degree of change, making the results referable.

Spatial correlation between producer services agglomeration and carbon emissions in the Yangtze River Economic Belt based on point-of-interest

Agglomeration of the industry significantly impacts economic performance and environmental sustainability. In line with its strategic context of striving to achieve carbon reduction targets, China is making efforts to optimize the producer services landscape to reduce carbon emissions. Understanding the spatial correlation between industrial agglomeration and carbon emissions is particularly crucial against this background. Based on POI and remote sensing data of China's Yangtze River Economic Belt (YREB), the paper adopts the mean nearest neighbor analysis, kernel density analysis, and standard deviation ellipse to portray the agglomeration of producer services. Then uses Moran's I to present the spatial distribution characteristics of carbon emissions. Accordingly, the spatial heterogeneity of producer services agglomeration and carbon emissions is showed using the Geographic detector so as to provide strong support for industrial structure optimization and sustainable development. Here are some of the conclusions drawn from the study: (1) Producer services are a significant state of agglomeration in the provincial capitals and some central cities, with similar agglomeration patterns. (2) Carbon emissions exhibits significant spatial aggregation characteristics, with the spatial distribution pattern of "High west-Low east". (3) Wholesale and retail services industry is the primary risk factor that causes spatial differentiation of carbon emission intensity, "leasing and business services industry-wholesale and retail services industry" is the key interaction factor of the spatial differentiation. (4) Carbon emissions shows a downward trend followed by an upward trend as producer services agglomeration increases.

Identification and prediction of mixed-use functional areas supported by POI data in Jinan City of China

The urban development of China is changing from incremental expansion to stock renewal mode. The study of urban functional areas has become one of the important fundamental works in current urban renewal and high-quality urban development. In recent years, big spatiotemporal data has been well applied in the urban function field. However, the study of spatial-temporal evolution characteristics and forecasting optimization for mixed-use urban functional areas has not been examined well. Thus, in this study, we proposed a new approach that applies a revised information entropy method to analyze the degrees of mixing for urban functional areas. We applied our approach in Jinan City, Shandong Province as the study area. We used Point-of-Interest, OpenStreetMap and other datasets to identify the mixed-use urban functional areas in Jinan. Then, the CA-Markov model simulated the urban layout in 2025. The results showed that: (1) the combination of road network and kernel density method has the highest accuracy of identifying urban functional areas. (2)The mixing degree model is constructed by using the improved information entropy, which makes up for the shortcoming of identifying the mixed functional areas simply by the frequency ratio of POI data. (3) The "residence and business" functional area has the highest proportion in the central area of Jinan from 2015 to 2020, and the total area of mixed-use unban functional areas continuously increased during this period. (4) The total area of the central area in Jinan has significantly increased in 2025. The optimization of urban functions should expand mixed-use functional areas and increase the proportion of infrastructure. Also, Jinan should improve the efficiency of space development.

Sub-Block Urban Function Recognition with the Integration of Multi-Source Data

The recognition of urban functional areas (UFAs) is of great significance for the understanding of urban structures and urban planning. Due to the limitation of data sources, early research was characterized by problems such as singular data, incomplete results, and inadequate consideration of the socioeconomic environment. The development of multi-source big data brings new opportunities for dynamic recognition of UFAs. In this study, a sub-block function recognition framework that integrates multi-feature information from building footprints, point-of-interest (POI) data, and Landsat images is proposed to classify UFAs at the sub-block level using a random forest model. The recognition accuracies of single- and mixed-function areas in the core urban area of Guangzhou, China, obtained by this framework are found to be significantly higher than those of other methods. The overall accuracy (OA) of single-function areas is 82%, which is 8-36% higher than that of other models. The research conclusions show that the introduction of the three-dimensional (3D) features of buildings and finer land cover features can improve the recognition accuracy of UFAs. The proposed method that uses open access data and achieves comprehensive results provides a more practical solution for the recognition of UFAs.