Urban housing development has always been a key area of focus in urban studies. Accurate understanding of housing policy texts is of great significance for the sustainable development of urban housing. Different from traditional text analysis methods, we have proposed a machine learning (ML) framework driven by a large language models (LLMs) to quickly and accurately extract policy text themes and classify them. We used Mengzi-BERT-Base (MBB) for semantic encoding of policy documents, used GPT-4o to extract policy keywords and grasp the macro logic, and finally integrated the features of the two using a random forest model to output classification results. The results show that this framework divides housing policy texts into 4 core themes, with an overall accuracy rate of 70.25%, and the accuracy rate of individual themes is 75.56%, indicating that this framework has certain application value in urban policy text analysis.

Against the backdrop of the transition of new-type urbanization towards high-quality development, the triple contradictions of population agglomeration, land constraints, and housing supply-demand imbalance have become increasingly prominent. The conventional binary framework of human–land relations can no longer meet the requirements of coordinated development within human settlement systems, creating an urgent need to examine the multi-system interactions among population, land, and housing in order to resolve spatial mismatch. Taking Guangzhou as a case study, this research integrates 2020 population census data, land-use data from the European Space Agency (ESA), housing-price data from the Anjuke platform, and multi-source data on related influencing factors, and conducts a systematic empirical analysis by combining coupling coordination analysis, a relative development model, and the geographical detector. The findings reveal that the coupling coordination level of population, land and housing in Guangzhou exhibits a concentric, ring-shaped distribution pattern with central agglomeration and peripheral decline. The relative development among the three systems can be classified into matching types including the core-differentiated type, the peripheral-imbalanced type, and the surrounding-equilibrium type. With respect to influencing factors, all pairwise interactions are of the bi-factor enhancement type, and the driving mechanism displays a three-stage dynamic evolution. This study enriches research on human–land relations, provides precise guidance for optimizing spatial allocation and alleviating housing mismatch conflicts in Guangzhou, and offers transferable practical experience for comparable cities in China seeking to advance the high-quality development of new-type urbanization.

The automated classification of policy texts holds significant importance for enhancing the efficiency of public administration. This study proposes a hybrid architecture that integrates GPT-4o's macro-semantic comprehension with the mi-cro-semantic encoding of the BERT model, constructing two combined models: “GPT-4o + Mengzi-BERT-Base + Random Forest (Model A)” and “GPT-4o + Chinese-RoBERTa-wwm-extlarge + Random Forest (Model B).” Experimental results on housing policy texts from Guangzhou spanning 1989 to 2025 demonstrate that: (1) the Model B exhibits superior overall performance $\quad(\text{OA}=72.78 \%, \quad$ Kappa $=0.6285)$, particularly achieving an accuracy rate of 87.23 % in the themes of housing finance and provident fund management; (2) the Model A shows greater advantages in specialized administrative scenarios such as housing system reform and land supply; (3) both models perform similarly on semantically clear themes but face recognition challenges in cross-semantic scenarios. This study validates the effectiveness of the hybrid architecture in policy text analysis and provides practical guidance for model selection across different policy contexts.

Urban expansion frequently concentrates high-level public services in cores, exacerbating urban–rural inequities, but little is known about when and how public transit mitigates such effects. Drawing on a 42-year longitudinal study (1980–2022) in Ningbo, China, we developed a conceptual framework to evaluate the phased moderating effects of public transit. Using the bus system as a primary proxy, we examined its capacity to bridge urban–rural healthcare accessibility gaps induced by rapid urban expansion. Despite an 11-fold increase in urban area and intensified healthcare centralization, the urban–rural accessibility gap followed a non-linear trajectory of divergence, convergence, and near-equilibrium, decreasing by about 113 min (95% CI: 104.344–120.782). Generalized additive models (GAMs) reveal that public transit effects are strongly phase-dependent: (1) inequality amplification, where early transit networks reinforced core-oriented centralization; (2) passive convergence, where rapid outward extensions yielded partial and unstable gap reductions; and (3) active moderation, where mature network integration and coordinated facility siting achieved durable spatial equity, effectively decoupling accessibility from the negative frictions of urban expansion. These findings show that public transit is not inherently equalizing; its equity effects depend on network maturity and cross-sector coordination. This study provides rare micro-level evidence for coordinated urban–rural infrastructure planning in rapidly urbanizing Global South cities.

This study leverages multi-source remote sensing data—Nighttime Light (NTL) imagery and POI (Point of Interest) datasets—to quantify the spatiotemporal interaction between urban spatial restructuring and logistics industry evolution in Zhengzhou, China. Using calibrated NPP/VIIRS NTL data (2012–2022) and fine-grained POI data, we (1) identified urban functional spaces through kernel density-based spatial grids weighted by public awareness parameters; (2) extracted built-up areas via the dynamic adaptive threshold segmentation of NTL gradients; (3) analyzed logistics agglomeration dynamics using emerging spatiotemporal hotspot analysis (ESTH) and space–time cube models. The results show that Zhengzhou’s urban form transitioned from a monocentric to a polycentric structure, with NTL trajectories revealing logistics hotspots expanding along air–rail multimodal corridors. POI-derived functional spaces shifted from single-dominant to composite patterns, while ESTH detected policy-driven clusters in Airport Economic Zones and market-driven suburban cold chain hubs. Bivariate LISA confirmed the spatial synergy between logistics growth and urban expansion, validating the “policy–space–industry” interaction framework. This research demonstrates how integrated NTL-POI remote sensing techniques can monitor policy impacts on urban systems, providing a replicable methodology for sustainable logistics planning.

Cities are actively engaged in policy and practices addressing urban housing crises and to foster social harmony, security, and stability. As the world's second largest economy, China's housing security system (HSS) has evolved alongside urbanization and economic advancement. Currently, the HSS is undergoing a new transformation. This study systematically reviews research on China's HSS, identifies the characteristics and limitations of current research, proposes future research trends based on new developments, and provides a scientific reference for gaining an in-depth understanding of its future development planning. Research on China's HSS focuses on two primary areas: the supply-side and the demand-side. Future research should also consider the following three aspects: (1) conducting further research on the multi-scheme policy integration and diversified policy choices of housing security supply; (2) thoroughly examining the demand effect of housing security and shifting the research focus from "access to housing" to "access to decent housing"; and (3) using big data to explore more refined and intelligent spatial adaptation analysis of affordable housing.

Introduction As China transitions toward high-quality development, the structural disconnect between urban expansion and socioeconomic-demographic growth has become increasingly pronounced, presenting fundamental constraints to sustainable urbanization. To address this asynchrony in urban spatial growth, our study establishes a multi-scalar, hierarchical analytical framework through the novel perspective of "spatial relative growth." Methods This study employs multi-source remote sensing and socioeconomic data from Chinese cities (from 2000 to 2020) to develop an integrated analytical framework. The analytical procedure comprises four sequential phases. First, nighttime light data and LandScan population datasets are integrated using wavelet transform to generate composite socioeconomic-demographic representations. Second, urban built-up areas are delineated and multi-temporal urban boundaries are extracted through a U-Net convolutional neural network. Third, urban centers and primary-secondary spatial structures are identified using spatial autocorrelation analysis (Global Moran's I) combined with Geographically Weighted Regression. Finally, coordination between urban expansion and socioeconomic-demographic growth is quantified through the Relative Development Index. Results The 2000-2020 period reveals three key findings in China's urban development. First, urban expansion systematically outpaces economic and demographic growth, with particularly pronounced spatial mismatch in central-western and southern regions. Second, relative spatial growth demonstrates scale dependence, showing progressively weaker effects from metropolitan to urban center scales, as evidenced by descending RDI values across these scales. Third, distinct hierarchical structures exhibit varying expansion patterns, indicating that urban functional specialization and resource allocation imbalances become amplified through multi-scalar interactions. Conclusion This multi-scalar investigation elucidates the hierarchical complexity of China's urban spatial growth patterns, advancing theoretical frameworks for understanding urban expansion. The findings offer substantive insights for optimizing territorial spatial organization, enhancing resource allocation efficiency, and guiding sustainable urban development pathways.

As China’s urban–rural integration progresses, the connections between urban and rural areas continue to strengthen, making the spatial matching between transportation infrastructure and tourism resources increasingly crucial for coordinated regional development. This study investigates the spatial–temporal mismatch between transportation development and tourism spatial vitality in Yunnan Province, proposing optimization strategies to improve their coordination. Using Weibo check-in big data and OpenStreetMap transportation network data, we apply Convolutional Long Short-Term Memory (ConvLSTM) networks and bivariate spatial autocorrelation analysis to examine this relationship. The results show strong transportation–tourism matching in Kunming and surrounding areas. However, northwest and southern Yunnan exhibit significant mismatches—despite transportation improvements, underdeveloped tourism resources constrain vitality growth. Particularly in some remote regions, well-developed transportation infrastructure coexists with low tourism vitality, revealing persistent spatial mismatches between transport facilities and tourism resources. In general, transportation infrastructure development generally enhances tourism spatial vitality, but requires coordinated tourism resource development and market demand alignment. The study results provide a basis for improving the coordinated development of transportation and tourism, offering practical guidance for policymakers to promote balanced regional development and urban–rural integration.

Clarifying the spatio-temporal evolution of PM2.5 concentration law and its driving mechanism is crucial for the prevention and control of air pollution in urban agglomerations, also helping promote their high-quality development. Based on remote sensing and statistics of urban agglomerations in China’s Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD), and Pearl River Delta (PRD) from 2005 to 2020, the paper analyses the evolution characteristics of the pollution concentration pattern and identifies the influencing factors through spatial analysis method combining the geodetector and geographically weighted regression (GWR) model. As the results show, during the study period: (1) Temporal Trends: annual PM2.5 concentrations exhibited significant declines, with BTH decreasing from 1004.71 μg/m 3 (2006) to 528 μg/m 3 (2020), YRD from 1434.81 μg/m 3 (2008) to 621 μg/m 3 , and PRD from 405.02 μg/m 3 (2007) to 292 μg/m 3 . The ranking remained YRD > BTH > PRD throughout the study period. (2) Spatial Heterogeneity: Spatial clustering (Moran’s I: 0.286–0.729, p < 0.05) dominated all regions. BTH showed a “high-south” pattern (e.g., Xingtai: 78.3 μg/m 3 vs. Qinhuangdao: 34.2 μg/m 3 ), YRD displayed “high-northwest” characteristics (Hefei: 68.5 μg/m 3 vs. Ningbo: 42.1 μg/m 3 ), while PRD exhibited a west-east gradient (Foshan: 49.8 μg/m 3 vs. Shenzhen: 25.6 μg/m 3 ). (3) The evolution of PM2.5 concentration in three urban agglomerations is generally positive autocorrelative aggregative distribution, and aggregation types include “high-high”, “low-low” and “high-low”. (4) The measurement of geographical detector indicates the differentiation of PM2.5 concentration is affected by both natural geography and socio-economic factors, and the former ones have stronger driving forces. (5) The measurement of GWR model indicates temperature, precipitation, vegetation coverage, urban expansion, industrial structure, and energy efficiency are main influencing factors of PM2.5 concentration pattern, and the degree of influence of these factors is different.

Achieving balanced development in both urban development level and urban life satisfaction is a key focus in the people-oriented guideline of the national New Type urbanization plan and constructing livable and sustainable cities. This study evaluates urban development levels based on nighttime light (NTL) data and LandScan population data and assesses urban life satisfaction by fusing urban amenities from objective built environment using Amap POIs and subjective emotions from human perspective based on sentiment analysis of Weibo social media data. The study then analyzes the coupling and coordination relationship and the relative development levels of these two aspects. The results indicate that first, urban development levels in China exhibit differentiated characteristics under the combined influence of economics and population. Second, cities with higher levels of urban life satisfaction are mostly cities in the eastern coastal regions and provincial capitals. Third, urban life satisfaction in China generally lags behind urban development levels. On one hand, this study innovatively combined subjective sentimental analysis and objective amenity assessment in urban life satisfaction evaluation. On the other hand, it enriches the case studies on the relationship between urban development and urban life satisfaction providing planning evidence for the livability and sustainable development of cities.

The accurate extraction of urban residential space (URS) is of great significance for recognizing the spatial structure of urban function, understanding the complex urban operating system, and scientific allocation and management of urban resources. The traditional URS identification process is generally conducted through statistical analysis or a manual field survey. Currently, there are also superpixel segmentation and wavelet transform (WT) processes to extract urban spatial information, but these methods have shortcomings in extraction efficiency and accuracy. The superpixel wavelet fusion (SWF) method proposed in this paper is a convenient method to extract URS by integrating multi-source data such as Point of Interest (POI) data, Nighttime Light (NTL) data, LandScan (LDS) data, and High-resolution Image (HRI) data. This method fully considers the distribution law of image information in HRI and imparts the spatial information of URS into the WT so as to obtain the recognition results of URS based on multi-source data fusion under the perception of spatial structure. The steps of this study are as follows: Firstly, the SLIC algorithm is used to segment HRI in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) urban agglomeration. Then, the discrete cosine wavelet transform (DCWT) is applied to POI–NTL, POI–LDS, and POI–NTL–LDS data sets, and the SWF is carried out based on different superpixel scale perspectives. Finally, the OSTU adaptive threshold algorithm is used to extract URS. The results show that the extraction accuracy of the NLT–POI data set is 81.52%, that of the LDS–POI data set is 77.70%, and that of the NLT–LDS–POI data set is 90.40%. The method proposed in this paper not only improves the accuracy of the extraction of URS, but also has good practical value for the optimal layout of residential space and regional planning of urban agglomerations.

The tertiary industry has become the main driving force for China’s economic development, and the adjustment and optimization of its structure are important prerequisites for achieving high-quality economic development. Existing studies have mostly focused on the spatial layout and influencing factors of the tertiary industry, with insufficient exploration of its internal structure. In this study, the PRD urban agglomeration is selected as the study area. On the basis of classifying the tertiary industry, the Dagum Gini coefficient, kernel density estimation, and local spatial autocorrelation are used to explore the spatial differentiation of various tertiary industries. The influencing factors are analyzed using geographical detectors, and suggestions for future development strategies are proposed. The results show that in terms of regional differentiation, the agglomeration of various tertiary industries in Guangzhou and Shenzhen is the most significant, but there is insufficient spillover to surrounding cities. In terms of development structure, the level of agglomeration of the consumptive tertiary industry is higher, the public tertiary industry tends to be more evenly distributed, and the productive tertiary industry is relatively dispersed. In terms of influencing factors, the interaction between population and employment dominates the spatial differentiation and evolution of the tertiary industry in the PRD urban agglomeration. Therefore, in the future, the tertiary industry in PRD urban agglomeration should promote the optimization of industrial structure and regional coordinated development under the guidance of the government.

In the context of pursuing high-quality development, the coupling and coordination of the ecosystem and economy has become the fundamental goal and inevitable choice for achieving the sustainable development of urban agglomerations. Based on remote sensing and statistical data for the Pearl River Delta (PRD) region from 2005 to 2020, in this paper, we construct an index system of the ecological and economic levels to assess the ecosystem service value (ESV). We use the equivalent factor method, entropy method, coupling coordination model, and relative development model to systematically grasp the spatial pattern of the levels of the two variables, analyse and evaluate their spatial and temporal coupling and coordination characteristics, and test the factors influencing their coupling and coordination using the geographical and temporal weighted regression (GTWR) model. The results show that ① the ESV in the PRD exhibited a fluctuating decreasing trend, while the level of the economy exhibited a fluctuating increasing trend; ② the coordination degree of the ESV and economy in the PRD exhibited a fluctuating increasing trend, and the region began to enter the basic coordination period in 2007; ③ in terms of the spatial distribution of the coordination degree, there was generally a circular pattern, with the Pearl River Estuary cities as the core and a decrease in the value towards the periphery; ④ the coordinated development model is divided into balanced development, economic guidance, and ESV guidance, among which balanced development is the major type; ⑤ the results of the GTWR reveal that the influencing factors exhibited significant spatial–temporal heterogeneity. Government intervention and openness were the dominant factors affecting the coordination, and the normalised difference vegetation index was the main negative influencing factor.

Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

本研究通过获取2013年和2022年粤港澳大湾区城市群的夜间灯光数据、LandScan空间数据和POI时空大数据,运用多种空间方法对比分析粤港澳大湾区城市群空间结构演变特征及其影响因素.研究发现:粤港澳大湾区城市群空间结构呈现"主聚副散""西多东少"的不平衡发展特征,且逐渐显现为多节点网络化的空间结构.此外,经济发展水平对大湾区城市群空间结构演变影响力最大,而自然因素的影响力最小.据此,本研究提出建设多节点支撑城市群空间格局、完善粤港澳大湾区交通网络、加强政府在资源要素配置中的宏观调控作用等建议,以期为优化粤港澳大湾区城市群空间结构提供有益借鉴.

The polycentric spatial structure is the most common spatial form of urban agglomerations, so exploring the evolution of this structure and analyzing its influencing factors is of great significance for the optimization of the spatial structure of urban agglomerations. However, there are relatively few studies on the topic that fuse multisource big data analysis, especially in the urban agglomeration of Western China. Therefore, this study uses a fusion of nighttime light (NTL) data, point of interest (POI) data and LandScan data to identify the polycentric spatial structure and its evolution in the Kunming–Yuxi (Kunyu) urban agglomeration and analyzes the factors that have dominated its evolution at different periods using geographic detectors. Results show that the fusion of multisource big data are more in line with the actual development process of the Kunyu urban agglomeration and the factors that have dominated the spatial evolution at different periods vary but the government and sectors have gradually become increasingly important. This study provides a feasible path for exploring urban spatial evolution through the fusion analysis of multisource big data in the Kunyu urban agglomeration and provides a reference for the key directions of urban agglomeration planning and development at different periods.

Planning policies are important drivers of spatial evolution in Chinese metropolitan areas; however, research on the impact of planning policy implementation on the spatial evolution of metropolitan areas is lacking. This study identifies the spatial evolution process of the Guangzhou metropolitan area, evaluates the results of planning policy implementation, and analyzes the possible spatial interactions between them. The results show that the spatial evolution of the Guangzhou metropolitan area is consistent with the point-axis development theory, and has formed a polycentric network-type spatial structure evolution. Moreover, there is an obvious spatial correlation between the implementation planning policies and the spatial evolution of a metropolitan area; that is, the planning policies have driven the spatial structure of the metropolitan area to develop gradually in different periods. This research enriches the theoretical study of the spatial evolution of metropolitan areas, and provides a point of reference for the development and planning of other metropolitan areas.

With the rapid expansion of urban built-up areas in recent years, accurate and long time series monitoring of urban built-up areas is of great significance for healthy urban development and efficient governance. As the basic carrier of urban activities, the accurate monitoring of urban built-up areas can also assist in the formulation of urban planning. Previous studies on urban built-up areas mainly focus on the analysis of a single time section, which makes the extraction results exist with a certain degree of contingency. In this study, a U-net is used to extract and monitor urban built-up areas in the Kunming and Yuxi area from 2012 to 2021 based on nighttime light data and POI_NTL (Point of Interest_Nighttime light) data. The results show that the highest accuracy of single nighttime light (NTL) data extraction was 89.31%, and that of POI_NTL data extraction was 95.31%, which indicates that data fusion effectively improves the accuracy of built-up area extraction. Additionally, the comparative analysis of the results of built-up areas and the actual development of the city shows that NTL data is more susceptible to urban emergencies in the extraction of urban built-up areas, and POI (Point of interest) data is subject to the level of technology and service available in the region, while the combination of the two can avoid the occasional impact of single data as much as possible. This study deeply analyzes the results of extracting urban built-up areas from different data in different periods and obtains the feasible method for the long time sequence monitoring of urban built-up areas, which has important theoretical and practical significance for the formulation of long-term urban planning and the current high-quality urban development.

With the rapid expansion of urban built-up areas in recent years, it has become particularly urgent to develop a fast, accurate and popularized urban built-up area extraction method system. As the direct carrier of urban regional relationship, urban built-up area is an important reference to judge the level of urban development. The accurate extraction of urban built-up area plays an important role in formulating scientific planning thus to promote the healthy development of both urban area and rural area. Although nighttime light (NTL) data are used to extract urban built-up areas in previous studies, there are certain shortcomings in using NTL data to extract urban built-up areas. On the other hand, point of interest (POI) data and population migration data represent different attributes in urban space, which can both assist in modifying the deficiencies of NTL data from both static and dynamic spatial elements, respectively, so as to improve the extraction accuracy of urban built-up areas. Therefore, this study attempts to propose a feasible method to modify NTL data by fusing Baidu migration (BM) data and POI data thus accurately extracting urban built-up areas in Guangzhou. More accurate urban built-up areas are extracted using the method of U-net deep learning network. The maximum built-up area extracted from the study is 1103.45 km(2), accounting for 95.21% of the total built-up area, and the recall rate is 0.8905, the precision rate is 0.8121, and the F1 score is 0.8321. The results of using POI data and BM data to modify NTL data to extract built-up areas have not been significantly improved due to the fact that the more data get fused, the more noise there would be, which would ultimately affect the results. This study analyzes the feasibility and insufficiency of using big data to modify NTL data through data fusion and feature extraction system, which has important theoretical and practical significance for future studies on urban built-up areas and urban development.

本文对影响干栏式建筑稳定性的各种因素进行了定性定量的分析,将各种因素的特点进行整理,利用物元可拓法建立对干栏式结构的安全评价体系模型.最后选取三江并流区域西双版纳的干栏式建筑,对其利用本文建立的安全性评价体系进行研究并评定其安全性,给出具体的评价数值.