Street vitality is a key indicator of urban sustainability, and high-quality built environments can promote street vitality. However, existing research lacks refined measurement approaches for street vitality and sufficient understanding of the spatial relationship patterns between built environment and street vitality. This study employs street view images and image detection to achieve a fine-grained measurement of street vitality. Furthermore, it utilizes methods such as the Optimal Parameter Geographical Detector, Spatial Lag Model, and Multi-scale Geographically Weighted Regression to explore the relationships between built environment factors and both pedestrian and cycling vitality, and to identify their distribution patterns and spatial effects. The findings reveal that: (1) there are significant differences in the distribution of pedestrian and cycling vitality, with varying associations with built environment factors; (2) the relationships between built environment factors and the two types of vitality differ inside and outside scenic areas; (3) both forms of vitality exhibit clear spatial lag effects, with approximately one-third of the vitality values correlated with adjacent areas; and (4) the correlation between built environment factors exhibits spatial heterogeneity. This study provides refined understanding of street vitality, offering guidance for street renewal.
Several studies have revealed that park green space (PGS) plays a crucial role in improving residents’ quality of life and promoting sustainable development of the environment. However, rapid urbanization and population growth have led to an inequitable supply and demand for PGS, especially in high-density cities, which has been widely recognized as an important environmental justice issue. However, few studies have evaluated the equity and sustainability of PGS in high-density cities based on multi-scale. This study developed a framework to explore the spatial equity of PGS and its coupling coordination degree (CCD) with socioeconomic deprivation (SED) based on a multi-scale approach (pocket park, community park, and comprehensive park), then analyzed the spatial correlation between PGS and CCD. The results showed that: (1) The overall supply of 3-scale PGS does not meet residents’ demand for PGS resources in the study area and the urban center has the highest demand for PGS. (2) Among the three-scale PGS, the comprehensive PGS has the strongest supply capacity, but it also has the most severe supply–demand mismatch. (3) Although the service radius of pocket PGS is smaller than that of community PGS, the supply of pocket PGS is higher. (4) More than 95% of the studied area lacks coordination between PGS and SED development. (5) The subsystem that has the greatest spatial correlation with CCD in pocket PGS and comprehensive PGS was the number of configurations, while that in community PGS was the spatial arrangement. This study not only provides a theoretical reference for conducting research on PGS equity in high-density cities, but also provides a novel perspective on the sustainable, coordinated development and planning of urban PGS system.
Dike-pond is a unique agricultural landscape type in the Pearl River Delta region of China, which has significance for the maintenance of ecological balance. In recent years, urbanization in China has developed rapidly, and dike-ponds have been extensively occupied, reducing their ecological regulation ability and threatening regional ecological security. Taking the Shunde District of Foshan as an example, based on remote sensing images from 1979 to 2020, using a CA-Markov model with the multi-criteria evaluation method (MCE), firstly the spatial and temporal evolution characteristics of the dike-pond landscape pattern were analyzed, then the dike-pond landscape in 2030 was simulated. At last, the spatio-temporal evolution of ecosystem service value (ESV) in Shunde was visualized. The results show that: (1) In the past four decades, the landscape types in Shunde have changed significantly. This mainly manifested as dike-pond, cultivated land, and forest land transforming into construction land. (2) At the class level, the degree of dike-pond landscape fragmentation increased, and the degree of dominance and agglomeration decreased. At the landscape level, the regional degree of dominance showed an upward trend, whereas the overall landscape showed an unbalanced trend distribution. It is predicted that from 2020 to 2030, the landscape pattern of dike-pond will not change significantly, and the overall landscape richness will increase. (3) The ESV in Shunde decreased continuously from 1979 to 2020. The dike-pond ESV accounts for the largest proportion and is the main landscape type that maintains ecological balance. It is predicted that the ESV decline will slow in the future. (4) The optimized MCE-CA-Markov model has greater precision and produces better simulations. The dike-pond development model proposed in this study can provide a scientific basis for delimiting the scope of regional ecological protection and sustainable development.
Under the combined pressures of climate change and rapid urbanization, high density cities are facing increasing risks of urban waterlogging (UW) during extreme rainfall events. However, existing UW risk assessments often lack systematic comparisons of different machine learning models and provide limited insight into nonlinear driving mechanisms. Taking Shenzhen, a representative high-density city in China, as a case study, this study develops an integrated assessment framework that combines multi source spatial data, multi-model machine learning comparison, and explainable artificial intelligence techniques. Thirteen risk factors are selected from the perspectives of hazard, environmental susceptibility, and exposure. Four ensemble tree-based models, namely Random Forest, Gradient Boosting Decision Tree, Extreme Gradient Boosting, and Light Gradient Boosting Machine, are applied and compared for UW risk prediction. The results show that Random Forest performs best overall, with high-risk areas identified by the model covering 92.45% of historical UW locations. Spatially, UW risk in Shenzhen exhibits a pronounced southeast low and northwest high pattern, closely associated with highly urbanized and densely populated areas. Model interpretation further reveals that risk factors exhibit strong nonlinear and threshold effects. Exposure related risk factors play a dominant role in shaping UW risk, among which impervious surface area, population density, and gross domestic product (GDP) are identified as key driving factors. In particular, GDP shows a rise then decline effect, indicating a mitigation role at higher development levels. This study provides a transferable framework to support differentiated flood risk management and resilience planning in high-density cities.