The rapid increase in infrastructural development in populated areas has had numerous adverse impacts. The rise in land surface temperature (LST) and its associated damage to urban ecological systems result from urban development. Understanding the current and future LST phenomenon and its relationship to landscape composition and land use/cover (LUC) changes is critical to developing policies to mitigate the disastrous impacts of urban heat islands (UHIs) on urban ecosystems. Using remote sensing and GIS data, this study assessed the multi-scale relationship of LUCC and LST of the cosmopolitan exponentially growing area of Beijing, China. We investigated the impacts of LUC on LST in urban agglomeration for a time series (2004–2019) of Landsat data using Classification and Regression Trees (CART) and a single channel algorithm (SCA), respectively. We built a CA–Markov model to forecast future (2025 and 2050) LUCC and LST spatial patterns. Our results indicate that the cumulative changes in an urban area (UA) increased by about 908.15 km² (5%), and 11% of vegetation area (VA) decreased from 2004 to 2019. The correlation coefficient of LUCC including vegetation, water bodies, and built-up areas with LST had values of r = −0.155 (p > 0.419), −0.809 (p = 0.000), and 0.526 (p = 0.003), respectively. The results surrounding future forecasts revealed an estimated 2309.55 km² (14%) decrease in vegetation (urban and forest), while an expansion of 1194.78 km² (8%) was predicted for a built-up area from 2019 to 2050. This decrease in vegetation cover and expansion of settlements would likely cause a rise of about ~5.74 °C to ~9.66 °C in temperature. These findings strongly support the hypothesis that LST is directly related to the vegetation index. In conclusion, the estimated overall increase of 7.5 °C in LST was predicted from 2019–2050, which is alarming for the urban community’s environmental health. The present results provide insight into sustainable environmental development through effective urban planning of Beijing and other urban hotspots.

As street imagery and big data techniques evolve, opportunities for refined urban governance emerge. This study delves into effective methods for urban perception evaluation and street refinement governance by using street view data and deep learning. Employing DeepLabV3+ and VGGNet models, we analyzed street view images from Nanshan District, Shenzhen, identifying critical factors that shape residents’ spatial perceptions, such as urban greenery, road quality, and infrastructure. The findings indicate that robust vegetation, well-maintained roads, and well-designed buildings significantly enhance positive perceptions, whereas detractors like fences reduce quality. Furthermore, Moran’s I statistical analysis and multi-scale geographically weighted regression (MGWR) models highlight spatial heterogeneity and the clustering of perceptions, underscoring the need for location-specific planning. The study also points out that complex street networks in accessible areas enhance living convenience and environmental satisfaction. This research shows that integrating street view data with deep learning provides valuable tools for urban planners and policymakers, aiding in the development of more precise and effective urban governance strategies to foster more livable, resilient, and responsive urban environments.

In recent decades, the availability of diverse location-based service (LBS) data has largely stimulated the research in individual human mobility. However, less attention has been paid on the intra-city movement of cyclists coupled with their spatiotemporal dynamics. To fill the knowledge gap, drawing on bicycle-sharing data over one week in Shanghai, China, this study investigates the dynamics of bicycle-sharing users at two spatial scales (i.e., city level and subdistrict level) and explores the intra-city spatial interactions by those cyclists. At the city level, by applying the analysis of variance (ANOVA) test and the Wilcoxon signed-rank test, this study examines the temporal variation of cyclists across a seven-day period. At the subdistrict level, we develop a new index to capture the urban vitality using bicycle-sharing data with the consideration of trip flow allied with spatial weights. In terms of the computed urban vitality over the course of a day, 98 subdistricts are partitioned into 7 groups by using K-means clustering. In addition, spatial autocorrelation and hot spot analysis are also applied to examine the spatial features of urban vitality at different periods. Our results reveal that urban vitality has an obvious character of the spatial cluster and this cluster feature varies markedly over the course of a day. By shedding new lights on intra-city movement, we argue our results are important in informing urban planners on how to better allocate public facilities and increase bicycle usage as a way to progress towards more sustainable urban areas.

When a public health emergency occurs, a potential sanitation threat will directly change local residents’ behavior patterns, especially in high-density urban areas. Their behavior pattern is typically transformed from demand-oriented to security-oriented. This is directly manifested as a differentiation in the population distribution. This study based on a typical area of high-density urban area in central Tianjin, China. We used Baidu heat map (BHM) data to calculate full-day and daytime/nighttime state population aggregation and employed a geographically weighted regression (GWR) model and Moran’s I to analyze pre-epidemic/epidemic population aggregation patterns and pre-epidemic/epidemic population flow features. We found that during the COVID-19 epidemic, the population distribution of the study area tended to be homogenous clearly and the density decreased obviously. Compared with the pre-epidemic period: residents’ demand for indoor activities increased (average correlation coefficient of the floor area ratio increased by 40.060%); traffic demand decreased (average correlation coefficient of the distance to a main road decreased by 272%); the intensity of the day-and-night population flow declined significantly (its extreme difference decreased by 53.608%); and the large-living-circle pattern of population distribution transformed to multiple small-living circles. This study identified different space utilization mechanisms during the pre-epidemic and epidemic periods. It conducted the minimum living security state of an epidemic-affected city to maintain the operation of a healthy city in the future.

Background: Urban heat island (UHI) is being intensified with the progress of urbanization. Meanwhile, respiratory diseases caused by high temperature become common. This study explores the influences of UHI on respiratory diseases (J00-J99) and the evolutionary characteristics of the spatial pattern of such influences. Methods: The pattern–process–function and the influencing mechanism of UHI on respiratory diseases were evaluated through landscape pattern indexes from 1992 to 2018 in Tianjin, China. The basis was on data from Landsat TM/OLI/TIRS remote-sensing images, meteorological stations, and mortality of respiratory diseases. Results: The fluctuating influence of UHI on the respiratory diseases in Tianjin has increased from 1992 to 2018, showing a significant phase-based characteristic. During 2011-2018, the influence has soared greatly, and mortality risk has increased by 101%, and the influenced area has reached 349 km². Furthermore, the regional space clustered, and the influenced patches are in irregular shape, and the highly influenced area is enlarged. Moreover, the indexes of the landscape level of the influenced areas all decrease. The patches at all levels are fragmented and distributed discontinuously. Spatially, the influenced areas gradually extend from the urban center to the suburbs. Conclusion: UHI causes a higher mortality of respiratory diseases because it increases daily average air temperature in summer. With respect to landscape pattern, the influenced areas at low level is highly interconnected and relatively concentrated, whereas the influenced area at high level is distributed in clusters. In general, the influenced area is fragmented and discontinuously distributed in urban center.

Understanding the evolution of rural landscapes in metropolises during rapid urbanization is crucial for formulating policies to protect the rural ecological environment. In this study, remote sensing and geographical information system data, as well as applied landscape index analysis, are used to examine the spatiotemporal evolution of rural landscape patterns in the Beijing-Tianjin region of China, which has experienced rapid urbanization. The relationships between land use/land cover changes and changes in rural landscape patterns are explored. The results revealed significant spatial differences in the rural landscapes in the Beijing-Tianjin region; farmland and forestland were the main types of landscapes, creating a "mountain-field-sea" natural landscape pattern. The conversion of rural landscapes in the Beijing-Tianjin region involved mainly the conversion of farmland to urban areas, with few exchanges between other landscape types. The urban areas in the Beijing-Tianjin region increased by 3% per decade; farmland decreased at the same rate. Additionally, the rural landscape patterns in the Beijing-Tianjin region were dominated by fragmentation, dispersion, and heterogeneity and moved from complex to regular. Water bodies displayed the most fragmented natural landscape; their number of patches increased by 36%, though their network characteristics were maintained. Forestland was the most concentrated natural landscape. In this study, theoretical support and a scientific reference for the optimization of rural landscape patterns and the improvement in rural living environments in rapidly urbanizing areas are provided.