Guanwei Zhao

Urban wetland parks serve as vital infrastructure for climate resilience, yet a critical epistemological gap remains between their objective thermodynamic performance and the subjective thermal well-being of visitors. To bridge this divide, this study establishes an integrated computational social science framework that couples remote sensing metrics with AI-decoded digital narratives. Focusing on the high-density context of Shenzhen, we synthesized Landsat-derived environmental data with large-scale crowd-sourced digital footprints, employing Large Language Models (LLMs) to extract in-situ thermal sentiments from 11,109 online reviews. The analysis suggests that human thermal experience may follow non-linear trajectories relative to physical indicators. Patch Richness Density (PRD) was strongly associated with cooling efficiency, suggesting that landscape heterogeneity may enhance thermal well-being through both physical air exchange and the psychological benefits of visual complexity. The study further identifies a counter-intuitive “accessibility paradox”: a moderate density of impervious-surface patches (PD-I) is associated with higher “cool” perception, with an exploratory empirical turning point around 32.3 n/ha in the Shenzhen wetland-park sample. This pattern suggests that well-distributed access infrastructure may act as a behavioral mediator, facilitating visitor access to cooling cores while remaining subject to site-specific ecological and urban-morphological conditions. Additionally, comfortable perception shows an empirical turning point around a Land Surface Temperature (LST) of 28.8 °C, indicating a context-dependent adaptation range rather than a universal comfort standard. These findings challenge the conventional “minimize-pavement” assumption and suggest that thermal satisfaction depends on a strategic balance between ecological integrity and recreational accessibility. Rather than providing prescriptive design benchmarks, the identified non-linear patterns offer hypothesis-generating evidence and indicative design references for human-centric urban governance. This study contributes a replicable, AI-enhanced paradigm for aligning climate resilience research with public thermal perception.

Sensing urban vitality is a useful method for understanding urban development. However, the spatio-temporal characteristics of the association between the built environment and urban vitality in Shenzhen, the youngest mega-city in China, have not yet been explored. In this paper, we examined the effects of built environment indicators on urban vitality by using spatial regression models and multi-source geospatial data. The main research findings were as follows. Firstly, urban vitality displayed a consistent high–low pattern during both weekdays and weekends. Differences in the distribution of urban vitality with time between weekdays and weekends were more significant. Secondly, the effects of various built environment indicators on urban vitality exhibited significant temporal disparities. Within a day, population density, building density, bus station density, and distance to metro stations all exhibited positive effects, while distance to the central business district (CBD) exhibited negative effects, with pronounced diurnal differences. Moreover, the effects of road network density and functional mix on urban vitality were both positive and negative throughout the day. Thirdly, besides population density and building density, road network density, functional mix, bus stop density, and distance from metro stations exhibited positive and negative disparities within the study area. Overall, distance to the CBD had a negative effect on urban vitality. This concludes that planning for urban vitality should consider the spatio-temporal heterogeneity of the association between the built environment and urban vitality.

Understanding the impact of the urban built environment on taxis’ emissions is crucial for sustainable transportation. However, the marginal effects and spatial heterogeneity of this impact is worth noting. To this end, we calculated the taxis’ emissions on weekdays and weekends in Chengdu, China, and investigated the impact of the built environment on taxis’ emissions by applying multi-source data and several spatial regression models. The results showed that the taxis’ daily emissions on weekdays were higher than the emissions on weekends. The time heterogeneity of hourly taxis’ emissions was not significant, while the spatial heterogeneity of taxis’ emissions was significant. Except the HHI, the selected built environment variables both had a significant positive effect on taxis’ emissions on the global scale. There was a marginal effect of some built environment variables on taxis’ emissions, such as the density of bus stops and population density. The former exhibited an inhibitory effect on taxis’ emissions only when it was greater than 9 stops/km², while the latter showed an inhibitory effect only in the range between 16,000 people/km² and 22,000 people/km². There were some spatial variations in the effects of built environment factors on taxis’ emissions, with HHI, road density, and accommodation service facilities density showing the most significant variation. The marginal effect and spatial variation of the impact needs to be considered when developing strategies to reduce taxis’ pollutant emissions.

Characterizing the taxi travel network is of fundamental importance to our understanding of urban mobility, and could provide intellectual support for urban planning, traffic congestion, and even the spread of diseases. However, the research on the interaction network between urban functional area (UFA) units are limited and worthy of notice. Therefore, this study has applied the taxi big data to construct a travel flow network for the exploration of spatial interaction relationships between different UFA units in Shenzhen, China. Our results suggested that taxi travel behavior was more active in UFA units dominated by functions, including residential, commercial, scenic, and greenspace during weekends, while more active in UFA units dominated by industrial function during weekdays. In terms of daily average volume, the characteristics of spatial interaction between the various UFA types during weekdays and weekends were similar. During the morning peak period, the sink areas were mainly distributed in Futian District and Nanshan District, while during the evening peak period, the sink areas were mainly distributed in the southern part of Yantian District, the southwestern part of Longgang District, and the eastern part of Luohu District. The average daily taxi mobility network during weekdays showed a spatial pattern of “dense in the west and north, sparse in the south and east”, exhibiting significant spatial unevenness. Compared with weekdays, the daily taxi mobility network during weekends was more dispersed and the differences in node sizes decreased, indicating that taxi travel destinations were more diverse. The pattern of communities was more consistent with the administrative division during weekdays, indicating that taxi trips are predominantly within the districts. Compared with weekdays, the community pattern of network during weekends was clearly different and more in line with the characteristics of a small world network. The findings can provide a better understanding of urban mobility characteristics in Shenzhen, and provide a reference for urban transportation planning and management.

Understanding the effect of the urban built environment on online car-hailing ridership is crucial to urban planning. However, how the effects change with the analysis scales are still noteworthy. Therefore, a multiscale exploratory study was conducted in Chengdu, China, by using the stepwise regression selection and three spatial regression models. The main findings are summarized as follows. First, as the grid size increases, the number of built environment factors that have significant effects on trip intensity decrease continuously. Second, the effects of population density and road density are always positive from the 500 m grid to the 3000 m grid. As the analysis scale increases, the effect of proximity to public transportation shifts from inhibitory to facilitation, while the positive effect of land-use mix becomes stronger. Land-use type has both positive and negative effects and shows different characteristics at different scales. Third, the effects of built environment factors on online car-hailing trip intensity show different spatial variability characteristics at different scales. The effect of population density gradually decreases from north to south. The effect of road network density shows circling and wave patterns, with the former at relatively fine scales and the latter at relatively coarse scales. The spatial variation in the effect of land-use mix can only be observed more significantly at a relatively coarse scale. The effect of bus stop density is only obvious at the relatively fine and medium scales and shows a wave-like pattern and a circle-like pattern. The effect of various land-use types shows different spatial patterns at different scales, including wave-like pattern, circle-like pattern, and multi-core-like pattern. The spatial variation in the effects of various land-use factors gradually decrease with the increase in the analysis scale.

Dockless bike-sharing systems have become one of the important transport methods for urban residents as they can effectively expand the metro’s service area. We applied the ordinary least square (OLS) model, the geographically weighted regression (GWR) model and the multiscale geographically weighted regression (MGWR) model to capture the spatial relationship between the urban built environment and the usage of bike-sharing connected to the metro. A case study in Beijing, China, was conducted. The empirical result demonstrates that the MGWR model can explain the varieties of spatial relationship more precisely than the OLS model and the GWR model. The result also shows that, among the proposed built environment factors, the integrated usage of bike-sharing and metro is mainly affected by the distance to central business district (CBD), the Hotels-Residences points of interest (POI) density, and the road density. It is noteworthy that the effect of population density on dockless bike-sharing usage is only significant at weekends. In addition, the effects of the built environment variables on dockless bike-sharing usage also vary across space. A common feature is that most of the built environment factors have a more obvious impact on the metro-oriented dockless bike-sharing usage in the eastern part of the study area. This finding can provide support for governments and urban planners to efficiently develop a bike-sharing-friendly built environment that promotes the integration of bike-sharing and metro.

The spatial decomposition of demographic data at a fine resolution is a classic and crucial problem in the field of geographical information science. The main objective of this study was to compare twelve well-known machine learning regression algorithms for the spatial decomposition of demographic data with multisource geospatial data. Grid search and cross-validation methods were used to ensure that the optimal model parameters were obtained. The results showed that all the global regression algorithms used in the study exhibited acceptable results, besides the ordinary least squares (OLS) algorithm. In addition, the regularization method and the subsetting method were both useful for alleviating overfitting in the OLS model, and the former was better than the latter. The more competitive performance of the nonlinear regression algorithms than the linear regression algorithms implies that the relationship between population density and influence factors is likely to be non-linear. Among the global regression algorithms used in the study, the best results were achieved by the k-nearest neighbors (KNN) regression algorithm. In addition, it was found that multi-sources geospatial data can improve the accuracy of spatial decomposition results significantly, and thus the proposed method in our study can be applied to the study of spatial decomposition in other areas.

Mapping population distribution at fine resolutions with high accuracy is crucial to urban planning and management. This paper takes Guangzhou city as the study area, illustrates the gridded population distribution map by using machine learning methods based on zoning strategy with multisource geospatial data such as night light remote sensing data, point of interest data, land use data, and so on. The street-level accuracy evaluation results show that the proposed approach achieved good overall accuracy, with determinant coefficient (R²) being 0.713 and root mean square error (RMSE) being 5512.9. Meanwhile, the goodness of fit for single linear regression (LR) model and random forest (RF) regression model are 0.0039 and 0.605, respectively. For dense area, the accuracy of the random forest model is better than the linear regression model, while for sparse area, the accuracy of the linear regression model is better than the random forest model. The results indicated that the proposed method has great potential in fine-scale population mapping. Therefore, it is advised that the zonal modeling strategy should be the primary choice for solving regional differences in the population distribution mapping research.

Cellular automata model is a useful tool to understand the urbanization process. But nontrivial questions have to be answered about the choice of model parameters such as cell state resolution. The objective of this study is to evaluate the sensitivity of cellular automata to cell state resolution when using CA in a geographic context. The study chooses CA-Markov model to simulate urban expansion in the Huadu district (Guangzhou city, china). Two cell state resolutions are designed (urban/non-urban land use categories, multiple land use categories). Then the sensitivity of cell state resolution is undertaken by evaluating the resulting simulation accuracy of the model and the morphology of urban area. Results show that cell state resolution have a significant impact on simulation result in terms of both urban area and spatial pattern. The model outputs using two different cell state resolutions have great difference in term of both the resulting simulation accuracy of the model and the morphology of urban area. The urban area and patch numbers of model output produced by multiple land use dataset are higher than the model output with urban/non-urban land use dataset. While the urban growth rate and mean annual increment urban area are lower than the latter. Therefore, we shouldn't ignore the effect of modifying land use categories resolution on model output when using CA model to simulate urban expansion.