Computers Environment and Urban Systems最新文献

Active transport (AT)—physical activity (PA) during travel—can promote human health. Among built environment factors related to travel research, design refers to the street network features encouraging AT. The advent of street view images (SVIs) presents the potential to measure design during travel by capturing the eye-level built environments. Benefited by SVIs, this study innovatively introduces streetscape diversity—the interconnection of street view-derived built environment factors—during travel as the proxy to measure design from the street view perspective. Exposures to higher streetscape diversity could provide increased access to potential destinations and therapeutic landscapes, thereby promoting AT. Through integrating SVIs and young adults’ Global Positioning System (GPS) trajectories, this study utilized negative binomial regression models to assess the relationship between streetscape diversity and time spent in AT. Results indicate that the inclusion of streetscape diversity improves the model performance, and there is a positive relationship between streetscape diversity and AT. This finding indicates that increased access to travel routes with diverse streetscapes could increase the probability of participating in AT. Furthermore, integrating individual GPS data and SVIs allows more precise space-time measurement of individual environmental exposures.

Pluvial flash floods are fast-moving hazards and causes significant disruptions in urban areas. With the increase in heavy precipitations, the ability to proactively identify flash floods hotspots in cities is critical for flood nowcasting and predictive monitoring of risks. While rainfall runoff models and hydrologic models are useful models for flash flood prediction, these models are computationally expensive and effort intensive to be used for flood nowcasting. To address this challenge, this study presents interpretable machine learning models for predicting urban flash flood hotspots based on intertwined land and built environment features. The task of predicting flash flood hotspots is formulated as a binary classification problem, and three recent flash flood events in U.S. cities are selected for data collection and model validation. Various features related to land and built environment characteristics are constructed using diverse datasets, and the occurrences of flash floods are captured using crowdsource data from the events. Using these features and datasets, the flash flood hotspots of cities are predicted with two ensemble models based on decision trees. The results demonstrate that the models can achieve good accuracy (0.8) in identifying flooded/non-flooded locations. Especially, the models can achieve high true positive rate (0.83–0.89) and low missing rate, demonstrating the methods' practicability for accurately predicting flooded hotspots. The model interpretation results indicate that land features related to hydrological and topological features have greater impacts on flash flood risk, than built environment features. Further analysis reveals that the feature importance, model performance, and model transferability performance vary among cities and localized specifications of the models are needed for accurate prediction of flash flood for a particular city. The data-driven machine learning models presented in this study provide a useful tool for predicting flash flood hotspots based on the intertwined features of land and the built environment in cities to enable nowcasting and proactive monitoring of flash flood hotspots for emergency response and also inform integrated urban design and development towards flash flood risk reduction.

Urban outputs, from economy to innovation, are known to grow as a power of a city's population. But, since large cities tend to be central in transportation and communication networks, the effects attributed to city size may be confounded with those of intercity connectivity. Here, we map intercity networks for the world's two largest economies (the United States and China) to explore whether a city's position in the networks of communication, human mobility, and scientific collaboration explains variance in a city's patenting activity that is unaccounted for by its population. We find evidence that models incorporating intercity connectivity outperform population-based models and exhibit stronger predictive power for patenting activity, particularly for technologies of more recent vintage (which we expect to be more complex or sophisticated). The effects of intercity connectivity are more robust in China, even after controlling for population, GDP, and education, but not in the United States once adjusted for GDP and education. This divergence suggests distinct urban network dynamics driving innovation in these regions. In China, models with social media and mobility networks explain more heterogeneity in the scaling of innovation, whereas in the United States, scientific collaboration plays a more significant role. These findings support the significance of a city's position within the intercity network in shaping its success in innovative activities.

Walkability reflects the well-being of a city, and its measurement is evolving rapidly due to advancements of big data and machine learning technologies. The study examines the transformative impact of these technological interventions on the evaluation of walkability trends over the period 2015 to 2022. We create a framework consisting of big data sources, machine learning methods, and research purposes, revealing research trajectories and associated challenges. Despite diverse data usage, image data dominates in walkability research. While street view and point of interest data were primarily used to depict the environment, social media and handheld/ wearable data were more commonly employed to represent user behaviours or perceptions. Leveraging machine learning in conjunction with big data assists researchers in three aspects of walkability studies. First, researchers utilise classification and clustering to predict street quality, walkability, and identify neighbourhoods with certain characteristics. Second, researchers unveil relationship between the built environment and pedestrian perceptions or behaviours through regression analysis. Third, researchers employ generative models to create streetscapes or urban structures, although their utilisation is limited. Meanwhile, challenges persist in data access, customisation of machine learning models for urban studies, and establishing standard criteria to guarantee data quality and model accuracy.

This study assesses how the quality of place management (measured with user-generated ratings from Google Places) is related to crime occurrences at specific settings and whether specific crime types are related to specific types of places. In 50 randomly sampled neighborhoods in Ghent (Belgium) and London (United Kingdom), we analyzed Google Places data as a proxy measure for the quality of place management at the street segment level. We used hurdle models to examine the effects for both the prevalence and frequency of crime at micro places, and to deal with excess zeros in the data. User-generated ratings of places provide a useful place-level indicator for place management that are related to crime. However, contextual differences are found between Ghent and London. For London, the results suggest that higher quality of place management has a protective effect on crime occurrences at the street segment level. This study indicates the importance of exploring new and emerging data sources as unique measurement opportunities to enhance insight in crime prevention mechanisms, and also acknowledges its limitations. For the first time from a large-scale empirical perspective, this study suggest that improving place management at specific places might be an effective intervention to guard against crime.

Prediction of high-risk areas for urban crime is of great significance for maintaining public safety and sustainable development. However, existing approaches are deficient in spatiotemporal sensitivity and perceptivity, which make it difficult to extract the spatiotemporal dependency from uneven and sparsely distributed data. To address this problem, the novel multi-scale neural network models, namely ST-HGNet and ST-HGNet(a) with attention, were proposed. It is dedicated to further exploring spatiotemporal patterns and improving hotspot location prediction accuracy for sparse types of crimes. First, multi-scale conception and attention mechanisms were introduced to address the receptive field range fixed problem. It enhanced representation of captured information by exposing spatial “scale” dimension and assigning weight relationships. Then, novel multi-scale hierarchical gating architecture was designed that has two forms of whether to add attention or not, to enhance the sensitivity of features and the perception of sparse features by filtering the valid information at different scales. Ultimately, the periodic temporal components were used to capture different time-trend dependencies. The proposed model adopted well-known Chicago assault crime dataset as a case study. Compared with five common benchmark models, the results show that the ST-HGNet model outperformed other baseline models and achieved higher prediction accuracy at multiple level spatial resolution. In particular, ST-HGNet(a) with self-attention achieved the greatest improvement at 1000 m, with a mean hit rate of more than 84%.

Urbanization-induced land cover changes significantly impact ecological environments and socioeconomic growth. Vector-based cellular automata (VCA) models are an advanced cellular automata (CA) method that use irregular cells and perform well in simulating land use changes within urban areas. However, the applicability and parameter setting of VCA models for land cover change simulation are still challenging for researchers. To address this issue, this study applied a VCA model and two raster-based models, i.e., a pixel-based CA model and a patch-based CA model, to simulate and compare their performance in simulating land cover changes. The results show that VCA and patch-based CA were superior, with VCA's FoM being 39.74% higher than pixel-based CA and 11.00% over patch-based CA. VCA effectively tracks construction land expansion in rapidly developing areas, while patch-based CA excels in central urban and suburban shifts, fitting broader study scopes. Additionally, a spatial scale sensitivity analysis of the VCA model revealed that a smaller VCA cell size improves accuracy but introduces a risk of spatial pattern errors. Notably, the scope of study impacts VCA accuracy more than cell size. These findings bolster land cover change modeling theory and offer insights for precise future land cover change simulations and decision-making.

Streets are a crucial part of the built environment, and their layouts, the street patterns, are widely researched and contribute to a quantitative understanding of urban morphology. However, traditional street pattern analysis only considers a few broadly defined characteristics. It uses administrative boundaries and grids as units of analysis that fail to encompass the diversity and complexity of street networks. To address these challenges, this research proposes a machine learning-based approach to automatically recognise street patterns that employs an adaptive analysis unit based on street-based local areas (SLAs). SLAs use a network partitioning technique that can adapt to distinct street networks, making it particularly suitable for different urban contexts. By calculating several streets’ network metrics and performing a hierarchical clustering method, streets with similar characters are grouped under the same street pattern. A case study is carried out in six cities worldwide. The results show that street pattern types are rather diverse and hierarchical, and categorising them into clearly demarcated taxonomy is challenging. The study derives a set of new morphometrics-based street patterns with four major types that resemble conventional street patterns and eleven sub-types to significantly increase their diversity for broader coverage of urban morphology. The new patterns capture urban structural differences across cities, such as the urban-suburban division and the number of urban centres present. In conclusion, the proposed machine learning-based morphometric street pattern to characterise urban morphology has an enhanced ability to encompass more information from the built environment while maintaining the intuitiveness of using patterns.

The issue of jobs-housing balance concerns the sustainable development of cities and the well-being of residents. Conventional measurement approaches, however, often fall short due to the zoning problem (as a subproblem of the modifiable areal unit problem), leading to inconsistent and inaccurate results depending on the spatial partitioning scheme applied. This paper discusses the application and advantages of the local colocation quotient method in jobs-housing balance measurement. A case study of Nanjing, China, is selected, and mobile location data are used to obtain the jobs and housing locations of workers. Then, the adjusted jobs-workers ratio and the local colocation quotient values that reflect the degree of jobs-housing balance are calculated and compared by category. The results show that on the one hand, due to the zoning effect, when points are aggregated into spatial units, some points with different spatial characteristics are masked by the dominant value of the units; on the other hand, the local colocation quotient method can solve the zoning problem and obtain more fine-scale and accurate results, thus providing a new analytical tool and perspective for this field.

African cities are growing rapidly and more than half of their populations live in deprived areas. Local stakeholders urgently need accurate, granular, and routine maps to plan, upgrade, and monitor dynamic neighborhood-level changes. Satellite imagery provides a promising solution for consistent, accurate high-resolution maps globally. However, most studies use very high spatial resolution images, which often cover only small areas and are cost prohibitive. Additionally, model transferability to new cities remains uncertain. This study proposes a scalable and transferable approach to routinely map deprived areas using free, Sentinel-2 images. The models were trained and tested on three cities: Lagos (Nigeria), Accra (Ghana), and Nairobi (Kenya). Contextual features were extracted at 10 m spatial resolution and aggregated to a 100 m grid. Four machine learning algorithms were evaluated, including multi-layer perceptron (MLP), Random Forest, Logistic Regression, and Extreme Gradient Boosting (XGBoost). The scalability of model performance was examined using patches of the different deprived types identified through visual image interpretation. The study also tested the ability of models to map deprived areas of different types across cities. Results indicate that deprived areas have heterogeneous local characteristics that affect large area mapping. The top 25 features for each city show that models are sensitive to the spatial structures of deprived area types. While models performed well on individual cities with XGBoost and MLP achieving an F1 scores of over 80%, the generalized model proves to be more beneficial for modeling multiple cities. This approach offers a promising solution for scaling routine, accurate maps of deprived areas to hundreds of cities that currently lack any such map, supporting local stakeholders to plan, implement, and monitor geotargeted interventions.