Computers Environment and Urban Systems最新文献

In the evolving landscape of poverty research, especially in China, the focus has shifted from eliminating absolute poverty to relieving relative poverty. Although much of the existing studies have begun to use built environment big data, such as remote sensing and street view imagery, to measure poverty, peoples' consumption, an essential indicator of poverty receives less attention. This study delves into the relationship and spatial disparity between poverty measured by consumer big data and multidimensional poverty measured based on the census data. We investigated 1731 communities in Guangzhou as case study regions and combined their residents' mobile phone metadata and spatial cost of living data as the input consumer big data. Then, we constructed Index of Multiple Deprivation (IMD) levels based on the census data and built random forest classification model based on our consumer big data to predict IMD level at community level. The result shows that the predicted poverty of 81.11% communities were generally consistent with the IMD level, indicating that the consumer big data poverty mapping provided a viable poverty measurement from consumer behavior perspective. The SHapley Additive exPlanations' values result shows that Pinduoduo (a low-cost online shopping mobile application) contributes the most to predicted poverty from consumer behavior. For spatial disparities, poverty mapping based on consumer big data is more sensitive to the poverty in suburban developing neighborhoods and affordable housing communities compared with the IMD. The urban poverty mapping based on consumer big data offers a timely portray of communities' socio-economic challenges and consumption-related poverty, and provides support and evidence for accurate urban poverty alleviation strategies.

Resilient post-disaster recovery is crucial for the long-term sustainable development of modern cities, and in this regard, predicting the unusual flows of human mobility when disasters hit, could offer insights into how emergency responses could be managed to cope with such unexpected shocks more efficiently. For years, many studies have been dedicated to developing various models to predict human movement; however, abnormal human flows caused by large-scale urban disasters, such as urban floods, remain difficult to capture accurately using existing models. In this paper, we propose a spatiotemporal hybrid deep learning model based on a graph convolutional network and long short-term memory with a spatial heterogeneity component. Using 1.32 billion movement records from smartphone users, we applied the model to predict total hourly flows of human mobility in the “7.20” extreme urban flood in Zhengzhou, China. We found that the proposed model can significantly improve the prediction accuracy (i.e., $R^2$ from 0.887 to 0.951) for during-disaster flows while maintaining high accuracy for before- and after-disaster flows. We also show that our model outperforms selected mainstream machine learning models in every disaster stage in a set of sensitivity tests, which verifies not only its better performance for predicting both usual and unusual flows but also its robustness. The results underscore the effective role of spatial heterogeneity in predicting human mobility flow in a disaster context. This study offers a novel tool for better depicting human mobility under the impact of urban floods and provides useful insights for decision-makers managing how people move in large-scale disaster emergencies.

Zoning regulates land use and intensity of urban development at the county and municipal level in the United States, promoting economic growth, community health, and environmental preservation. However, limited availability of zoning data at scale hinders regional assessments of regulations and coordinated resilience planning efforts. In this study, we developed an open-source, replicable, and transferable framework to predict spatially complete zoning in areas where zoning information is publicly unavailable. We applied a Hierarchical Random Forest algorithm to predict multilevel zoning districts, including three core districts (residential, non-residential, mixed use) and 13 sub-districts. To mimic real-world data accessibility challenges, we evaluated two models: one filling gaps within a county (within-county) and the other extrapolating for counties with no available data (between-county). We tested our models statewide in North Carolina (NC), USA, and developed the State's first comprehensive zoning map. We found strong predictive performance for our within-county model (∼99% accuracy; macro averaged F1 score of ∼0.97) irrespective of district breakdown (i.e., core and sub). However, our between-county model performance was lower and varied depending on the training counties sampled and the district breakdown considered (19–90% accuracy; macro averaged F1 score of 0.105–0.451). Our framework provides spatially complete zoning maps for previously inaccessible locations, enabling researchers and planners to conduct large-scale comprehensive zoning assessments.

Cities around the world are grappling with multiple interconnected challenges, including population growth, shortage of affordable and decent housing, and the need for neighborhood improvements. Despite its critical importance for policy, our ability to effectively monitor and track urban change remains limited. Deep learning-based computer vision methods applied to street-level images have been successful in the measurement of socioeconomic and environmental inequalities but did not fully utilize temporal images to track urban change, as time-varying labels are often unavailable. We used self-supervised methods to measure change in London using 15 million street images taken between 2008 and 2021. Our novel adaptation of Barlow Twins, Street2Vec, embeds urban structure while being invariant to seasonal and daily changes without manual annotations. It outperformed generic pretrained embeddings, successfully identified point-level change in London's housing supply from street-level images, and distinguished between major and minor change. This capability can provide timely information for urban planning and policy decisions towards more liveable, equitable, and sustainable cities.

Public events, such as concerts and sports games, can be major attractors for large crowds, leading to irregular surges in travel demand. Accurate human mobility prediction for public events is thus crucial for event planning as well as traffic or crowd management. While rich textual descriptions about public events are commonly available from online sources, it is challenging to encode such information in statistical or machine learning models. Existing methods are generally limited in incorporating textual information, handling data sparsity, or providing rationales for their predictions. To address these challenges, we introduce a framework for human mobility prediction under public events (LLM-MPE) based on Large Language Models (LLMs), leveraging their unprecedented ability to process textual data, learn from minimal examples, and generate human-readable explanations. Specifically, LLM-MPE first transforms raw, unstructured event descriptions from online sources into a standardized format, and then segments historical mobility data into regular and event-related components. A prompting strategy is designed to direct LLMs in making and rationalizing demand predictions considering historical mobility and event features. A case study is conducted for Barclays Center in New York City, based on publicly available event information and taxi trip data. Results show that LLM-MPE surpasses traditional models, particularly on event days, with textual data significantly enhancing its accuracy. Furthermore, LLM-MPE offers interpretable insights into its predictions. Despite the great potential of LLMs, we also identify key challenges including misinformation and high costs that remain barriers to their broader adoption in large-scale human mobility analysis.

Urban greenways enhance the social, environmental, and ecological facets of city life by offering accessible and engaging spaces for residents. Despite their significance, the route selection for these urban greenways often hinges on suitability analysis, which can be influenced by a planner's subjective judgment, thus potentially introducing bias. Spatial optimization is a potential solution for determining optimal urban greenway routes. However, urban greenway route planning poses a distinct spatial optimization challenge that is not addressed by existing models. While urban greenways are inherently linear features, there are generally no specific start or end points dictated in their planning, which contrasts with many existing line-based spatial optimization models. Moreover, the way that coverage for urban greenways is measured—by taking into account the area encompassed within a particular distance from the entire urban greenway—deviates from the method used in conventional coverage optimization models, which works through discrete point-based evaluations. To address these gaps, our study introduces the maximal covering location problem for lines (MCLP-Line) model, which is designed to determine the optimal single-line-shaped urban greenway route with maximum coverage of nearby residents. In this paper, we utilize a line graph data structure to transform the candidate road network into a graph where road segments become nodes and junctions are treated as edges. We delineate the mixed integer linear programming formulation for the MCLP-Line model and discuss approaches for eliminating subtours in the MCLP-Line model in detail. The study provides simulation tests using both randomly generated data and an empirical dataset from Lhasa to demonstrate the practicality and computational efficiency of the proposed model.

Fine-granular spatio-temporal trajectories, i.e., time-stamped sequences of locations, play a pivotal role in transport and urban analytics. However, sharing or publishing trajectory data of individuals raises concerns about location privacy given the potential for re-identification and unintentional dissemination of sensitive information. A key enabler for privacy breaches is precise temporal information. Thus, this study investigates the privacy-preserving capabilities of third-party free mechanisms protecting trajectories by exclusively targeting the temporal dimension. We compare a deterministic and a stochastic technique for shifting trajectories in time by adding an offset to each timestamp. The stochastic approach leverages a generalized version of differential privacy to render an individual's presence at any event plausibly deniable, obstructing re-identification attacks based on spatio-temporal side knowledge. Furthermore, we present a Markov chain-based speed perturbation technique that preserves dynamic patterns while obfuscating travel times and motion attributes. Using simulated re-identification attacks, we analyze privacy gains and contrast them with the utility loss. The results demonstrate a favorable utility-to-privacy ratio of the temporal techniques compared to established spatial and spatio-temporal approaches. This underlines the importance of accounting for temporal aspects in addition to spatial considerations in privacy-preserving trajectory publishing.

This research investigates the potential of Shared Autonomous Vehicles (SAVs) to eliminate Conventional Private Vehicles (CPVs) towards sustainable carfree cities. Besides internal-city CPV travellers, travellers with external trips (either origins or destinations are outside the city) are also shifted to SAVs or Public Transit (PT) based on individuals' utilities with Park-and-Ride (PnR) initiatives. Our research presents a new PnR allocation approach optimising PnR facilities selections. Then, several Agent-Based Modellings (ABM) are conducted using MATSim. Brussels, the capital of Belgium, is selected as the case study area. The outcomes reveal the significant impacts of PnR market penetration and SAV pricing strategies. The proposed carfree initiatives bring notable benefits, including reduced congestion in the city centre and significant transport emission reductions. However, there are also drawbacks, such as longer travel time for PnR travellers and increased congestion in specific regions. Consequently, a PnR market penetration between 40% to 60% represents a feasible range under the current Brussels mobility network. Furthermore, SAVs should be seen as a complement to PT rather than with a very low fare structure. Generally, our findings emphasise the necessity for a multifaceted approach for different stakeholders to maximise SAV benefits towards more sustainable mobility networks.

China is on the brink of transitioning into an aged society, resulting in a growing demand for an age-friendly street-built environment. However, previous research has paid limited attention to the differentiated walking needs of older adults. To address this gap, this study investigated the relationship between street-built environments and the subjective perception of older adults with different physical capabilities, focusing on safety, comfort, and interest. The older adults were classified into three types based on their physical mobility abilities. The TrueSkill algorithm was used to develop an online image selection website to obtain perception scores for sampled pictures from these three types of older adults. Image segmentation and deep learning were combined to extract indices of street view factors, and machine learning was used to train a scoring prediction model for all streetscape pictures of the area. The study found differences in the subjective perception among all three types of older adults, namely independent elderly (A), mediated-assisted elderly (B), and dependent elderly (C). Type A older adults might be attracted to factors related to the interest of walking despite their negative impact on safety and comfort; Type B older adults were more concerned about street conditions for safety and comfort. Type C older adults were prone to the convenience of barrier-free access and visibility. This study contributes to the study of walkability by providing a research framework for the subjective walking perceptions of older adults with different physical capabilities. Additionally, the visualized walkability map can serve as a reference for architects and urban designers, further strengthening the development of age-friendly communities with the aid of human-centric computational analysis, evaluation, and design.

Although the successfulness of public participation projects has been studied from many different perspectives, there is a lack of knowledge of how participation influences the planning outcomes. Through the interview study of nine Finnish urban planning projects, we studied how the use of a digital public participation GIS tool has influenced the outcomes of urban planning. In the selected cases the information collected with a PPGIS tool has been highly valued by the planners, leading to concretely influential participation in 6 out of 9 cases. In these cases, the planners gave concrete examples of how the information had influenced the created plan or draft. We created a model that describes how the information produced by participants is traveling from the participants to the outcome of the planning process. With this model, the main factors limiting the degree of influence were recognized, and actions were presented that could increase the influence.