Quantifying the spatial homogeneity of urban road networks via graph neural networks

Xue, Jiawei; Jiang, Nan; Liang, Senwei; Pang, Qiyuan; Ukkusuri, Satish V.; Ma, Jianzhu

doi:10.1038/s42256-022-00462-y

Cited by 54 publications

(11 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is particularly significant in cities lacking available mobility data, providing immediate and valuable applications in the fields of epidemic disease containment, traffic engineering, and urban planning [52][53][54] . Looking ahead, the framework can be enhanced by integrating the impact of urban road networks on human mobility, thus offering a more comprehensive modeling approach 55 . In terms of future applications, DeepMobility has the potential to evolve into a transparent tool for constructing open urban mobility data that could offer detailed insights into population movements within cities globally.…”

Section: Discussionmentioning

confidence: 99%

Learning the complexity of urban mobility with deep generative collaboration network

Li,

Yuan,

Ding

et al. 2023

Preprint

View full text Add to dashboard Cite

City-scale individual movements, resulting population flows, and urban morphology intricately intertwine, collectively contributing to the complexity of urban mobility, impacting critical aspects of a city, including socioeconomic exchanges and epidemic transmission. Existing models, derived from the fundamental laws governing human mobility, often capture only partial facets of this complexity. This paper introduces DeepMobility, a powerful deep generative collaboration network to bridge the heterogeneous behaviors of individuals and collective behaviors emerging from the entire population via constructing a unified model that encapsulates the multifaceted nature of complex urban mobility. Our experiments, conducted on mobility trajectories and flows in cities of China and Senegal, reveal that, in contrast to state-of-the-art deep learning models that simply “memorize” observed data, DeepMobility excels in learning the intricate data distribution and successfully reproduces the existing universal scaling laws that characterize human mobility behaviors at both the individual and population levels. DeepMobility also exhibits robust generalization capabilities, enabling it to generate realistic trajectories and flows for cities lacking corresponding training data. Our approach underscores the feasibility of employing generative deep learning to model the underlying mechanism of human mobility, and establishes an effective generative machine learning framework to capture the complexity of urban mobility comprehensively.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning the complexity of urban mobility with deep generative collaboration network

Li,

Yuan,

Ding

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Hence, to save time on training models, we set both thresholds for the number of epochs in training and the F1 score. informed by existing studies [38,63], we would accept the validity of the embeddings when the F1 score of the model is greater than 0.5. In this study, the performance of the models for all selected counties satisfies this criterion.…”

Section: Generating and Validating The Embedding Spacementioning

confidence: 99%

Neural Embeddings of Urban Big Data Reveal Emergent Structures in Cities

Fan¹,

Yang²,

Mostafavi³

2021

Preprint

View full text Add to dashboard Cite

Over decades, many cities have been expanded and functionally diversified by population activities, sociodemographics and attributes of the built environment. Urban expansion and development have led to emergence of spatial structures of cities. Uncovering cities' emergent structures and spatial gradients is critical to the understanding of various urban phenomena such as segregation, equality of access, and sustainability. In this study, we propose using a neural embedding model-graph neural network (GNN)-that leverages the heterogeneous features of urban areas and their interactions captured by human mobility network to obtain vector representations of these areas. Using large-scale high-resolution mobility data sets from millions of aggregated and anonymized mobile phone users in 16 metropolitan counties in the United States, we demonstrate that our embeddings encode complex relationships among features related to urban components (such as distribution of facilities) and population attributes and activities. The spatial gradient in each direction from city center to suburbs is measured using clustered representations and the shared characteristics among urban areas in the same cluster. Furthermore, we show that embeddings generated by a model trained on a different county can capture 50% to 60% of the emergent spatial structure in another county, allowing us to make cross-county comparisons in a quantitative way. Our GNN-based framework overcomes the limitations of previous methods used for examining spatial structures and is highly scalable. The findings reveal non-linear relationships among urban components and anisotropic spatial gradients in cities. Since the identified spatial structures and gradients capture the combined effects of various mechanisms, such as segregation, disparate facility distribution, and human mobility, the findings could help identify the limitations of the current city structure to inform planning decisions and policies. Also, the model and findings set the stage for a variety of research in urban planning, engineering and social science through integrated understanding of how the complex interactions between urban components and population activities and attributes shape the spatial structures in cities.

show abstract

“…Graph neural networks show excellent learning ability on non-Euclidean data, which could more adaptably construct the complex interactions between regions in traffic accident prediction task (Jin et al, 2022). For example, Xue et al (2022) introduced a graph-based deep learning models to examining the spatial homogeneity of different subnetworks across 30 cities in the world. Jin et al (2022) created an automated dilated spatio-temporal synchronous graph model to record spatio-temporal correlation at various scales.…”

Section: Traffic Accident Predictionmentioning

confidence: 99%

Sparse Spatio-Temporal Dynamic Hypergraph Learning for Traffic Accident Prediction

Cui¹,

Yang

Abdel-Aty

2023

Preprint

View full text Add to dashboard Cite

Traffic accidents have become one of the biggest public health safety matters, which has raised many concerns from citizens and city managers. Accurate traffic accident prediction can not only assist the government in making decisions in advance but also enhance public trust in public safety. Conventional spatio-temporal prediction models, limited by the skewed distributions and sparse labels of traffic accident occurrence, are prone to overfitting. Inspired by hypergraph learning and self-supervised learning, this paper suggests a sparse spatio-temporal dynamic hypergraph learning (SST-DHL) framework to capture the higher-order dependencies in sparse traffic accidents. Specifically, a multi-view spatio-temporal convolution block is employed first to capture the local spatio-temporal correlation and inherent semantics of traffic accidents. Then we propose a cross-regional dynamic hypergraph learning model to capture global spatio-temporal dependencies beneath the entire urban landscape. In addition, a two-supervised self-learning paradigm is intended to strengthen the representation of sparse traffic occurrences by regional self-identification, which can capture local and global spatio-temporal traffic patterns. The proposed model is applicable to most sparse datasets for traffic forecasts. Extensive experiments was conducted on two heterogeneous accident datasets from New York City and London, and the results shows an average improvements of 7.21%-23.09% at different sparsity levels compared to the optimal baselines. More importantly, the proposed SST-DHL improves the interpretability of model results, which demonstrates that hypergraph learning can efficiently capture the complex higher-order spatio-temporal dependencies among different traffic accident instances.

show abstract

Quantifying the spatial homogeneity of urban road networks via graph neural networks

Cited by 54 publications

References 94 publications

Learning the complexity of urban mobility with deep generative collaboration network

Learning the complexity of urban mobility with deep generative collaboration network

Neural Embeddings of Urban Big Data Reveal Emergent Structures in Cities

Sparse Spatio-Temporal Dynamic Hypergraph Learning for Traffic Accident Prediction

Contact Info

Product

Resources

About