The configuration of the urban built environment is critical for promoting sustainability and achieving carbon neutrality. However, existing studies mostly use linear and spatial econometric models to investigate the relationship between urban built environments and traffic carbon dioxide (CO₂) emissions, in-depth studies exploring the heterogeneous impacts of related features on traffic CO₂ emission by interpretive machine learning models are scarce. Hence, we extract four dimensionless features to depict the size, compactness, irregularity, and isolation of built-up areas, and road network-related features (i.e., average cluster coefficient, road topological density, and road geometric density), respectively. Subsequently, we develop an interpretive machine learning framework based on the extracted features related to the urban built-up areas and road networks. The interpretive results of the proposed framework uncover that urban morphological features, especially population density (POP), GDP per capita (GDPpc), and urban physical compactness (UPC), have a heterogeneous impact on the per capita traffic emission (PCCE) across different cities. GDPpc is more like a linear relationship with PCCE, and UPC has a significant influence on PCCE when its value is between 62% and 78%. Our results also reveal the nonlinear relationships and interactive effects between these features, providing the implications of urban morphological planning and carbon emission reduction.

Background: Existing studies mainly focus on the relationship between real-time weather and traffic crash injury severity, while few scholars have investigated the operation risk levels caused by traffic incidents. Identifying weather-related factors that affect the incident-induced delay is helpful for estimating the delay levels when an incident occurs. Accordingly, the present study profoundly explores the relationship between weather conditions and traffic delays caused by traffic incidents. Methods: The traffic incident and weather datasets from January 1 to December 31, 2020, in New York State are used. To that end, the hazard-based duration and multinomial logit modeling frameworks are employed to determine the effect of weather conditions on the duration of traffic delay and the delay severity, respectively. More importantly, to account for multiple layers of unobserved heterogeneity, a random parameter with heterogeneity in means approach is introduced into the above two models. Results: (1) The strong breeze (wind speed over 8 m/s) and low visibility (visibility under 5 km) significantly affect the duration of delay. (2) Hot day (between 20 and 30 °C) has a 344.03 % greater probability of minor delay. A strong breeze has a higher probability of severe delay. The low visibility is found to increase the estimated odds of moderate delay and severe delay by 51.15 % and 13.39 %, respectively. In comparison, the normal visibility (between 10 and 20 km) significantly decreases the estimated odds of severe delay by 119.17 %. Conclusions: Compared with other weather factors, wind speed, temperature, and visibility have the greatest impact on the traffic delay levels after a traffic accident, and there are significant differences in the impact under different delay severity. Findings from this study will help policymakers to establish comprehensive differentiating security measures to resolve traffic delays.

Knowledge of the hierarchical organization of urban heavy truck flows is important for understanding the structure of urban freight system and underlying interactions dynamics, providing insights to assess and develop freight policies. The complexity and dynamic nature of urban freight system pose significant challenges in comprehensively capturing structured arrangement of heavy truck movements. In this paper, we uncover the hierarchical organization of urban heavy truck flows by using complex network theory. We use large-scale heavy truck GPS data and urban freight location point-of-interest (POI) data to construct urban heavy truck mobility networks, and detect their community structure. The empirical results suggest different sets of locations are closely linked to each other to form multiple clusters. By integrating the categories of locations, we reveal the cluster-specific industry concentration and industry-specific location roles, informing evidence-based policy formulation. To capture the interaction dynamics of locations, we develop a spatial network growth model that considers the spatial agglomeration of industrial clusters and interaction pattern of locations. The model provides a mathematical tool to simulate the formation process of real-world networks for logistics planning and management.

Accurate estimation of intercity heavy truck mobility flows is of vital importance to urban planning, transportation management and logistics operations. The inaccessibility of big data related to intercity transport systems and the heterogeneity of trucking activities pose challenges for the reliable estimation. Recently, the advance of Artificial Intelligence (AI) provides a potential solution to this problem. However, most previous studies focused on the estimation of inter-regional passenger mobility. In-depth studies of estimating intercity heavy truck mobility flows by using deep learning techniques are still scarce. To fill in the gaps, we construct a deep neural network based on the Deep Gravity framework, an advanced predictive model for human mobility. We collect a wide range of data related to heavy truck movements, freight locations, road networks and land uses to train the model, and validate its high performance by comparing to traditional gravity model. Furthermore, we use an explainable AI technique to interpret how the city features contribute to the determination of intercity heavy truck movements, and the results can provide valuable policy implications for logistics operations, businesses and urban planning.