Traffic Analysis Zones Research Articles

Using Statewide Transportation Planning Model to Forecast Demand for Electric Vehicle Charging at Stations Along Intercity Highways

The availability of Charging Stations (CSs) with adequate capacity is critical for the growth in ownership and usage of Electric Vehicles (EVs). In the United States, the state Departments of Transportation (DOTs) are responsible for planning CSs along the Interstate, national, and state highways. While the state DOTs have their Statewide Transportation Planning Models (STPMs), most of these models do not represent EVs internally. The state DOTs can only rely on the existing STPMs to forecast the demand for EV charging at specific CS locations in a state’s highway network. This research proposes a methodology that utilizes an existing STPM, EV and non-EV vehicle registration data, and hourly traffic volumes at strategic counting stations to predict the hourly demand for EV charging (charging port occupancy) at proposed CSs. This approach first estimates the volume of all passenger cars that will pass the vicinity of a CS along intercity highways, and identifies the Traffic Analysis Zones (TAZs) of their trip origins. Based on the EV adoption rates of the TAZs, EV range, and EV owner’s charging behavior, the methodology forecasts the volume of EVs that pass the vicinity of a CS and the number of EVs that will stop at the CS to charge every hour of the day. An example problem demonstrated the application of the methodology in the State of Texas. It not only forecasted the hourly occupancy at CSs along three major corridors, but also demonstrated how to determine the capacities of the CSs. The challenges of using the existing STPM and their solutions are discussed. This proposed methodology enables the state DOTs to forecast the demand for EV charging and the capacities at the proposed CSs along intercity highways, thus allowing the DOTs to apply for federal funds to accelerate the deployment of the CSs. (298 words)

Performance Evaluation for the Expansion of Multi-Level Rail Transit Network in Xi’an Metropolitan Area: Empirical Analysis on Accessibility and Resilience

As the main form of new urbanization, the coordinated development of cities in metropolitan areas requires reliable and efficient rail transit skeleton support. However, in the rapid development of metropolitan areas, the layout and analysis of multi-level rail transit systems have a certain lag. Taking the Xi’an metropolitan area as an example, this study analyzes the comprehensive accessibility and resilience of the multi-level rail transit network, and proposes an expansion plan accordingly. The traffic analysis zone (TAZ) is divided by towns and streets, and the relationship between points of interest (POIs) and the regional average level is analyzed using DEA. The improved weighted average travel time model is built with the analysis results as regional weights; a site selection model based on multiple construction influencing factors is proposed, and four expansion plans, namely, economic optimal, environmental optimal, transport optimal, and integrated optimal, are designed. The peak passenger flow scenario and the “failure–reparation” scenario during the entire operation period are designed to analyze the resilience of four plans, and the resilience is quantified by the elasticity curve of the maximum connected subgraph ratio (MCSR) changing over time. The research results show that the transport optimal plan has the best comprehensive accessibility and resilience, reducing travel costs in Houzhenzi Town, which has the worst accessibility, by 34%. The expansion model and evaluation method in this study can provide an empirical example for the development of other metropolitan areas and provide a reasonable benchmark and guidance for the development of multi-level rail transit networks in future urban areas.

SenseMap: Urban Performance Visualization and Analytics Via Semantic Textual Similarity.

As urban populations grow, effectively accessing urban performance measures such as livability and comfort becomes increasingly important due to their significant socioeconomic impacts. While Point of Interest (POI) data has been utilized for various applications in location-based services, its potential for urban performance analytics remains unexplored. In this article, we present SenseMap, a novel approach for analyzing urban performance by leveraging POI data as a semantic representation of urban functions. We quantify the contribution of POIs to different urban performance measures by calculating semantic textual similarities on our constructed corpus. We propose Semantic-adaptive Kernel Density Estimation which takes into account POIs' influential areas across different Traffic Analysis Zones and semantic contributions to generate semantic density maps for measures. We design and implement a feature-rich, real-time visual analytics system for users to explore the urban performance of their surroundings. Evaluations with human judgment and reference data demonstrate the feasibility and validity of our method. Usage scenarios and user studies demonstrate the capability, usability and explainability of our system.

Investigating the Nonlinear Effect of Land Use and Built Environment on Public Transportation Choice Using a Machine Learning Approach

Understanding the relationship between the demand for public transportation and land use is critical to promoting public-transportation-oriented urban development. Taking Beijing as an example, we took the Public Transportation Index (PTI) during the working day’s early peak hours as the dependent variable. And 15 land use and built environment variables were selected as the independent variables according to the “7D” built environment dimensions. According to the Modifiable Areal Unit Problem (MAUP), the size and shape of the spatial units will affect the aggregation results of the dependent variable and the independent variables. To find the ideal spatial unit division method, we assess how well the nonlinear model fits several spatial units. Extreme Gradient Boosting (XGBoost) was utilized to investigate the nonlinear effects of the built environment on PTI and threshold effects based on the ideal spatial unit. The results show that (1) the best spatial unit division method is based on traffic analysis zones (TAZs); (2) the top four explanatory variables affecting PTI are, in order: mean travel distance, residential density, subway station density, and public services density; (3) there are nonlinear relationships and significant threshold effects between the land use variables and PTI. The priority regeneration TAZs were identified according to the intersection analysis of the low PTI TAZs set and the PTI-sensitive TAZs set based on different land use variables. Prioritized urban regeneration TAZs require targeted strategies, and the results of the study may provide a scientific basis for proposing strategies to renew land use to increase PTI.

Improving accessibility to radiotherapy services in Cali, Colombia: cross-sectional equity analyses using open data and big data travel times from 2020

In this study, we evaluated and forecasted the cumulative opportunities for residents to access radiotherapy services in Cali, Colombia, while accounting for traffic congestion, using a new people-centred methodology with an equity focus. Furthermore, we identified 1–2 optimal locations where new services would maximise accessibility. We utilised open data and publicly available big data. Cali is one of South America's cities most impacted by traffic congestion.Methodology: Using a people-centred approach, we tested a web-based digital platform developed through an iterative participatory design. The platform integrates open data, including the location of radiotherapy services, the disaggregated sociodemographic microdata for the population and places of residence, and big data for travel times from Google Distance Matrix API. We used genetic algorithms to identify optimal locations for new services. We predicted accessibility cumulative opportunities (ACO) for traffic ranging from peak congestion to free-flow conditions with hourly assessments for 6–12 July 2020 and 23–29 November 2020. The interactive digital platform is openly available.Primary and secondary outcomes: We present descriptive statistics and population distribution heatmaps based on 20-min accessibility cumulative opportunities (ACO) isochrones for car journeys. There is no set national or international standard for these travel time thresholds. Most key informants found the 20-min threshold reasonable. These isochrones connect the population-weighted centroid of the traffic analysis zone at the place of residence to the corresponding zone of the radiotherapy service with the shortest travel time under varying traffic conditions ranging from free-flow to peak-traffic congestion levels. Additionally, we conducted a time-series bivariate analysis to assess geographical accessibility based on economic stratum. We identify 1–2 optimal locations where new services would maximize the 20-min ACO during peak-traffic congestion.Results: Traffic congestion significantly diminished accessibility to radiotherapy services, particularly affecting vulnerable populations. For instance, urban 20-min ACO by car dropped from 91% of Cali’s urban population within a 20-min journey to the service during free-flow traffic to 31% during peak traffic for the week of 6–12 July 2020. Percentages represent the population within a 20-min journey by car from their residence to a radiotherapy service. Specific ethnic groups, individuals with lower educational attainment, and residents on the outskirts of Cali experienced disproportionate effects, with accessibility decreasing to 11% during peak traffic compared to 81% during free-flow traffic for low-income households. We predict that strategically adding sufficient services in 1–2 locations in eastern Cali would notably enhance accessibility and reduce inequities. The recommended locations for new services remained consistent in both of our measurements.These findings underscore the significance of prioritising equity and comprehensive care in healthcare accessibility. They also offer a practical approach to optimising service locations to mitigate disparities. Expanding this approach to encompass other transportation modes, services, and cities, or updating measurements, is feasible and affordable. The new approach and data are particularly relevant for planning authorities and urban development actors.

An urban building use identification framework based on integrated remote sensing and social sensing data with spatial constraints

ABSTRACT Building use identification is crucial in urban planning and management. Current identification methods often rely on a single data source and neglect spatial proximity. In this paper, we propose a stepwise urban building use identification framework that integrates remote sensing and social sensing data with spatial constraints based on the association of buildings with Point of Interest (POI), Area of Interest (AOI) and remote sensing data. First, the study data are preprocessed using geometric correction and POI and AOI reclassification. Then, we identify buildings with the quantitative-density index of the POIs as well as the spatial relationships between the AOIs and the buildings. Next, we generate Traffic Analysis Zones (TAZs) from road network data and utilize the similarity in physical features of buildings from remote sensing data to identify building use within spatial constraints. Finally, POI kernel density estimation is used to determine the semantic features of the buildings, and the similarity of the features between the buildings is utilized to identify the remaining buildings. The specificity of our proposed framework lies not only in the combination of multiple source data at the building-level but also in the introduction of the spatial relationships of AOIs and spatial constraints. Shenyang is selected as an example. The proposed framework identifies buildings as commercial, residential, industrial, public service and scenic spots. The accuracy assessment indicates that the proposed framework performs well, with an Overall Accuracy (OA) of 87.1% and a kappa coefficient (kappa) of 73.4%. The results of the comparison experiments show that the consideration of spatial constraints and the integration of multiple data sources help to improve the accuracy of building use identification. The proposed framework provides a new tool for better identification of urban building use, and the generated data are suitable for in-depth analyses such as building-level urban heat islands.

Identifying Urban functional regions: A multi-dimensional framework approach integrating metro smart card data and car-hailing data

Urban functions often diverge from initial planning due to changes driven by residents’ behaviors. Effective urban planning and renewal require accurately identifying urban functional regions based on residents’ behavior data (including activity and travel data). However, previous methods have primarily relied on either point of interest (POI) data or a single source of traffic data, and often ignore the combined influence of residents’ activities and travel behaviors. In this study, we introduce a novel framework that integrates multiple sources of traffic data (such as metro smart card data and car-hailing data) with POI data to identify urban functional regions. This approach is unique because it simultaneously considers two critical dimensions of residents’ behavior: travel and activity behaviors. By combining these dimensions, we extract a comprehensive set of characteristics, including travel time, travel flow, origin-destination patterns, activity types, and activity time, which are then aggregated at the regional level (i.e., traffic analysis zone). To process these characteristics, we use latent Dirichlet allocation (LDA) to extract high-level semantic features from each data type. Additionally, to handle the sparse data from metro smart cards, we employ a specialized clustering technique. The integration of diverse and complementary information from multiple data sources enables more accurate and nuanced identification of urban functional regions than single data source and k-means clustering algorithm, providing valuable insights for urban planners.

An Estimation Method for Passenger Flow Volumes from and to Bus Stops Based on Land Use Elements: An Experimental Study

To unravel the general relationship between bus travel and land use around bus stops and along bus routes and to promote their coordinated development, this paper explores a method to estimate passenger flow volumes from and to bus stops based on land use types, intensities, and spatial distributions around bus stops and along bus routes. Firstly, following the principle of the gravity model, which considers traffic volumes analogous to gravity based on trip generation and distance impedance between traffic analysis zones (TAZs), a gravitational logic estimation method for passenger flow volumes from and to bus stops was constructed with land use elements between bus stop TAZs and the upstream and downstream collections of bus stop TAZs. Building upon this, the passenger flow volumes from and to 38 bus stops in the Xueyuan Square area of Dalian during weekday morning peak hours were taken as the experimental objects. The basic estimation models of two gravity sets corresponding to passenger flow volumes from and to bus stops were constructed using the bus travel generation based on the aggregation of area-based origin unit method and the bus travel distance impedance based on the probability density method. Finally, the reliability of the estimation method of passenger flow volumes from and to bus stops was verified by regression fitting between the surveyed values of passenger flow volume and the estimated values of the basic models. The results indicate that the fuzzy estimation and transformation of bus travel based on land use elements, which serves as a crucial lever for facilitating strategic alignment in transit-oriented development (TOD), can be effectively achieved by using the area-based origin unit method to aggregate bus travel generation and the probability density method to evaluate the bus travel distance impedance.

Dynamic measurements of geographical accessibility considering traffic congestion using open data: a cross-sectional assessment for haemodialysis services in Cali, Colombia

Many cities with traffic congestion lack accessibility assessments accounting for traffic congestion and equity considerations but have disaggregated georeferenced municipal-level open data on health services, populations, and travel times big data. We convened a multistakeholder intersectoral collaborative group that developed a digital, web-based platform integrating open and big data to derive dynamic spatial-temporal accessibility measurements (DSTAM) for haemodialysis services. We worked with stakeholders and data scientists and considered people's places of residence, service locations, and travel time to the service with the shortest travel time. Additionally, we predicted the impacts of strategically introducing haemodialysis services where they optimise accessibility. Cross-sectional analyses of DSTAM, accounting for traffic congestion, were conducted using a web-based platform. This platform integrated traffic analysis zones, public census and health services datasets, and Google Distance Matrix API travel-time data. Predictive and prescriptive analytics identified optimal locations for new haemodialysis services and estimated improvements. Primary outcomes included the percentage of residents within a 20-min car drive of a haemodialysis service during peak and free-flow traffic congestion. Secondary outcomes focused on optimal locations to maximise accessibility with new services and potential improvements. Findings were disaggregated by sociodemographic characteristics, providing an equity perspective. The study in Cali, Colombia, used geographic and disaggregated sociodemographic data from the adjusted 2018 Colombian census. Predicted travel times were obtained for two weeks in2020. There were substantial traffic variations. Congestion reduced accessibility, especially among marginalised groups. For 6-12 July, free-flow and peak-traffic accessibility rates were 95.2% and 45.0%, respectively. For 23-29 November, free-flow and peak traffic accessibility rates were 89.1% and 69.7%. The locations where new services would optimise accessibility had slight variation and would notably enhance accessibility and health equity. Establishing haemodialysis services in targeted areas has significant potential benefits. By increasing accessibility, it would enhance urban health and equity. No external or institutional funding was received.

Delineating Source and Sink Zones of Trip Journeys in the Road Network Space

Source–sink zones refer to aggregated adjacent origins/destinations with homogeneous trip flow characteristics. Current relevant studies mostly detect source–sink zones based on outflow/inflow volumes without considering trip routes. Nevertheless, trip routes detail individuals’ journeys on road networks and give rise to relationships among human activities, road network structures, and land-use types. Therefore, this study developed a novel approach to delineate source–sink zones based on trip route aggregation on road networks. We first represented original trajectories using road segment sequences and applied the Latent Dirichlet Allocation (LDA) model to associate trajectories with route semantics. We then ran a hierarchical clustering operation to aggregate trajectories with similar route semantics. Finally, we adopted an adaptive multi-variable agglomeration strategy to associate the trajectory clusters with each traffic analysis zone to delineating source and sink zones, with a trajectory topic entropy defined as an indicator to analyze the dynamic impact between the road network and source–sink zones. We used taxi trajectories in Xiamen, China, to verify the effectiveness of the proposed method.

Scale effects-aware bottom-up population estimation using weakly supervised learning

ABSTRACT Fine-scale population estimation (FPE) is crucial for urban management. After training, the bottom-up FPE models can be applied independently of census data. However, given the lack of real fine-scale population data, the existing bottom-up methods typically apply models trained on coarse-grained census data to FPE directly, causing estimation bias induced by scale effects. Traffic analysis zones (TAZs) balance geo-semantics and fine granularity, but their potential as population analysis units has not been fully exploited. Hence, we developed a weakly-supervised TAZ-scale bottom-up population estimation method (WSTP). Specifically, to mitigate scale effects, the weakly-supervised training procedure involves fine-scale feature input, model prediction, spatial aggregation, and coarse-scale supervision is designed to ensure that WSTP consistently focuses on FPE throughout the training and prediction phases. To enable weakly-supervised training using census data, we treated TAZs as graph nodes and designed a Spatial Aggregation Layer to aggregate TAZ-scale population predictions into communities. Given the diverse distribution patterns across age groups, we decomposed the FPE task by age groups. The experiments showed that WSTP significantly outperformed the baselines with R2 values of 0.821 and 0.785 at the community and TAZ scales, respectively, indicating that WSTP can mitigate scale effects and produce high-resolution, accurate population data.

How does visual environment affect outdoor jogging behavior? Insights from large-scale city images and GPS trajectories

Understanding the relationships between visual environment (VE) and outdoor jogging is crucial to facilitating effective environmental interventions. However, how the visual environment affects jogging behavior remains unclear due to data and technology limitations. This study aimed to explore the spatially and temporally varying effects of visual environment on jogging behavior. Specifically, street view images and geotagged photos were used to measure the visual environment outside and inside the traffic analysis zone (TAZ), respectively; and massive GPS trajectories collected from a fitness application were utilized to estimate jogging activities. Furthermore, random forest and multiscale geographically weighted regression (MGWR) models were established to examine the impacts of VE on jogging flow in Beijing, China. Results showed that visual greenery, openness, and walkability play an important role in determining jogging behaviors. Effects of some VE variables display distinct scale effects and spatial non-stationarity. Notably, the dual effects or synergistic effects of specific VE factors, such as visual greenery, walkability, between inside and outside the TAZ were identified. Effects of certain VE factors, e.g., visual greenness, openness, on jogging behavior vary across peak-hours, weekdays and weekends, and seasons, respectively. These findings have practical implications in city planning design for building jogging-friendly urban environment.

An integrated multi-resolution framework for jointly estimating crash type and crash severity

The current research effort contributes to safety literature by developing an integrated framework that allows for the influence of independent variables from crash type and severity components at the disaggregate level to be incorporated within the aggregate level propensity to estimate crash frequency by crash type and severity. The empirical analysis is based on the crash data drawn from the city of Orlando, Florida for the year 2019. The disaggregate level analysis uses 15,518 crash records of three crash types including rear end, angular and sideswipe. Each crash record contains crash specific factors, driver and vehicle factors, roadway attributes, road environmental and weather information. For aggregate level model analysis, the study aggregates the crash records by crash type over 300 traffic analysis zones. An exhaustive set of independent variables including roadway and traffic characteristics, land-use attributes, built environment and sociodemographic factors are considered in this level. The empirical analysis is further augmented by employing several goodness of fit and predictive measures. A validation exercise is also conducted using a holdout sample to highlight the superiority of the proposed integrated model relative to the non-integrated model system. The proposed framework can also incorporate unobserved heterogeneity in the model system. The findings of the study indicate that the proposed framework is advantageous for capturing the variable effects simultaneously across the aggregate and disaggregate levels.

Analyzing Transportation Equity in the D.C. Metropolitan Area Using Large-Scale Agent-Based Modeling and Simulation

Policymakers face the challenge of providing equitable infrastructure services to all city dwellers with limited budgets. Further, equity analysis based on the socioeconomic characteristics of travelers is not palatable for some. This paper proposes a novel framework for analyzing equity in terms of access to opportunity rather than equity of outcomes. We showcase the use of a large-scale, high-fidelity agent-based, activity-based transportation model to analyze equity in the Washington DC metropolitan region. Travel time between each traffic analysis zone and its nearest activity area is used as a measure of access-to-opportunities, thereby carrying out equity analysis without using the socioeconomic characteristics of the traveler. The results of this analysis are visualized in a GIS heatmap. Decision-makers can visually identify regions needing attention and focus their funding and efforts on improving infrastructure services in the specified regions. Decision makers may elect to increase the capacity of road segments or develop a new employment activity center in the area of interest. The paper contributes to the literature by analyzing equity of opportunities without considering individuals’ socioeconomic characteristics, applying a higher fidelity activity-based model to a large metropolitan area, and documenting a framework and the results of large-scale equity analysis of the Washington DC metropolitan region.

An analysis of bicycle accidents with respect to spatial heterogeneity

Bicycles are an eco-friendly mode of transportation, and in the capital city of South Korea, Seoul, efforts are being made to encourage citizens to use bicycles. However, without appropriate safety measures, these efforts can lead to an increase in bicycle-related traffic accidents. To promote bicycle usage while ensuring safety, this study identified various factors that influence bicycle accidents. Data were utilized that had not been properly considered in previous bicycle accident-related studies, including slope and the level of public transportation services. By considering the factors influencing bicycle traffic accidents, various models were constructed, and through comparisons of statistical indicators, the optimal model was selected geographically weighted negative binomial regression. Ultimately, three significant conclusions to ensure bicycle safety were drawn. First, across all areas of Seoul, an increase in road slope leads to a decrease in bicycle-related accidents. Furthermore, for certain Traffic Analysis Zones (TAZs), as the number of local buses (or neighborhood/community buses) increases, the bicycle traffic volume decreases, resulting in a reduction in bicycle accidents. Lastly, for some TAZs, an increase in bicycle lanes to be installed into the roadway was associated with an increase in bicycle accidents.

Comparative Analysis of Discrete Choice Approaches for Modeling Destination Choices of Urban Home-Based Trips to Work

Discrete choice models based on the Random Utility Maximization (RUM) approach are alternatives to traditional aggregated trip distribution models. However, the Random Regret Minimization (RRM) approach has emerged as an alternative to RUM for analyzing behavioral phenomena. This study compares the RUM and RRM approaches to model the destination choice of urban home-based trips to work, with a case study in the city of São Paulo, Brazil. The attributes of distance between traffic analysis zones (TAZs), total number of jobs, and number of jobs per type (industry and services) were considered, and the attributes referring to TAZs in commercial areas were tested in different models. We combined a method to estimate the optimal choice set size and a stratified sampling method to choose alternatives from available choices for a destination-choice problem with many alternatives. The RUM and RRM models produced similar results with respect to the final log-likelihood, [Formula: see text], Akaike information criterion, and Bayesian information criterion for the studied case. However, the RRM models required 52 min to be estimated on average, whereas estimation of the RUM models took only 31 s on average. Models derived from the RUM approach including the total number of jobs and distance produced higher accuracy, requiring less computational time to estimate the parameters.

Shared e-scooter service providers with large fleet size have a competitive advantage: Findings from e-scooter demand and supply analysis of Nashville, Tennessee

Shared e-scooter systems are one of the fastest-growing micromobility modes in the United States. In response to service providers’ rapid deployment of e-scooter vehicles, several city governments have regulated shared e-scooters through permits and pilot programs, including the number of service providers, their fleet size, and provisions for expanding/downsizing the fleet size. However, the literature lacks an empirical analysis of the demand elasticity of shared e-scooters. We used a Poisson fixed effects regression to evaluate the demand elasticity of e-scooter vehicle deployment using the Shared Urban Mobility Device (SUMD) dataset from Nashville, Tennessee, between March 1, 2019 and February 2020. This dataset included disaggregated e-scooter trip summary data and vehicle location data that updates approximately every five minutes. We also estimated land-use specific demand elasticity of e-scooter vehicle deployment by clustering Traffic Analysis Zones (TAZs) using the K-means algorithm. We found that the average daily demand elasticity of e-scooter vehicle deployment is inelastic (0.64). Service providers with large fleet sizes (>500 average daily e-scooters) have a demand elasticity of e-scooter deployment that is 1.8 times higher than that of medium fleet-sized service providers (250–500 average daily e-scooters). Fleet size is likely correlated to service provider-specific attributes such as vendor popularity, brand loyalty, and rideshare services. We also found a significant difference in demand elasticity of e-scooter deployment for land use types, with university and park & waterfront land uses having the highest elasticity values. These findings could be helpful for city governments to identify the optimal number of service providers and fleet sizes to permit so that demand is fulfilled without an oversupply of e-scooter vehicles in public spaces.

Spatial and Temporal Evolution of the Characteristics of Spatially Aggregated Elements in an Urban Area: A Case Study of Wuhan, China

Urban spatial elements present agglomeration and dispersion geographic processes in the urban development. Identifying the characteristics of their distribution changes and accurately capturing the evolution of the urban spatial structure is of great significance to urban construction and management. This study takes Wuhan as a case study and focuses on the spatial agglomeration distribution of urban elements. Point of Interest (POI) data from 2017 to 2021 were collected, and the Block2Vec model was employed to extract the comprehensive geographic information from various elements within the traffic analysis zones (TAZs). Subsequently, identification and division were carried out to access the level of urban spatial element agglomeration. Finally, the spatial–temporal evolution characteristics of urban aggregated elements in the Wuhan metropolitan development area over five years were compared and analyzed. The results indicate the following: (1) urban elements present an obvious circle structure in their spatial agglomeration, with distinct differences observed among different element types; (2) from 2017 to 2021, the Wuhan urban development zone experienced obvious expansion in urban space; (3) increased agglomeration of spatial elements mainly occurred in the surrounding areas of the city, while some areas in the city center displayed weaker element agglomeration and a reduction in various service facilities. The results demonstrate that the method used in this study could effectively identify the spatial agglomeration distribution of urban elements, as well as accurately distinguishing regions with distinct development characteristics. This approach could provide robust support for optimizing land use and urban spatial planning.

How Does the Built Environment Affect Drunk-Driving Crashes? A Spatial Heterogeneity Analysis

In this research, 3356 alcohol-related traffic crashes were obtained from blood-alcohol test reports in Tianjin, China. Population density, intersection density, road density, and alcohol outlet densities, including retail density, entertainment density, restaurant density, company density, hotel density, and residential density, were extracted from 2114 traffic analysis zones (TAZs). After a spatial autocorrelation test, the multiple linear regression model (MLR), geographically weighted Poisson regression model (GWPR), and semi-parametric geographically weighted Poisson regression model (SGWPR) were utilized to explore the spatial effects of the aforementioned variables on drunk-driving crash density. The result shows that the SGWPR model based on the adaptive Gaussian function had the smallest AICc value and the best-fitting accuracy. The residential density and the intersection density are global variables, and the others are local variables that have different influences in different regions. Furthermore, we found that the influence of local variables in the economic–technological development area shows significantly different characteristics compared with other districts. Thus, a comprehensive consideration of spatial heterogeneity would be able to improve the effectiveness of the programs formulated to decrease drunk driving crashes.

Exploring the impact of trip patterns on spatially aggregated crashes using floating vehicle trajectory data and graph Convolutional Networks

In recent years, increased attention has been given to understanding the spatial pattern of crashes in urban areas. Accurately capturing the spatial relationship between crash counts and variables requires extracting hidden information from multiple data sources. In this study, we propose a machine learning model to explore the spatial impact of activity patterns on spatially aggregated crash counts. Our paper introduces a two-step framework: (a) the Latent Dirichlet Allocation (LDA) model, an unsupervised method for mining hidden activity patterns from floating vehicle trajectory data, and (b) the Graph Convolutional Network (GCN) model, which builds the spatial relationship between multi-source data. The data and hidden activity patterns were aggregated into 175 Traffic Analysis Zones (TAZs) in San Francisco using spatial partitioning. The GCN model provided higher prediction accuracy than commonly used machine learning algorithms that did not consider combined spatial relationships and those that only considered traditional vehicle counts data. Furthermore, we used attribution algorithms to obtain the respective weight scores of each factor. Our results reveal that daily vehicle kilometers traveled, road density, population density, commercial activity during weekends, and residential activity during morning peak hours on weekdays are factors associated with crashes.