Analysis of Traffic Crashes Involving Pedestrians Using Big Data: Investigation of Contributing Factors and Identification of Hotspots

Developing equity-aware safety performance functions for identifying hotspots of pedestrian-involved crashes

Crashes are frequently disproportionally observed in disadvantaged areas. Despite the evident disparities in transportation safety, there has been limited exploration of quantitative approaches to incorporating equity considerations into road safety management. This study proposes a novel concept of equity-aware safety performance functions (SPFs), enabling a distinct treatment of equity-related variables such as race and income. Equity-aware SPFs introduce a fairness distance and integrate it into the log-likelihood function of the negative binomial regression as a form of partial lasso regularization. A parameter λ is used to control the importance of the regularization term. Equity-aware SPFs are developed for pedestrian-involved crashes at the census tract level in Virginia, USA, and then employed to compute the potential for safety improvement (PSI), a prevalent metric used in hotspot identification. Results show that equity-aware SPFs can diminish the effects of equity-related variables, including poverty ratio, black ratio, Asian ratio, and the ratio of households without vehicles, on the expected crash frequencies, generating higher PSIs for disadvantaged areas. Based on the results of Wilcoxon signed-rank tests, it is evident that there are significant differences in the rankings of PSIs when equity awareness is considered, especially for disadvantaged areas. This study adds to the literature a new quantitative approach to harmonize equity and effectiveness considerations, empowering more equitable decision-making in safety management, such as allocating resources for safety enhancement.

Analysis of the elderly pedestrian traffic accidents in urban scenarios: the case of the Spanish municipalities

As the elderly population grows, there is a greater concern for their safety on the roads. This is particularly important for elderly pedestrians who are more vulnerable to accidents. In Spain, one of the most aged countries in the world, the elderly accounted for 70% of all pedestrian deaths in 2019. In this study, the focus was on analysing the occurrence of elderly pedestrian-vehicle collisions in Spanish municipalities and how it is related to the built environment. The study used the hurdle negative binomial model to analyse the number of elderly and non-elderly pedestrian accidents per municipality in 2016-2019. The exploratory analysis showed that cities above 50,000 inhabitants were safer for the elderly, and larger provincial capitals had lower elderly pedestrian traffic accident rates. The occurrence of all pedestrian traffic accidents was linked to the socio-demographic features. For elderly pedestrians, land use was found to be influential, with a lower proportion of land covered by manufacturing and service activities linked to a smaller number of accidents. Results showed that improving road safety for older pedestrians may not necessarily compromise the situation for the rest of population. Hence, policymakers should focus on infrastructure improvements adapted to the needs of elderly pedestrians.

Predicting pharmaceutical supply chain disruptions before and during the COVID-19 pandemic

Disruptions to the pharmaceutical supply chain (PSC) have negative implications for patients, motivating their prediction to improve risk mitigation. Although data analytics and machine learning methods have been proposed to support the characterization of probabilities to inform decisions and risk mitigation strategies, their application in the PSC has not been previously described. Further, it is unclear how well these models perform in the presence of emergent events representing deep uncertainty such as the COVID-19 pandemic. This article examines the use of data-driven models to predict PSC disruptions before and during the COVID-19 pandemic. Using data on generic drugs from the pharmacy supply chain division of a Fortune 500 pharmacy benefit management firm, we have developed predictive models based on the naïve Bayes algorithm, where the models predict whether a specific supplier or whether a specific product will experience a supply disruption in the next time period. We find statistically significant changes in the relationships of nearly all variables associated with product supply disruptions during the pandemic, despite pre-pandemic stability. We present results showing how the sensitivity, specificity, and false positive rate of predictive models changed with the onset of the COVID-19 pandemic and show the beneficial effects of regular model updating. The results show that maintaining model sensitivity is more challenging than maintaining specificity and false positive rates. The results provide unique insight into the pandemic's effect on risk prediction within the PSC and provide insight for risk analysts to better understand how surprise events and deep uncertainty affect predictive models.

Investigating the temporal dynamics of motor vehicle collision density patterns in urban road networks - A case study of New York

INTRODUCTION

Motor vehicle collisions are a leading source of mortality and injury on urban highways. From a temporal perspective, the determination of a road segment as being collision-prone over time can fluctuate dramatically, making it difficult for transportation agencies to propose traffic interventions. However, there has been limited research to identify and characterize collision-prone road segments with varying collision density patterns over time.

METHOD

This study proposes an identification and characterization framework that profiles collision-prone roads with various collision density variations. We first employ the spatio-temporal network kernel density estimation (STNKDE) method and time-series clustering to identify road segments with different collision density patterns. Next, we characterize collision-prone road segments based on spatio-temporal information, consequences, vehicle types, and contributing factors to collisions. The proposed method is applied to two-year motor vehicle collision records for New York City.

RESULTS

Seven clusters of road segments with different collision density patterns were identified. Road segments frequently determined as collision-prone were primarily found in Lower Manhattan and the center of the Bronx borough. Furthermore, collisions near road segments that exhibit greater collision densities over time result in more fatalities and injuries, many of which are caused by both human and vehicle factors.

CONCLUSIONS

Collision-prone road segments with various collision density patterns over time have distinct differences in the spatio-temporal domain and the collisions that occur on them.

PRACTICAL APPLICATIONS

The proposed method can help policymakers understand how collision-prone road segments change over time, and can serve as a reference for more targeted traffic treatment.

A spatiotemporal deep learning approach for pedestrian crash risk prediction based on POI trip characteristics and pedestrian exposure intensity

Pedestrians represent a population of vulnerable road users who are directly exposed to complex traffic conditions, thereby increasing their risk of injury or fatality. This study first constructed a multidimensional indicator to quantify pedestrian exposure, considering factors such as Point of Interest (POI) attributes, POI intensity, traffic volume, and pedestrian walkability. Following risk interpolation and feature engineering, a comprehensive data source for risk prediction was formed. Finally, based on risk factors, the VT-NET deep learning network model was proposed, integrating the algorithmic characteristics of the VGG16 deep convolutional neural network and the Transformer deep learning network. The model involved training non-temporal features and temporal features separately. The training dataset incorporated features such as weather conditions, exposure intensity, socioeconomic factors, and the built environment. By employing different training methods for different types of causative feature variables, the VT-NET model analyzed changes in risk features and separately trained temporal and non-temporal risk variables. It was used to generate spatiotemporal grid-level predictions of crash risk across four spatiotemporal scales. The performance of the VT-NET model was assessed, revealing its efficacy in predicting pedestrian crash risks across the study area. The results indicated that areas with concentrated crash risks are primarily located in the city center and persist for several hours. These high-risk areas dissipate during the late night and early morning hours. High-risk areas were also found to cluster in the city center; this clustering behavior was more prominent during weekends compared to weekdays and coincided with commercial zones, public spaces, and educational and medical facilities.

Effect of signal timing on vehicles' near misses at intersections

Driving characteristics often vary between the different states of the signal. During red and yellow phase, drivers tend to speed up and reduce the following distance which in turn increases the possibility of rear end crashes. Intersection safety, therefore, relies on the correct modelling of signal phasing and timing parameters, and how drivers respond to its changes. This paper aims to identify the relationship between surrogate safety measures and signal phasing. Unmanned aerial vehicle (UAV) video data has been used to study a major intersection. Post encroachment time (PET) between vehicles was calculated from the video data as well as speed, heading and relevant signal timing parameters such as all red time, red clearance time, yellow time, etc. Random parameter ordered logit model was used to model the relationship between PET and signal timing parameters. Overall, the results showed that yellow time and red clearance time is positively related to PETs. The model was also able to identify certain signal phases that could be a potential safety hazard and would need to be retimed by considering the PETs. The odds ratios from the models also indicate that increasing the mean yellow and red clearance times by one second can improve the PET levels by 10% and 3%, respectively.

Do factors associated with older pedestrian crash severity differ? A causal factor analysis based on exposure level of pedestrians

OBJECTIVE

Older pedestrians are more likely to have severe or fatal consequences when involved in traffic crashes. Identifying the factors contributing to the severity and possible interdependencies between factors in specific exposure areas is the first step to improving safety. Therefore, examining the causal factors' impact on pedestrian-vehicle crash severity in a given area is vital for formulating effective measures to reduce the risk of pedestrian fatalities and injuries.

METHODS

This study implements the Thiessen polygon algorithm deployed to define older pedestrians' exposure influence area. Enabling trip characteristics and built environment information as exposure index settings for the background of the pedestrian severity causal analysis. Then, structural equation modeling (SEM) was applied to conduct a factor analysis of the crash severity in high- and low-exposure areas. The SEM evaluates latent factors such as driver risk attitude, risky driving behavior, lack of risk perception among older pedestrians, natural environment, adverse road conditions for driving or walking, and vehicle conditions. The SEM crash model also establishes the relationship between each latent factor.

RESULTS

In total, drivers' risky driving behavior (0.270, p < 0.05) in low-exposure areas significantly impacts older pedestrian crash severity more than in high-exposure areas. Lack of risk perception among older pedestrians (0.232, p < 0.05) is the most critical factor promoting crash severity in high-exposure areas. The natural environment (0.634, p < 0.05) in high-exposure areas positively influences older pedestrians' lack of risk perception more than in low-exposure areas.

CONCLUSIONS

Significant group differences (p-values ∼ 0.001-0.049) existed between the causal factors of the high-exposure risk areas and the low-exposure risk factors. Different exposure intervals require detailed scenarios based on the critical risks identified. The crash severity promotion measures in different exposure areas can be focused on according to the critical causes analyzed. Those clues, in turn, can be used by transportation authorities in prioritizing their plans, policies, and programs toward improving the safety and mobility of older pedestrians.

Investigating the Risk Factors Associated with Injury Severity in Pedestrian Crashes in Santiago, Chile

Pedestrians are vulnerable road users that are directly exposed to road traffic crashes with high odds of resulting in serious injuries and fatalities. Therefore, there is a critical need to identify the risk factors associated with injury severity in pedestrian crashes to promote safe and friendly walking environments for pedestrians. This study investigates the risk factors related to pedestrian, crash, and built environment characteristics that contribute to different injury severity levels in pedestrian crashes in Santiago, Chile from a spatial and statistical perspective. First, a GIS kernel density technique was used to identify spatial clusters with high concentrations of pedestrian crash fatalities and severe injuries. Subsequently, partial proportional odds models were developed using the crash dataset for the whole city and the identified spatial clusters to examine and compare the risk factors that significantly affect pedestrian crash injury severity. The model results reveal higher increases in the fatality probability within the spatial clusters for statistically significant contributing factors related to drunk driving, traffic signage disobedience, and imprudence of the pedestrian. The findings may be utilized in the development and implementation of effective public policies and preventive measures to help improve pedestrian safety in Santiago.

Tracking traffic congestion and accidents using social media data: A case study of Shanghai

Traffic congestion and accidents take a toll on commuters' daily experiences and society. Locating the venues prone to congestion and accidents and capturing their perception by public members is invaluable for transport policy-makers. However, few previous methods consider user perception toward the accidents and congestion in finding and profiling the accident- and congestion-prone areas, leaving decision-makers unaware of the subsequent behavior responses and priorities of retrofitting measures. This study develops a framework to identify and characterize the accident- and congestion-prone areas heatedly discussed on social media. First, we use natural language processing and deep learning to detect the accident- and congestion-relevant Chinese microblogs posted on Sina Weibo, a Chinese social media platform. Then a modified Kernel Density Estimation method considering the sentiment of microblogs is employed to find the accident- and congestion-prone regions. The results show that the 'congestion-prone areas' discussed on social media are mainly distributed throughout the historical urban core and the Northwest of Pudong New Area, in reasonably good agreements with actual congestion records. In contrast, the 'accident-prone areas' are primarily found in locations with severe accidents. Finally, the above venues are characterized in spatio-temporal and semantic aspects to understand the nature of the incidents and assess the priority level for mitigation measures. The outcomes can provide a reference for traffic authorities to inform resource allocation and prioritize mitigation measures in future traffic management.

Investigating the fatal pedestrian crash occurrence in urban setup in a developing country using multiple-risk source model

Pedestrian fatalities and injuries are a major public health burden in developing countries. In the safety literature, pedestrian crashes have been modelled predominately using single equation regression models, assuming a single underlying source of risk factors. In contrast, the fatal pedestrian crash counts at a site may be an outcome of multiple sources of risk factors, such as poor road infrastructure, land use type, traffic exposures, and operational parameters, site-specific socio-demographic characteristics, as well as pedestrians' poor risk perception and dangerous crossing behavior, which may be influenced by poor road infrastructure and lack of information, etc. However, these multiple sources are generally overlooked in traditional single equation crash prediction models. In this background, this study postulates, and demonstrates empirically, that the total fatal pedestrian crash counts at the urban road network level may arise from multiple simultaneous and interdependent sources of risk factors, rather than one. Each of these sources may distinctively contribute to the total observed crash count. Intersection-level crash data obtained from the "Kolkata Police", India, is utilized to demonstrate the present modelling methodology. The three-components mixture model and a joint econometric model are developed to predict fatal pedestrian crashes. The study outcomes indicate that the multiple-source risk models perform significantly better than the single equation regression model in terms of prediction ability and goodness-of-fit measures. Moreover, while the single equation model predicts total fatal crash counts for individual sites, the multiple risk source model predicts crash count proportions contributed by each source of risk factors and predicts crashes by a particular source.

Vulnerable road users' crash hotspot identification on multi-lane arterial roads using estimated exposure and considering context classification

This research develops safety performance functions and identifies the crash hotspots based on estimated vulnerable road users' exposure at intersections and along the roadway segments. The study utilized big data including Automated Traffic Signal Performance Measures (ATSPM) data, crowdsourced data (Strava), Closed Circuit Television (CCTV) surveillance camera videos, crash data, traffic information, roadway features, land use attributes, and socio-demographic characteristics. It comprises an extensive comparison between a wide array of statistical and machine learning models that were developed to estimate pedestrian and bike exposure. The results indicated that the XGBoost approach was the best to estimate vulnerable road users' exposure at intersections as well as bike exposure along the roadway segments. Afterwards, the estimated exposure was utilized as input variables to develop crash prediction models that relate different crash types to potential explanatory variables. Negative Binomial approach was followed to develop crash prediction models to be consistent with the Highway Safety Manual. The results show that the exposure variables (i.e., AADT, bike exposure, and the interaction between them) have significant influences on the two types of crashes (i.e., crashes of vulnerable road users at intersections and bike crashes along the segments). Further, the results indicated that the context classification is significantly related to crashes. Based on the developed models, the PSIs were calculated and the hotspots were identified for the two crash types. It was found that hotspots were more likely to be located near the city of Orlando. Coastal roadways were classified as cold categories regarding bike crashes. Further, C4 roadway segments were found to be significantly related to the increase of vulnerable road users' crashes at intersections and bike crashes along the segments.

An accelerated hierarchical Bayesian crash frequency model with accommodation of spatiotemporal interactions

Although spatial and temporal correlations of crash observations have been well addressed in the literature, the interactions between them are rarely studied. This study proposes a Bayesian spatiotemporal interaction (BSTI) approach for crash frequency modeling with an integrated nested Laplace approximation (INLA) method to greatly expedite the Bayesian estimation process. Manhattan, which is the most densely populated urban area of New York City, is selected as the study area. Hexagons are used as the basic geographic units to capture crash, transportation, land use, and demo-economic data from 2013 to 2019. A series of Bayesian models with various spatiotemporal specifications are developed and compared. The BSTI model with Type II interaction, which assumes that the structured temporal random effect interacts with the unstructured spatial random effect is found to outperform the others in terms of goodness-of-fit and the ability to reduce the dependency of residuals. It is also found that the unobserved heterogeneity is mostly attributed to the spatial effects instead of temporal effects. In addition, the BSTI Type II model also yields the lowest predictive error when the last year's data are used as the test set. The proposed BSTI approach can potentially advance safety analytics by achieving high prediction accuracy and computational efficiency while maintaining its interpretability on the effects of contributing factors and the unobserved heterogeneity.

Fusing crash data and surrogate safety measures for safety assessment: Development of a structural equation model with conditional autoregressive spatial effect and random parameters

Most existing efforts to assess safety performance require sufficient crash data, which generally takes a few years to collect and suffers from certain limitations (such as long data collection time, under-reporting issue and so on). Alternatively, the surrogate safety measure (SSMs) based approach that can assess traffic safety by capturing the more frequent "near-crash" situations have been developed, but it is criticized for the potential sampling and measurement errors. This study proposes a new safety performance measure-Risk Status (RS), by fusing crash data and SSMs. Real-world connected vehicle data collected in the Safety Pilot Model Deployment (SPMD) project in Ann Arbor, Michigan is used to extract SSMs. With RS treated as a latent variable, a structural equation model with conditional autoregressive spatial effect and corridor-level random parameters is developed to model the interrelationship among RS, crash frequency, risk identified by SSMs, and contributing factors. The modeling results confirm the proposed interrelationship and the necessity to account for both spatial autocorrelation and unobserved heterogeneity. RS can integrate both crash frequency and SSMs together while controlling for observed and unobserved factors. RS is found to be a more reliable criterion for safety assessment in an implementation case of hotspot identification.

Using bus critical driving events as surrogate safety measures for pedestrian and bicycle crashes based on GPS trajectory data

Pedestrian and bicycle safety is a key component in traffic safety studies. Various studies were conducted to address pedestrian and bicycle safety issues for intersections, road segments, etc. However, only a few studies investigated pedestrian and bicycle safety for bus stops, which usually have a relatively larger volume of pedestrians and bicyclists. Moreover, traditional reactive safety approaches require a significant number of historical crashes, while pedestrian and bicycle crashes are usually rare events. Alternatively, surrogate safety measures could proactively evaluate traffic safety status when crash data are rare or unavailable. This paper utilized critical bus driving events extracted from GPS trajectory data as pedestrian and bicycle surrogate safety measures for bus stops. A city-wide trajectory data from Orlando, Florida was used, which contains around 300 buses, 6,700,000 GPS records, and 1300 bus stops. Three critical driving events were identified based on the buses' acceleration rates and stop time; hard acceleration, hard deceleration, and long stop. The relationships between critical driving events and crashes were examined using Spearman's rank correlation coefficient. All three events were positively correlated with pedestrian and bicycle crashes. Long stop event has the highest correlation coefficient, followed by hard acceleration and hard deceleration. A Bayesian negative binomial model incorporating spatial correlation (Bayesian NB-CAR) was built to estimate the pedestrian and bicycle crash frequency using the generated events. The results were consistent with the correlation estimation. For example, hard acceleration and long stop events were both positively related to pedestrian and bicycle crashes. Moreover, model evaluation results indicated that the proposed Bayesian NB-CAR outperformed the standard Bayesian negative binomial model with lower Watanabe-Akaike Information Criterion (WAIC) and Deviance Information Criteria (DIC) values. In conclusion, this paper suggests the use of critical bus driving events as surrogate safety measures for pedestrian and bicycle crashes, which could be implemented in a proactive traffic safety management system.

Towards activity-based exposure measures in spatial analysis of pedestrian-motor vehicle crashes

BACKGROUND

Although numerous efforts have been devoted to exploring the effects of area-wide factors on the frequency of pedestrian crashes in neighborhoods over the past two decades, existing studies have largely failed to provide a full picture of the factors that contribute to the incidence of zonal pedestrian crashes, due to the unavailability of reliable exposure data and use of less sound analytical methods.

METHODS

Based on a crowdsourced dataset in Hong Kong, we first proposed a procedure to extract pedestrian trajectories from travel-diary survey data. We then aggregated these data to 209 neighborhoods and developed a Bayesian spatially varying coefficients model to investigate the spatially non-stationary relationships between the number of pedestrian-motor vehicle (PMV) crashes and related risk factors. To dissect the role of pedestrian exposure, the estimated coefficients of models with population, walking trips, walking time, and walking distance as the measure of pedestrian exposure were presented and compared.

RESULTS

Our results indicated substantial inconsistencies in the effects of several risk factors between the models of population and activity-based exposure measures. The model using walking trips as the measure of pedestrian exposure had the best goodness-of-fit. We also provided new insights that in addition to the unstructured variability, heterogeneity in the effects of explanatory variables on the frequency of PMV crashes could also arise from the spatially correlated effects. After adjusting for vehicle volume and pedestrian activity, road density, intersection density, bus stop density, and the number of parking lots were found to be positively associated with PMV crash frequency, whereas the percentage of motorways and median monthly income had negative associations with the risk of PMV crashes.

CONCLUSIONS

The use of population or population density as a surrogate for pedestrian exposure when modeling the frequency of zonal pedestrian crashes is expected to produce biased estimations and invalid inferences. Spatial heterogeneity should also not be negligible when modeling pedestrian crashes involving contiguous spatial units.

An ensemble-learning method for potential traffic hotspots detection on heterogeneous spatio-temporal data in highway domain

Inter-city highway plays an important role in modern urban life and generates sensory data with spatio-temporal characteristics. Its current situation and future trends are valuable for vehicles guidance and transportation security management. As a domain routine analysis, daily detection of traffic hotspots faces challenges in efficiency and precision, because huge data deteriorates processing latency and many correlative factors cannot be fully considered. In this paper, an ensemble-learning based method for potential traffic hotspots detection is proposed. Considering time, space, meteorology, and calendar conditions, daily traffic volume is modeled on heterogeneous data, and trends predictive error can be reduced through gradient boosting regression technology. Using real-world data from one Chinese provincial highway, extensive experiments and case studies show our methods with second-level executive latency with a distinct improvement in predictive precision.

Risk Analysis: Celebrating the Accomplishments and Embracing Ongoing Challenges

As part of the celebration of the 40th anniversary of the Society for Risk Analysis and Risk Analysis: An International Journal, this essay reviews the 10 most important accomplishments of risk analysis from 1980 to 2010, outlines major accomplishments in three major categories from 2011 to 2019, discusses how editors circulate authors' accomplishments, and proposes 10 major risk-related challenges for 2020-2030. Authors conclude that the next decade will severely test the field of risk analysis.

Review on big data applications in safety research of intelligent transportation systems and connected/automated vehicles

The era of Big Data has arrived. Recently, under the environment of intelligent transportation systems (ITS) and connected/automated vehicles (CAV), Big Data has been applied in various fields in transportation including traffic safety. In this study, we review recent research studies that employed Big Data to analyze traffic safety under the environment of ITS and CAV. The particular topics include crash detection or prediction, discovery of contributing factors to crashes, driving behavior analysis, crash hotspot identification, etc. From the reviewed studies, employing advanced analytics for Big Data has a great potential for understanding and enhancing traffic safety. Big Data application in traffic safety integrates and processes massive multi-source data, breaks through the limitations of the traditional data analytics, and discovers and solves the problems, which cannot be solved by the traditional safety analytics. Lastly, suggestions are provided for future Big Data safety analytics under the environment of ITS and CAV.

Modeling crash risk of horizontal curves using large-scale auto-extracted roadway geometry data

Highway horizontal curves (H-curves) provide a smooth transition between two tangent sections of roadways. They allow vehicles to adjust their travel directions gradually. However, the geometry changes of the highway sections with H-curves often raise safety concerns. In order to deploy effective safety countermeasures, a critical task is to understand the risk factors associated with H-curves. Existing studies have made efforts to probe the safety issues associated with H-curves, whereas they were limited to relatively small-scale examinations because of the challenges in identifying H-curves from large road networks. In addition, due to the lack of well-archived traffic and roadway information, gathering other data associated with the H-curves is also difficult. Regarding to these gaps, this study aims to leverage open-source data to analyze the crash risk of highway sections with H-curves. In particular, the present study highlights itself from two main aspects: (i) a H-curve extraction tool was developed to facilitate large-scale curve data collection through the analytics of different open source data; and (ii) a crash modeling framework was developed to quantify H-curve crash risk. A case study based on a statewide road network was performed to test the developed crash risk models with the collected curve data. The results show the opportunities of using the developed tool for large-scale data collection and analyze the safety impacts of H-curve geometric properties, elevation change, traffic exposure, among others. Findings of this study provide insights into the improvement of H-curve data collection and safety evaluation.

Safety of micro-mobility: Analysis of E-Scooter crashes by mining news reports

Dockless electric scooters (E-Scooters) have emerged as a popular micro-mobility mode for urban transportation. This new form of mobility offers riders a flexible option for massive first-/last-mile trips. Despite the popularity, the limited regulations of E-Scooters raise numerous safety concerns among the public and agencies. Due to the unavailability of well-archived crash data, it is difficult to understand and characterize current state quo of E-Scooter-involved crashes. This paper aims to shorten the gap by analyzing a set of reported crash data to describe the patterns of crashes related to E-Scooter use. Specifically, massive media reports were searched and investigated for constructing the crash dataset. Key crash elements such as rider demographics, crash type, and location were organized in an information table for analysis. From 2017 to 2019, there were 169 E-Scooter-involved crashes identified from the news reports across the country. Through the descriptive analysis and cross tabulation analysis, the distinct characteristics of these reported crashes were highlighted. Overall, there was a growing trend for the reported E-Scooter-involved crashes unevenly distributed among the States. The distribution of the crashes across different groups of users, facilities, time periods, and severity levels also showed skewed patterns toward a subset of categories. The quantitative analyses also provide some supportive evidences for warranting the discussion on key issues, including helmet use, riding under influence (RUI), vulnerable riders, and data deficiency. This study highlights the importance of public awareness and timely developing safety countermeasures to mitigate crashes involving E-Scooters.

Exploring the Spatial-Temporal Relationship between Rainfall and Traffic Flow: A Case Study of Brisbane, Australia

The impact of inclement weather on traffic flow has been extensively studied in the literature. However, little research has unveiled how local weather conditions affect real-time traffic flows both spatially and temporally. By analysing the real-time traffic flow data of Traffic Signal Controllers (TSCs) and weather information in Brisbane, Australia, this paper aims to explore weather’s impact on traffic flow, more specifically, rainfall’s impact on traffic flow. A suite of analytic methods has been applied, including the space-time cube, time-series clustering, and regression models at three different levels (i.e., comprehensive, location-specific, and aggregate). Our results reveal that rainfall would induce a change of the traffic flow temporally (on weekdays, Saturday, and Sunday and at various periods on each day) and spatially (in the transportation network). Particularly, our results consistently show that the traffic flow would increase on wet days, especially on weekdays, and that the urban inner space, such as the central business district (CBD), is more likely to be impacted by inclement weather compared with other suburbs. Such results could be used by traffic operators to better manage traffic in response to rainfall. The findings could also help transport planners and policy analysts to identify the key transport corridors that are most susceptible to traffic shifts in different weather conditions and establish more weather-resilient transport infrastructures accordingly.

A review of spatial approaches in road safety

Spatial analyses of crashes have been adopted in road safety for decades in order to determine how crashes are affected by neighboring locations, how the influence of parameters varies spatially and which locations warrant interventions more urgently. The aim of the present research is to critically review the existing literature on different spatial approaches through which researchers handle the dimension of space in its various aspects in their studies and analyses. Specifically, the use of different areal unit levels in spatial road safety studies is investigated, different modelling approaches are discussed, and the corresponding study design characteristics are summarized in respective tables including traffic, road environment and area parameters and spatial aggregation approaches. Developments in famous issues in spatial analysis such as the boundary problem, the modifiable areal unit problem and spatial proximity structures are also discussed. Studies focusing on spatially analyzing vulnerable road users are reviewed as well. Regarding spatial models, the application, advantages and disadvantages of various functional/econometric approaches, Bayesian models and machine learning methods are discussed. Based on the reviewed studies, present challenges and future research directions are determined.

Intersections and Non-Intersections: A Protocol for Identifying Pedestrian Crash Risk Locations in GIS

Intersection and non-intersection locations are commonly used as spatial units of analysis for modeling pedestrian crashes. While both location types have been previously studied, comparing results is difficult given the different data and methods used to identify crash-risk locations. In this study, a systematic and replicable protocol was developed in GIS (Geographic Information System) to create a consistent spatial unit of analysis for use in pedestrian crash modelling. Four publicly accessible datasets were used to identify unique intersection and non-intersection locations: Roadway intersection points, roadway lanes, legal speed limits, and pedestrian crash records. Two algorithms were developed and tested using five search radii (ranging from 20 to 100 m) to assess the protocol reliability. The algorithms, which were designed to identify crash-risk locations at intersection and non-intersection areas detected 87.2% of the pedestrian crash locations (r: 20 m). Agreement rates between algorithm results and the crash data were 94.1% for intersection and 98.0% for non-intersection locations, respectively. The buffer size of 20 m generally showed the highest performance in the analyses. The present protocol offered an efficient and reliable method to create spatial analysis units for pedestrian crash modeling. It provided researchers a cost-effective method to identify unique intersection and non-intersection locations. Additional search radii should be tested in future studies to refine the capture of crash-risk locations.

A New Methodology for Before-After Safety Assessment Using Survival Analysis and Longitudinal Data

The widely used empirical Bayes (EB) and full Bayes (FB) methods for before-after safety assessment are sometimes limited because of the extensive data needs from additional reference sites. To address this issue, this study proposes a novel before-after safety evaluation methodology based on survival analysis and longitudinal data as an alternative to the EB/FB method. A Bayesian survival analysis (SARE) model with a random effect term to address the unobserved heterogeneity across sites is developed. The proposed survival analysis method is validated through a simulation study before its application. Subsequently, the SARE model is developed in a case study to evaluate the safety effectiveness of a recent red-light-running photo enforcement program in New Jersey. As demonstrated in the simulation and the case study, the survival analysis can provide valid estimates using only data from treated sites, and thus its results will not be affected by the selection of defective or insufficient reference sites. In addition, the proposed approach can take into account the censored data generated due to the transition from the before period to the after period, which has not been previously explored in the literature. Using individual crashes as units of analysis, survival analysis can incorporate longitudinal covariates such as the traffic volume and weather variation, and thus can explicitly account for the potential temporal heterogeneity.

A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data

The primary objective of this study is to investigate how the deep learning approach contributes to citywide short-term crash risk prediction by leveraging multi-source datasets. This study uses data collected from Manhattan in New York City to illustrate the procedure. The following multiple datasets are collected: crash data, large-scale taxi GPS data, road network attributes, land use features, population data and weather data. A spatiotemporal convolutional long short-term memory network (STCL-Net) is proposed for predicting the citywide short-term crash risk. A total of nine prediction tasks are conducted and compared, including weekly, daily and hourly models with 8 × 3, 15 × 5 and 30 × 10 grids, respectively. The results suggest that the prediction performance of the proposed model decreases as the spatiotemporal resolution of prediction task increases. Moreover, four commonly-used econometric models, and four state-of-the-art machine-learning models are selected as benchmark methods to compare with the proposed STCL-Net for all the crash risk prediction tasks. The comparative analyses suggest that in general the proposed STCL-Net outperforms the benchmark methods for different crash risk prediction tasks in terms of higher prediction accuracy rate and lower false alarm rate. The results verify that the proposed spatiotemporal deep learning approach performs better at capturing the spatiotemporal characteristics for the citywide short-term crash risk prediction. In addition, the comparative analyses also reveal that econometric models perform better than machine-learning models in weekly crash risk prediction tasks, while they exhibit worse results than machine-learning models in daily crash risk prediction tasks. The results can potentially guide transportation safety engineers to select appropriate methods for different crash risk prediction tasks.

A multivariate spatial approach to model crash counts by injury severity

Conventional safety models rely on the assumption of independence of crash data, which is frequently violated. This study develops a novel multivariate conditional autoregressive (MVCAR) model to account for the spatial autocorrelation of neighboring sites and the inherent correlation across different crash types. Manhattan, which is the most densely populated urban area of New York City, is used as the study area. Census tracts are used as the basic geographic units to capture crash, transportation, land use, and demo-economic data. The specification of the proposed multivariate model allows for jointly modeling counts of various crash types that are classified according to injury severity. Results of Moran's I tests show the ability of the MVCAR model to capture the multivariate spatial autocorrelation among different crash types. The MVCAR model is found to outperform the others by presenting the lowest deviance information criterion (DIC) value. It is also found that the unobserved heterogeneity was mostly attributed to spatial factors instead of non-spatial ones and there is a strong shared geographical pattern of risk among different crash types.

Bayesian approach to model pedestrian crashes at signalized intersections with measurement errors in exposure

This study intended to identify the potential factors contributing to the occurrence of pedestrian crashes at signalized intersections in a densely populated city, based on a comprehensive dataset of 898 pedestrian crashes at 262 signalized intersections during 2010-2012 in Hong Kong. The detailed geometric design, traffic characteristics, signal control, built environment, along with the vehicle and pedestrian volumes were elaborately collected. A Bayesian measurement errors model was introduced as an alternative method to explicitly account for the uncertainties in volume data. To highlight the role played by exposure, models with and without pedestrian volume were estimated and compared. The results indicated that the omission of pedestrian volume in pedestrian crash frequency models would lead to reduced goodness-of-fit, biased parameter estimates, and incorrect inferences. Our empirical analysis demonstrated the existence of moderate uncertainties in pedestrian and vehicle volumes. Six variables were found to have a significant association with the number of pedestrian crashes at signalized intersections. The number of crossing pedestrians, the number of passing vehicles, the presence of curb parking, and the presence of ground-floor shops were positively related with pedestrian crash frequency, whereas the presence of playgrounds near intersections had a negative effect on pedestrian crash occurrences. Specifically, the presence of exclusive pedestrian signals for all crosswalks was found to significantly reduce the risk of pedestrian crashes by 43%. The present study is expected to shed more light on a deeper understanding of the environmental determinants of pedestrian crashes.

Identifying traffic accident black spots with Poisson-Tweedie models

This paper aims at the identification of black spots for traffic accidents, i.e. locations with accident counts beyond what is usual for similar locations, using spatially and temporally aggregated hospital records from Funen, Denmark. Specifically, we apply an autoregressive Poisson-Tweedie model, which covers a wide range of discrete distributions and handles zero-inflation as well as overdispersion. The estimated power parameter of the model was 1.6 (SE=0.06) suggesting a distribution close to the Pólya-Aeppli distribution. We identified nine black spots consistently standing out in all six considered calendar years and calculated by simulations a probability of p=0.03 for these to be chance findings. Altogether, our results recommend these sites for further investigation and suggest that our simple approach could play a role in future area based traffic accident prevention planning.

Advances in Risk Analysis with Big Data

With cloud computing, Internet-of-things, wireless sensors, social media, fast storage and retrieval, etc., organizations and enterprises have access to unprecedented amounts and varieties of data. Current risk analysis methodology and applications are experiencing related advances and breakthroughs. For example, highway operations data are readily available, and making use of them reduces risks of traffic crashes and travel delays. Massive data of financial and enterprise systems support decision making under risk by individuals, industries, regulators, etc. In this introductory article, we first discuss the meaning of big data for risk analysis. We then examine recent advances in risk analysis with big data in several topic areas. For each area, we identify and introduce the relevant articles that are featured in the special issue. We conclude with a discussion on future research opportunities.