Decline in Traffic Congestion Increased Crash Severity in the Wake of COVID-19.

Highway fatalities are a leading cause of death in the U.S. and other industrialized countries. Using highly detailed crash, speed, and flow data, we show highway travel and motor vehicle crashes fell substantially in California during the response to the COVID-19 pandemic. However, we also show the frequency of severe crashes increased owing to lower traffic congestion and higher highway speeds. This "speed effect" is largest in counties with high pre-existing levels of congestion, and we show it partially or completely offsets the "VMT effect" of reduced vehicle miles traveled on total fatalities. During the first eleven weeks of the COVID-19 response, highway driving decreased by approximately 22% and total crashes decreased by 49%. While average speeds increased by a modest 2 to 3 mph across the state, they increased between 10 and 15 mph in several counties. The proportion of severe crashes increased nearly 5 percentage points, or 25%. While fatalities decreased initially following restrictions, increased speeds mitigated the effect of lower vehicle miles traveled on fatalities, yielding little to no reduction in fatalities later in the COVID period.

A Bibliometric Analysis and Benchmark of Machine Learning and AutoML in Crash Severity Prediction: The Case Study of Three Colombian Cities.

Traffic accidents are of worldwide concern, as they are one of the leading causes of death globally. One policy designed to cope with them is the design and deployment of road safety systems. These aim to predict crashes based on historical records, provided by new Internet of Things (IoT) technologies, to enhance traffic flow management and promote safer roads. Increasing data availability has helped machine learning (ML) to address the prediction of crashes and their severity. The literature reports numerous contributions regarding survey papers, experimental comparisons of various techniques, and the design of new methods at the point where crash severity prediction (CSP) and ML converge. Despite such progress, and as far as we know, there are no comprehensive research articles that theoretically and practically approach the model selection problem (MSP) in CSP. Thus, this paper introduces a bibliometric analysis and experimental benchmark of ML and automated machine learning (AutoML) as a suitable approach to automatically address the MSP in CSP. Firstly, 2318 bibliographic references were consulted to identify relevant authors, trending topics, keywords evolution, and the most common ML methods used in related-case studies, which revealed an opportunity for the use AutoML in the transportation field. Then, we compared AutoML (AutoGluon, Auto-sklearn, TPOT) and ML (CatBoost, Decision Tree, Extra Trees, Gradient Boosting, Gaussian Naive Bayes, Light Gradient Boosting Machine, Random Forest) methods in three case studies using open data portals belonging to the cities of Medellín, Bogotá, and Bucaramanga in Colombia. Our experimentation reveals that AutoGluon and CatBoost are competitive and robust ML approaches to deal with various CSP problems. In addition, we concluded that general-purpose AutoML effectively supports the MSP in CSP without developing domain-focused AutoML methods for this supervised learning problem. Finally, based on the results obtained, we introduce challenges and research opportunities that the community should explore to enhance the contributions that ML and AutoML can bring to CSP and other transportation areas.

Risk factors associated with truck-involved fatal crash severity: Analyzing their impact for different groups of truck drivers.

INTRODUCTION: Fatal crashes that include at least one fatality of an occupant within 30 days of the crash cause large numbers of injured persons and property losses, especially when a truck is involved. METHOD: To better understand the underlying effects of truck-driver-related characteristics in fatal crashes, a five-year (from 2012 to 2016) dataset from the Fatality Analysis Reporting System (FARS) was used for analysis. Based on demographic attributes, driving violation behavior, crash histories, and conviction records of truck drivers, a latent class clustering analysis was applied to classify truck drivers into three groups, namely, ''middle-aged and elderly drivers with low risk of driving violations and high historical crash records," ''drivers with high risk of driving violations and high historical crash records," and ''middle-aged drivers with no driving violations and conviction records." Next, equivalent fatalities were used to scale fatal crash severities into three levels. Subsequently, a partial proportional odds (PPO) model for each driver group was developed to identify the risk factors associated with the crash severity. Results' Conclusions: The model estimation results showed that the risk factors, as well as their impacts on different driver groups, were different. Adverse weather conditions, rural areas, curved alignments, tractor-trailer units, heavier weights and various collision manners were significantly associated with the crash severities in all driver groups, whereas driving violation behaviors such as driving under the influence of alcohol or drugs, fatigue, or carelessness were significantly associated with the high-risk group only, and fewer risk factors and minor marginal effects were identified for the low-risk groups. Practical Applications: Corresponding countermeasures for specific truck driver groups are proposed. And drivers with high risk of driving violations and high historical crash records should be more concerned.

An exploratory analysis of factors associated with traffic crashes severity in Cartagena, Colombia.

Traffic fatalities are the second cause of violent deaths in Colombia. However, due to the signing of the peace agreement and the growing number of fatalities in road crashes, it is possible that soon traffic fatalities will be the primary cause of violent deaths in the country, particularly in urban areas. This study is an exploratory analysis focused on identifying the main factors associated with the severity of traffic crashes in urban areas, using Cartagena as a case study. We analyzed three levels of crash severity, namely fatal, injury, and property-damage-only, considering factors in several different dimensions: victim, vehicle, road infrastructure, traffic and control, day and time, and environmental factors. A modeling approach based on multinomial ordered discrete models was used to properly identify the main factors associated with the severity levels. We found that the probability of fatal accidents is higher on streets with speed limits over 40 km/h, and that males and people aged 60 years or older are the victims with the most significant risk of fatal crashes. Motorcycles were also identified as vehicles with the highest probability of fatal crashes in the city. We showed that the probability of fatal crashes occurring is higher on streets where pedestrian bridges, traffic lights, and crosswalks are present. These findings are worthy because, in Colombia and other developing countries, the authorities normally expect to reduce the probability of fatal accidents through investments in pedestrian bridges, signaling devices, and crosswalk markings. However, according to our results, it possibly will not occur unless further countermeasures are taken. Based on these findings, reducing speed limits, operational improvements at signalized intersections, zero tolerance for traffic violations related to pedestrians, an awareness campaign on pedestrian safety focused on males and people aged 60 or older, and improving motorcycle safety are the countermeasures we proposed. Furthermore, as the authorities make significant efforts to investing in pedestrian bridges, we propose a further investigation into the traffic crashes in streets where there is this infrastructure since more severe events occur near them.