Urban micromobility represents a significant shift towards sustainable cities, underscoring the paramount importance of its safety. With the surge in micromobility adoption, collisions involving micromobility devices, such as bicycles and e-scooters, have surged in recent years. The second most common crash type involving these vehicles is one that only involves a micromobility vehicle (single micromobility crashes). This study analyzed 6030 single micromobility crashes that occurred in Spanish urban areas from 2016 to 2020. The Random Forest methodology was applied to create a classification model for the purpose of characterizing these crashes, predicting their injury severity, and identifying the primary influencing factors. To address the issue of imbalanced data, resulting from the relatively smaller dataset of fatal and seriously injured crashes compared to slightly injured ones, the Synthetic Minority Oversampling Technique (SMOTE) was applied.

The strong rise in modes of travel commonly referred to as micromobility has changed the mobility patterns and lifestyles in cities worldwide, especially after the COVID-19 pandemic. It has led to a significant increase in the number of crashes involving these types of vehicles, especially bicycles and stand-up e-scooters. The risk of crashes is higher at intersections where motor-vehicles perform a turning maneuver crossing a bike lane. The consequences of a passenger car-to-micromobility vehicle side-impact crashes, considering both bicycle and e-scooter, were studied based on the results of the simulation of several scenarios with PC-Crash software. Two injury criteria were applied: Head Injury Criterion (HIC₁₅) and 3 ms chest acceleration criterion. When motor-vehicle speed is lower than 50 km/h, the 3 ms chest acceleration never exceeds the 60 g threshold. However, at 50 km/h, it is close to 50 g in the case of e-scooter rides. At this speed, HIC₁₅ is considerably greater than 1000, both for bicycles and for e-scooters, and the safety margin of 700 is exceeded at 45 km/h for e-scooters. In case of motor vehicle-to-micromobility vehicle side-impact crash, riding a bicycle is safer than riding an e-scooter since the observed HIC₁₅ experienced by the cyclists is lower than that experienced by the e-scooter rider when motor vehicle speed is greater than 30 km/h. To reduce micromobility users injury risk at intersections, motor vehicle speed limit should be equal or lower than 40 km/h. At this impact speed, the activation of hood or bumper airbags could be justified.

The growth of micromobility transport in cities has created a new mobility paradigm, but this has also resulted in increased traffic conflicts and collisions. This research focuses on understanding the impacts of micromobility vehicles on pedestrian injury severity in urban areas of Spain between 2016 and 2021. The Random Forest classification model was used to identify the most significant factors and their combinations affecting pedestrian injury severity. To address the issue of unbalanced data, the synthetic minority oversampling technique was employed. The findings indicate that pedestrians’ age, specifically those 70 years or older, is the most important variable in determining injury severity. Additionally, collisions at junctions or on weekends are associated with worse outcomes for pedestrians. The results highlight the combined influence of multiple factors, including offenses and distractions by micromobility users and pedestrians. These factors are more prevalent among younger micromobility users and those riding for leisure or on weekends. To enhance micromobility road safety and reduce pedestrian injuries, separating micromobility traffic from pedestrian areas is recommended, restricting micromobility vehicle use on sidewalks, providing training and information to micromobility users, conducting road safety campaigns, increasing enforcement measures, and incorporating buffer zones in bike lanes near on-street parking.

Extracting driver collision patterns by gender and age regarding offences, collision type and injury severity is very useful in road safety, providing a better understanding on behavior of the different driver groups. Self-Organizing Map (SOM) is the tool proposed for distributing and projecting 145,904 drivers according to 8 offence variables on a 2D map. Thus, drivers who are close in the original 8D space (one dimension per offence variable), will remain so in the projected one (2D). Multivariate driving and collision patterns are explored to support the development of future measures to improve road safety. Tests of proportions are used for shedding light on clusters where driver offence is present. Finally, the SOM results were compared for validation with those of the standard K-Means clustering technique. The results show that the characteristics of road crashes and the severity of injuries depend jointly, i.e., in multivariate (pattern) terms, on gender, age, type of collisions and offences. There are relevant multivariate driver behavior differences in both the type of collisions (and therefore their severity) and the type and number of offences with regard to gender and age of the driver. This research unveils different multivariate driver behavior patterns, providing information about their relative importance (proportion), which helps in road policy decision making in terms of development of prevention measures. The results help in decision making through a potentially better allocation of resources as carried out by road safety regulating offices such as the Spanish Traffic General Directorate (Dirección General de Tráfico, DGT).

An accurate estimation of exposure is essential for road collision rate estimation, which is key when evaluating the impact of road safety measures. The quasi-induced exposure method was developed to estimate relative exposure for different driver groups based on its main hypothesis: the not-at-fault drivers involved in two-vehicle collisions are taken as a random sample of driver populations. Liability assignment is thus crucial in this method to identify not-at-fault drivers, but often no liability labels are given in collision records, so unsupervised analysis tools are required. To date, most researchers consider only driver and speed offences in liability assignment, but an open question is if more information could be added. To this end, in this paper, the visual clustering technique of self-organizing maps (SOM) has been applied to better understand the multivariate structure in the data, to find out the most important variables for driver liability, analyzing their influence, and to identify relevant liability patterns. The results show that alcohol/drug use could be influential on liability and further analysis is required for disability and sudden illness. More information has been used, given that a larger proportion of the data was considered. SOM thus appears as a promising tool for liability assessment.