Aug 2026· Stochastic environmental research and risk assessment (Print)· Vol 40· 0 citations· 57 references
Abstract
Historically, mountain activities have been associated to accidents, injuries and fatalities. The spatial and temporal context, however, has been largely neglected, with most studies focusing on proximal causes of accidents. The objective of the present study is to analyse the effects of spatial and temporal covariables on the distribution of mountain accidents in a specific area over a span of 11 years. The current dataset includes 572 rescues on Montserrat Natural Protected Area between 2011 and 2021 and comprises 249 climbing rescues and 310 hiking rescues. We assume that mountain accidents follow a Log-Gaussian Cox Process (LGCP) and we consider an empirical analysis of the first-order characteristics. Then we propose a model in which the conditional intensity of the point process depends on some specific spatial and temporal covariables affecting the distribution of this space-time point pattern. We use the inhomogeneous spatio-temporal K-function to estimate second-order properties. Finally, we model the residual spatio-temporal variation as a stochastic process using a space-time covariance function under a separable space-time structure, and we conduct a risk analysis based on the resulting full LGCP through the Value-at-Risk. The results indicate that rescues are clustered over short distances, typically below 100–300 m. Spatial and temporal predictors differ across activities, while risk remains consistently concentrated in specific areas throughout the study period. Overall, the full LGCP model shows a good fit and is able to generate simulations consistent with the observed data.
This study presents a comprehensive multidimensional analysis of pedestrian accidents in Amman, Jordan, from 2014 to 2023. By integrating spatial, temporal, and statistical techniques, the research identifies critical risk patterns to inform evidence-based safety interventions. Characterizing a decade-long database of 14,821 cases, the study utilizes radar graphs, Kernel Density Estimation (KDE), and DBSCAN cluster analysis to delineate high-risk zones and temporal peaks. Temporal findings indicate that Thursdays recorded the highest accident frequency (2382 cases), with peak occurrences between 17:00 and 23:00. Spatial clustering identified five significant high-risk zones, with Central Amman emerging as the primary critical area. The study’s novelty lies in being the first in the Jordanian context to bridge accident frequency with severity mechanisms by integrating advanced spatial clustering and KDE with a robust Ordered Logit Model. Severity analysis reveals that while 59.34% of incidents resulted in minimal injuries, fatalities accounted for 5.02%. The model demonstrates that injury outcomes are systematically associated with traffic dynamics and behavior rather than environmental factors. Speed-related driver error was identified as the strongest predictor of severe outcomes (OR = 81.3). Significant dependencies were confirmed between vehicle category and road type (χ2 = 2182.20, p < 0.001), lighting and road surface (χ2 = 76.21, p < 0.001), and vehicle type and lighting (χ2 = 148.52, p < 0.001). The study proposes a multi-layered framework combining site-specific nodal improvements with corridor-level strategies to enhance urban safety in Amman City.
Haitham A. Al Hasanat, Omar Alharasees, Lafee Alshamaileh et al.· ISPRS International Journal...· 0 citations
Road traffic accidents pose a significant threat to life and property. However, the multitude of contributing factors makes it challenging to pinpoint the most critical ones, thereby hindering effective prevention strategies. Therefore, this study conducts relevant work using the UK Department for Transport’s 2019 road traffic accident datasets. To investigate the distribution characteristics of accidents across various dimensions (person, vehicle, road, environment, and accident configuration), we first preprocessed the data. Missing values were imputed using a chained random forest-based multiple imputation method. To identify key contributing factors, we employed an integrated approach combining Bayesian-optimized random forest, Cramér’s V correlation test, K-modes clustering, and frequency statistics. This framework enabled the exploratory identification of potential high-risk scenarios for both non-operating and passenger vehicles. Subsequently, we applied a constraint-based Apriori algorithm to analyze correlations across these dimensions and temporal factors, revealing significant associations between accident severity and the examined attributes. Finally, a Bayesian-optimized LightGBM model was built to predict accident risk levels. External validation using the 2022 UK dataset, combined with interpretive analysis, confirmed the model’s strong generalization ability.
Ziyan Zhang, Zhenfei Zhan, Rongjie Mao et al.· Vehicles· 0 citations
This study analyzes road traffic accident risk in Tanzania and introduces a composite Regional Road Accident Risk Index (RARI), defined as accidents per 100 km of road, to compare regional risk and assess progress toward SDG 3.6. A multi-method approach was used: national traffic fatality trends from 2000–2022 were modeled using ARIMA forecasting to 2030; a five-year regional panel of 30 regions from 2018–2022 was examined using fixed-effects Poisson regression; and spatial clustering of RARI values was assessed using GIS and Global Moran’s I. Results show that official fatalities declined markedly from the mid-2010s to 2020 but rose again in 2022–2023, suggesting that Tanzania is unlikely to sustain progress toward the SDG target without renewed interventions. Regression findings indicate that driver-related factors, especially speeding, reckless driving, and negligence, are the strongest predictors of accident counts, while vehicle defects and alcohol-related factors also increase risk. RARI reveals substantial regional disparities, with the national average close to one accident per 100 km annually, the highest-risk urban region reaching about 2.5 accidents per 100 km, and the lowest-risk regions around 0.3 accidents per 100 km. Spatial analysis confirms significant clustering, with high-risk areas concentrated around major urban centers and trunk highways. The study is limited by likely under-reporting in police data, lack of vehicle-kilometres-travelled data, and the short regional panel. Nevertheless, the combined forecasting, regression, and spatial approach provides actionable evidence for prioritizing enforcement, infrastructure improvements, vehicle safety checks, and protection of vulnerable road users in high-risk regions.
S. Hamisi· Journal of Environment, Clim...· 0 citations
Aiming at the problem of insufficient modeling of spatio-temporal heterogeneity in road traffic accident prediction, a dual task machine learning framework integrating geographical environment, location attributes and time periodicity is proposed. The dataset used in this study was derived from traffic accident records of Nanchang during 2019–2023. Firstly, geographical identifiers are generated by rounding and aggregating latitude and longitude coordinates. At the same time, the location type is processed by a one-hot encoding, so as to carry out spatial clustering analysis of accident hotspots. Compared with the North-South pattern, the contribution of geographical features shows a strong East-West trend. The kernel density heatmap identified Zone A and zone B as dual core high-risk areas. Secondly, the sinusoidal/cosine function is used to encode the time feature circularly, which effectively captures the daily change of the accident. The quantitative analysis of random forest regression model showed that time characteristics accounted for 89.2% of the variance of accident frequency interpretation, significantly exceeding the contribution of geographical factors (10.2%) and location attributes (0.6%). After hyperparameter optimization, the accuracy of XGBoost classifier in predicting serious accidents is 75.97%, and the AUC value is 0.8412, which has strong robustness, and provides reliable support for dynamic risk assessment of traffic management system.
Jiang Luo, Yuxin Zhang, Xin Li et al.· SAE technical paper series· 0 citations
Understanding traffic collision patterns is important for road safety planning in fast-growing urban environments. This study examines temporal and spatial patterns of traffic collisions in Dubai, United Arab Emirates, with emphasis on collision severity. Traffic incident records from November 5, 2024, to June 2, 2025, were obtained from the Dubai Police open dataset. After spatial validation, 33,480 collision records were analyzed, including 1,365 pedestrian-related collisions, representing 4.07% of the dataset. Hourly, daily, and month-to-month variations in collision frequency and severity were examined within the available study period. Temporal associations with severity were evaluated using chi-square tests and Cramér’s V, while spatial patterns were analyzed using severity-weighted Getis–Ord Gi* hotspot analysis, complemented by inverse distance weighting interpolation. The results show observable temporal variation in collision frequency and severity proportions, with higher collision frequencies during evening and nighttime periods. For overall collisions, severity is significantly associated with time of day, day of week, and month, although the effect sizes are small or negligible. The observed proportion of high-severity outcomes is 44% higher during nighttime than during the afternoon. Pedestrian-related collisions show higher occurrence during late-evening hours, but pedestrian severity is not significantly associated with the temporal variables considered. Spatial analysis identifies severity-weighted collision concentrations in northern and northwestern Dubai and along the Al Ain–Dubai Highway, while pedestrian hotspots are concentrated near the industrial area in the southwestern region. The findings provide a severity-focused diagnostic basis for identifying locations that may warrant further investigation and targeted safety assessment in Dubai.
Nael Alsaleh, Noura Falis, T. Alsaleh et al.· IEEE Access· 0 citations
Fatal construction accidents, which cause significant loss of life, often arise from complex risks that evolve over time rather than from isolated or static hazards. However, existing research largely neglects this dynamic nature and offers limited insight into the temporal evolution of construction safety risks. To address this gap, this study systematically investigates the interperiod changes of construction safety risks to improve understanding of the dynamic mechanisms underlying fatal construction accidents. Specifically, tree-augmented naive Bayes models were developed for 357 fatal accidents in Hong Kong across two intervals (2000–2010 and 2011–2021), enabling explicit visualization of the state probability distributions for each descriptive and causal factor. Sensitivity analyses were subsequently performed to identify the most impactful factors, followed by scenario-based simulations to evaluate the risk evolution trends of various accident typologies during the two periods. Findings indicate the time-varying dynamics of construction safety risks: (1) falls from height remain the most prevalent accident type, increasing from 50.0% in the earlier period to 59.2% in the later period. (2) Among descriptive factors, specific risk agents and work types are strongly associated with distinct accident types; among causal factors, lack of skills/knowledge and unsafe workplace arrangements have recently become more critical in determining accident type. (3) The probabilities of inadequate risk assessment, insufficient safety training, and deficient safety rules or procedures have increased significantly across all accident types. This study deepens understanding of the temporal evolution of construction safety risks and highlights the need to allocate adequate safety resources and establish effective safety management systems, particularly for preventing falls from heights.
Hanyi Zhou, Zixuan Yan, A. Chan et al.· Journal of Management in Eng...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
