Negative binomial regression identifies key environmental and visitor factors influencing accidents in trails, suggesting safety management improvements.
This study empirically analyzed the factors affecting the occurrence of safety accidents based on the characteristics of Hallasan National Park. Negative binomial regression and SHAP (SHapley Additive exPlanations) analysis techniques were applied using data on the number of monthly visitors, topographic and environmental characteristics, number of accidents, and climate data for each trail. As a result, it was found that the length, time required, difficulty, average altitude, and number of drinking water sites of the trail segment had a significant effect on the number of accidents, and the risk of accidents was relatively high, especially in trail segments with low average altitude, short length, and low difficulty. In the SHAP analysis results, the average altitude, length of the trail segment, and number of visitors showed the highest contribution to accident prediction, suggesting that the visitors’ lack of safety awareness may be the main cause of accidents rather than topographic risk. The research results are expected to be used in the future to establish effective safety management policies, such as strengthening safety publicity for low-altitude and low-difficulty trail segments, relocating major facilities, and efficient deployment of seasonal management personnel.
No takes yet. Share an insight, caveat, or question.
Yoon et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: