Train related accidents, particularly derailments, can lead to severe consequences especially when they involve injuries or fatalities or when they involve hazardous materials that might result in environmental impacts. Whereas numerous road safety studies have suggested appropriate approaches to predicting vehicle-to-vehicle collisions, very few railway safety studies have considered predicting the number of derailments on rail tracks in North America. In addition, the existing few rail safety assessment and derailment prediction models have often been constrained by aggregated data limiting the safety assessments by, for example, failing to consider segment-level characteristics. This paper focused on the development of an integrated database for the development of a segment-level derailment prediction model for Canada's rail network. The primary objective of this paper is to report how challenges in the data integration process were overcome and also to develop a network screening tool to identify segments with high derailment risk in Canada's rail network. Negative binomial regression and the Empirical Bayes technique were used to estimate the predicted number of derailments on Canada's rail network at the segment level. A network screening process was then successfully applied to identify key segments of safety concern: the top ten segments of concern accounted for approximately 1% of the rail network allowing decision makers to focus their derailment mitigation efforts on a manageable part of Canada's vast rail network. The data processing approach and analysis in this study have strong implications for advancing research on rail safety in North America.
Keywords: Data integration; Derailments; Negative binomial regression; Network screening; Rail safety; Risk prediction.
Copyright © 2020 Elsevier Ltd. All rights reserved.