A data-driven conceptual framework for understanding the nature of hazards in railway accidents
Bibliographic record
Abstract
Hazards threaten railway safety by their potential to trigger railway accidents, resulting in significant costs and impacting the public's willingness to use railways. Whilst many prior works investigate railway hazards, few offer a holistic view of hazards across jurisdictions and time because the large number of primary sources make synthesising such learnings time consuming and potentially incomplete. The conceptual framework HazardMap is developed to overcome this gap, employing open-sourced Natural Language Processing topic modelling for the automated analysis of textual data from Rail Accident Investigation Branch (RAIB), Australian Transport Safety Bureau (ATSB), National Transportation Safety Board (NTSB) and Transportation Safety Board of Canada (TSB) railway accident reports. The topic modelling depicts the relationships between hazards, railway accidents and investigator recommendations and is further extended and integrated with the existing risk theory and epidemiological accident models. The results allow the different aspects of each hazard to be listed along with the potential combinations of hazards that could trigger railway accidents. Better understanding of the aspects of individual hazards and the relationships between hazards and previous accidents can inform more effective hazard mitigation policies including technical or regulatory interventions. A case study of the risk at level crossings is provided to illustrate how HazardMap works with real-world data. This demonstrates a high degree of coverage within the existing risk management system, indicating the capability to better inform policymaking for managing risks. The primary contributions of the framework proposed are to enable a large amount of knowledge accumulated to be summarised for an intuitive policymaking process, and to allow other railway investigators to leverage lessons learnt across jurisdictions and time with limited human intervention. Future research could apply the technique to road, aviation or maritime accidents.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".