Comparative analysis of methods to identify road sections with high accidents risk: a case study of E67 Estonia–Latvia–Lithuania corridor
DOI: 10.1051/matecconf/202133402001
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the need for efficient road infrastructure safety management in the Baltic States, motivated by high accident rates and European Union goals to reduce road fatalities. The authors compare three distinct methodologies used by Estonia, Latvia, and Lithuania to identify dangerous road sections along the E67 (Via Baltica) corridor, a critical transit route connecting the three nations. The research aims to reveal differences in how these countries define and locate high-risk areas, thereby informing better safety prioritization and resource allocation. The study applied the specific identification methods of each country to the entire 663 km Estonia–Latvia–Lithuania section of the E67 corridor. Lithuania employs a Black Spot Management (BSM) approach using a 500-meter sliding window, identifying a spot if three or more accidents with casualties occur within a four-year period. Latvia also uses BSM but analyzes three-year data on 1-kilometer stretches, incorporating both casualty and damage-only accidents, while defining serious injury based on hospitalization duration. Estonia utilizes Network Safety Management (NSM), dividing the network into homogeneous groups based on road parameters and traffic data. It calculates safety levels using an empirical Bayes approach to estimate expected accident numbers, identifying sections with a relative risk level of one or higher as dangerous. Data collection involved integrating road, traffic, and accident databases from each country, though inconsistencies in data availability and accuracy were noted. The analysis identified a total of 126 dangerous locations across the corridor, averaging 19 per 100 km. The Estonian methodology identified 91 dangerous sections, the Latvian method found 53 black spots, and the Lithuanian method detected only 19. Significant discrepancies existed between the methods; for instance, the Lithuanian method identified zero black spots within Lithuania itself, whereas the Estonian and Latvian methods identified 42 and 21 dangerous locations there, respectively. Only nine locations were classified as dangerous by all three methodologies. The results highlighted that the Latvian method’s inclusion of damage-only accidents shifts focus toward material loss prevention, while the Estonian method identifies risky infrastructure even in the absence of historical accidents. The findings suggest that current Lithuanian methods may lack sensitivity, potentially missing hazardous sections that other approaches detect, and are prone to false positives. The study concludes that Estonia’s network safety ranking offers a more comprehensive view by identifying inherent risks rather than relying solely on accident history. However, the authors note that data limitations, such as the lack of serious injury data in Estonia and Lithuania and poor location accuracy in Latvia, hinder the full application of these methods. The research implies that adopting more sensitive, network-wide safety assessments and improving data quality are essential for effective road safety management in the region.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-18 |
| archive | success | canonical_url | — | — | 1 | 2026-06-25 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-18 |
| chunk | success | chunk | — | — | 1 | 2026-06-18 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-18 |
| promote | success | — | — | — | 1 | 2026-06-18 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-18 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: crash risk outcomes