Alcohol-related hot-spot analysis and prediction : final report.
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study addresses the challenge of identifying and mitigating alcohol-related motor vehicle crashes by improving the accuracy of spatial hot-spot analysis and developing more efficient law enforcement patrol strategies. Motivated by the high fatality rates associated with drunk driving and the limitations of traditional spatial mapping methods, the research aims to create geospatial tools that allow for targeted safety campaigns. The primary objective is to reduce alcohol-related crashes in Ohio by refining how crash locations are identified and how police resources are deployed to deter intoxicated driving. The methodology involves a multi-step analytical process applied to crash data from several Ohio counties, including Cuyahoga, Franklin, Summit, and Ross. First, the study compares Euclidean versus network-based distances for calculating spatial autocorrelation, finding that network-based distances yield more accurate hot-spot identifications. Second, it conducts a spatio-temporal analysis to examine how crash clusters shift over time, distinguishing between single and multi-vehicle incidents across different times of day and days of the week. Third, the research investigates the influence of population density on hot-spot mapping, testing whether normalization improves accuracy. Finally, the study develops a new patrol method using Local Indicators of Spatial Association (LISA) to identify statistically significant locations for intoxicated drivers. These locations are used in route optimization models to guide officers, which are then compared against traditional corridor-based enforcement using performance metrics and failure probability models. The results indicate that network-based distance calculations significantly improve the precision of hot-spot identification compared to Euclidean methods. The spatio-temporal analysis reveals that crash clusters are dynamic, appearing and disappearing throughout the day and week, suggesting that static enforcement strategies may miss peak risk periods. Regarding normalization, the study finds that strict normalization by population density yields unfavorable results; instead, using crash frequency or societal crash costs provides better targeting for different campaign types. Crucially, the new route-optimized patrol method, guided by LISA-derived hot spots, allows officers to pass through more alcohol-related crash locations per minute and mile than traditional corridor patrols. Failure probability models further justify this new approach, demonstrating its superior efficiency and potential for better decision-making by jurisdiction administrators. The significance of this work lies in its contribution to data-driven approaches to roadway safety. By enhancing the accuracy of spatial analysis and providing a validated, efficient method for police patrolling, the study offers a practical framework for reducing alcohol-related crashes. The findings suggest that moving from static, corridor-based enforcement to dynamic, location-specific patrols can increase the visibility of law enforcement in high-risk areas, thereby deterring impaired driving. The methodologies developed are applicable beyond the study areas, offering a scalable model for transportation agencies and law enforcement bodies seeking to optimize safety campaigns and resource allocation.
Key finding
Route optimization guided by hot spot analysis allows officers to pass through more alcohol-related crash locations per minute and mile than traditional corridor patrolling practices.
Methodology
dataset
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. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; 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