Impact of Wind Turbine Distraction on Crash Severity: Assessment and Prediction Study
DOI: 10.28991/cej-2025-011-04-018
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 investigates the impact of wind turbines as external driver distractions on traffic crash severity and frequency along Jordan’s King’s Highway. Motivated by the growing installation of wind farms near highways and limited research on their safety implications, the authors aimed to quantify how turbine presence affects crash outcomes. The research addresses a gap in literature that has predominantly focused on in-vehicle distractions, proposing that large visual structures like wind turbines may distract drivers and increase crash risk. The methodology employed a mixed-methods approach using crash data from 2015 to 2021, covering 1,646 recorded incidents. The study compared two periods: before wind turbine installation (2015–2017) and after operationalization (2018–2021). Data included driver demographics, road geometry, environmental conditions, and crash details. The authors utilized a mixed-effects logit model to analyze crash severity, accounting for unobserved heterogeneity across road segments. Additionally, machine learning techniques were applied to predict crash severity levels (injury vs. no injury). Five classifiers—Decision Tree, Naïve Bayes, Support Vector Machine (SVM), Kernel, and Ensemble (Bagged Tree)—were tested. To address class imbalance in the dataset, the study compared original data with datasets balanced via Random Under-Sampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE). The mixed-effects logit model revealed that wind turbine presence significantly increased crash severity. Specifically, there was a 117.4% increase in severe injury or fatal crashes (KAB) and a 25.7% rise in property damage-only crashes near turbines. Conversely, crashes with minor injuries (KABC) decreased by 19.3%. Other significant factors included higher speed limits, run-off crash types, young drivers (18–24 years), and poorly separated roads. In the machine learning analysis, the Bagged Tree classifier applied to the SMOTE-balanced dataset achieved the highest performance, with a test accuracy of 89.6% and an ROC-AUC of 0.9241. Shapley value analysis identified crash type and wind turbine proximity as the most critical predictors of severity, followed by the number of vehicles involved and license type. The findings underscore that wind turbines act as significant external distractions, contributing to more severe crash outcomes. The study demonstrates the efficacy of combining statistical modeling with machine learning for traffic safety analysis. The authors conclude that regulatory policies should optimize wind turbine placement to mitigate distraction risks. They also highlight the potential of ML techniques, particularly when handling imbalanced data with SMOTE, for enhancing predictive accuracy in road safety assessments. Future research is recommended to explore multi-class severity predictions and assess these effects in different geographic contexts.
Key finding
The presence of wind turbines along the highway was associated with a 117.4% increase in severe injury crashes and a 25.7% increase in property-damage-only crashes.
Methodology
mixed_methods
Sample size: 1646
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 | 2026-06-05 |
| archive | success | unpaywall | — | — | 2 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-07 |
| chunk | success | chunk | — | — | 1 | 2026-06-07 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-07 |
| promote | success | — | — | — | 1 | 2026-06-05 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 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
- Methodological Resource: dataset resource