Real-time Secondary Crash Likelihood Prediction Excluding Post Primary Crash Features
arXiv:2602.16739v1 Announce Type: new Abstract: Secondary crash likelihood prediction is a critical component of an active traffic management system to mitigate congestion and adverse impacts caused by secondary crashes. However, existing approaches mainly rely on post-crash features (e.g., crash type and severity) that are rarely available in real time, limiting their practical applicability. To address this limitation, we propose a hybrid secondary crash likelihood prediction framework that does not depend on post-crash features. A dynamic spatiotemporal window is designed to extract real-time traffic flow and environmental features from primary crash locations and their upstream segments. The framework includes three models: a primary crash model to estimate the likelihood of secondary crash occurrence, and two secondary crash models to evaluate traffic conditions at crash and upstream segments under different comparative scenarios. An ensemble learning strategy integrating six mac
arXiv:2602.16739v1 Announce Type: new Abstract: Secondary crash likelihood prediction is a critical component of an active traffic management system to mitigate congestion and adverse impacts caused by secondary crashes. However, existing approaches mainly rely on post-crash features (e.g., crash type and severity) that are rarely available in real time, limiting their practical applicability. To address this limitation, we propose a hybrid secondary crash likelihood prediction framework that does not depend on post-crash features. A dynamic spatiotemporal window is designed to extract real-time traffic flow and environmental features from primary crash locations and their upstream segments. The framework includes three models: a primary crash model to estimate the likelihood of secondary crash occurrence, and two secondary crash models to evaluate traffic conditions at crash and upstream segments under different comparative scenarios. An ensemble learning strategy integrating six machine learning algorithms is developed to enhance predictive performance, and a voting-based mechanism combines the outputs of the three models. Experiments on Florida freeways demonstrate that the proposed hybrid framework correctly identifies 91% of secondary crashes with a low false alarm rate of 0.20. The Area Under the ROC Curve improves from 0.654, 0.744, and 0.902 for the individual models to 0.952 for the hybrid model, outperforming previous studies.
Executive Summary
This article proposes a hybrid framework for real-time secondary crash likelihood prediction, excluding post-primary crash features. The framework integrates three models and six machine learning algorithms, achieving a 91% correct identification rate of secondary crashes with a low false alarm rate. The approach demonstrates significant improvement over individual models, with an Area Under the ROC Curve of 0.952, outperforming previous studies.
Key Points
- ▸ Hybrid framework for real-time secondary crash likelihood prediction
- ▸ Exclusion of post-primary crash features
- ▸ Integration of three models and six machine learning algorithms
- ▸ 91% correct identification rate of secondary crashes with a low false alarm rate
Merits
Improved Predictive Performance
The hybrid framework demonstrates significant improvement in predictive performance, with an Area Under the ROC Curve of 0.952, outperforming previous studies.
Real-time Applicability
The framework's ability to operate in real-time, without relying on post-crash features, enhances its practical applicability in active traffic management systems.
Demerits
Limited Geographical Scope
The study's experiments are limited to Florida freeways, which may not be representative of other regions or traffic conditions.
Complexity of the Framework
The integration of multiple models and algorithms may increase the complexity of the framework, potentially affecting its scalability and maintainability.
Expert Commentary
The proposed hybrid framework represents a significant advancement in real-time secondary crash likelihood prediction. The exclusion of post-primary crash features and the integration of multiple models and algorithms demonstrate a nuanced understanding of the complexities involved in traffic safety prediction. However, further research is needed to validate the framework's performance in diverse traffic conditions and to address potential limitations, such as the geographical scope and complexity of the framework.
Recommendations
- ✓ Further validation of the framework's performance in diverse traffic conditions
- ✓ Investigation of the framework's scalability and maintainability in large-scale traffic management systems
- ✓ Exploration of the framework's potential applications in other domains, such as pedestrian safety prediction
