Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method
Pile-up (PU) crashes, which involve multiple collisions between more than two vehicles within a brief timeframe, carry substantial consequences, including fatalities and significant damages. This study aims to investigate the real-time traffic, environmental, and crash characteristics and their inte...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Safety |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-576X/10/1/22 |
| _version_ | 1797239410774769664 |
|---|---|
| author | Seyed Alireza Samerei Kayvan Aghabayk Alfonso Montella |
| author_facet | Seyed Alireza Samerei Kayvan Aghabayk Alfonso Montella |
| author_sort | Seyed Alireza Samerei |
| collection | DOAJ |
| description | Pile-up (PU) crashes, which involve multiple collisions between more than two vehicles within a brief timeframe, carry substantial consequences, including fatalities and significant damages. This study aims to investigate the real-time traffic, environmental, and crash characteristics and their interactions in terms of their contributions to severe PU crashes, which have been understudied. This study investigates and interprets the effects of Total Volume/Capacity (TV/C), “Heavy Vehicles Volume/Total Volume” (HVV/TV), and average speed. For this purpose, the PU crash severity was modelled and interpreted using the crash and real-time traffic data of Iran’s freeways over a 5-year period. Among six machine learning methods, the CatBoost model demonstrated superior performance, interpreted via the SHAP method. The results indicate that avg.speed > 90 km/h, TV/C < 0.6, HVV/TV ≥ 0.1, horizontal curves, longitudinal grades, nighttime, and the involvement of heavy vehicles are associated with the risk of severe PU crashes. Additionally, several interactions are associated with severe PU crashes, including the co-occurrence of TV/C ≈ 0.1, HVV/TV ≥ 0.25, and nighttime; the interactions between TV/C ≈ 0.1 or 0.45, HVV/TV ≥ 0.25, and avg.speed > 90 km/h; horizontal curves and high average speeds; horizontal curves; and nighttime. Overall, this research provides essential insights into traffic and environmental factors driving severe PU crashes, supporting informed decision-making for policymakers. |
| first_indexed | 2024-04-24T17:51:06Z |
| format | Article |
| id | doaj.art-e8572483220e426f8f51cd0aeff9ca34 |
| institution | Directory Open Access Journal |
| issn | 2313-576X |
| language | English |
| last_indexed | 2024-04-24T17:51:06Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Safety |
| spelling | doaj.art-e8572483220e426f8f51cd0aeff9ca342024-03-27T14:03:19ZengMDPI AGSafety2313-576X2024-02-011012210.3390/safety10010022Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations MethodSeyed Alireza Samerei0Kayvan Aghabayk1Alfonso Montella2School of Civil Engineering, College of Engineering, University of Tehran, Tehran 4563-11155, IranSchool of Civil Engineering, College of Engineering, University of Tehran, Tehran 4563-11155, IranDepartment of Civil, Architectural and Environmental Engineering, University of Naples Federico II, 80125 Naples, ItalyPile-up (PU) crashes, which involve multiple collisions between more than two vehicles within a brief timeframe, carry substantial consequences, including fatalities and significant damages. This study aims to investigate the real-time traffic, environmental, and crash characteristics and their interactions in terms of their contributions to severe PU crashes, which have been understudied. This study investigates and interprets the effects of Total Volume/Capacity (TV/C), “Heavy Vehicles Volume/Total Volume” (HVV/TV), and average speed. For this purpose, the PU crash severity was modelled and interpreted using the crash and real-time traffic data of Iran’s freeways over a 5-year period. Among six machine learning methods, the CatBoost model demonstrated superior performance, interpreted via the SHAP method. The results indicate that avg.speed > 90 km/h, TV/C < 0.6, HVV/TV ≥ 0.1, horizontal curves, longitudinal grades, nighttime, and the involvement of heavy vehicles are associated with the risk of severe PU crashes. Additionally, several interactions are associated with severe PU crashes, including the co-occurrence of TV/C ≈ 0.1, HVV/TV ≥ 0.25, and nighttime; the interactions between TV/C ≈ 0.1 or 0.45, HVV/TV ≥ 0.25, and avg.speed > 90 km/h; horizontal curves and high average speeds; horizontal curves; and nighttime. Overall, this research provides essential insights into traffic and environmental factors driving severe PU crashes, supporting informed decision-making for policymakers.https://www.mdpi.com/2313-576X/10/1/22pile-up crashcrash severitymachine learningSHAP method |
| spellingShingle | Seyed Alireza Samerei Kayvan Aghabayk Alfonso Montella Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method Safety pile-up crash crash severity machine learning SHAP method |
| title | Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method |
| title_full | Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method |
| title_fullStr | Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method |
| title_full_unstemmed | Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method |
| title_short | Analyzing Pile-Up Crash Severity: Insights from Real-Time Traffic and Environmental Factors Using Ensemble Machine Learning and Shapley Additive Explanations Method |
| title_sort | analyzing pile up crash severity insights from real time traffic and environmental factors using ensemble machine learning and shapley additive explanations method |
| topic | pile-up crash crash severity machine learning SHAP method |
| url | https://www.mdpi.com/2313-576X/10/1/22 |
| work_keys_str_mv | AT seyedalirezasamerei analyzingpileupcrashseverityinsightsfromrealtimetrafficandenvironmentalfactorsusingensemblemachinelearningandshapleyadditiveexplanationsmethod AT kayvanaghabayk analyzingpileupcrashseverityinsightsfromrealtimetrafficandenvironmentalfactorsusingensemblemachinelearningandshapleyadditiveexplanationsmethod AT alfonsomontella analyzingpileupcrashseverityinsightsfromrealtimetrafficandenvironmentalfactorsusingensemblemachinelearningandshapleyadditiveexplanationsmethod |