Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model
Secondary crashes (SCs) are typically defined as the crash that occurs within the spatiotemporal boundaries of the impact area of the primary crashes (PCs), which will intensify traffic congestion and induce a series of road safety issues. Predicting and analyzing the time and distance gaps between...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2023/7833555 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850159658293002240 |
|---|---|
| author | Xinyuan Liu Jinjun Tang Fan Gao Xizhi Ding |
| author_facet | Xinyuan Liu Jinjun Tang Fan Gao Xizhi Ding |
| author_sort | Xinyuan Liu |
| collection | DOAJ |
| description | Secondary crashes (SCs) are typically defined as the crash that occurs within the spatiotemporal boundaries of the impact area of the primary crashes (PCs), which will intensify traffic congestion and induce a series of road safety issues. Predicting and analyzing the time and distance gaps between the SCs and PCs will help to prevent the occurrence of SCs. In this paper, a combined data-driven method of static and dynamic approaches is applied to identify SCs. Then, the random forests (RF) method is implemented to predict the two gaps using temporal, primary crash, roadway, and real-time traffic characteristics data collected from 2016 to 2019 at California interstate freeways. Subsequently, the SHapley Additive explanation (SHAP) approach is employed to interpret the RF outputs. The results show that the traffic volume, speed, lighting, and population are considered the most significant factors in both gaps. Furthermore, the main and interaction effects of factors are also quantified. High volume possibly promotes the time and distance gaps, while low volume inhibits them. And volume affects the distance gap inconsiderably when it falls between 300 and 400 veh/5 min. Traffic conditions with high speed and low volume are strongly associated with short-time and short-distance gaps. Darker surroundings probably accelerate the occurrence of SCs. Moreover, crashes involving the violation categories of improper turns or unsafe lane changes likely result in long time and distance gaps. These results have important implications for proposing traffic management and improving road safety. |
| format | Article |
| id | doaj-art-b2db2460997d4026b0a344096afaf4c0 |
| institution | OA Journals |
| issn | 2042-3195 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-b2db2460997d4026b0a344096afaf4c02025-08-20T02:23:27ZengWileyJournal of Advanced Transportation2042-31952023-01-01202310.1155/2023/7833555Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP ModelXinyuan Liu0Jinjun Tang1Fan Gao2Xizhi Ding3Smart Transportation Key Laboratory of Hunan ProvinceSmart Transportation Key Laboratory of Hunan ProvinceSmart Transportation Key Laboratory of Hunan ProvinceSmart Transportation Key Laboratory of Hunan ProvinceSecondary crashes (SCs) are typically defined as the crash that occurs within the spatiotemporal boundaries of the impact area of the primary crashes (PCs), which will intensify traffic congestion and induce a series of road safety issues. Predicting and analyzing the time and distance gaps between the SCs and PCs will help to prevent the occurrence of SCs. In this paper, a combined data-driven method of static and dynamic approaches is applied to identify SCs. Then, the random forests (RF) method is implemented to predict the two gaps using temporal, primary crash, roadway, and real-time traffic characteristics data collected from 2016 to 2019 at California interstate freeways. Subsequently, the SHapley Additive explanation (SHAP) approach is employed to interpret the RF outputs. The results show that the traffic volume, speed, lighting, and population are considered the most significant factors in both gaps. Furthermore, the main and interaction effects of factors are also quantified. High volume possibly promotes the time and distance gaps, while low volume inhibits them. And volume affects the distance gap inconsiderably when it falls between 300 and 400 veh/5 min. Traffic conditions with high speed and low volume are strongly associated with short-time and short-distance gaps. Darker surroundings probably accelerate the occurrence of SCs. Moreover, crashes involving the violation categories of improper turns or unsafe lane changes likely result in long time and distance gaps. These results have important implications for proposing traffic management and improving road safety.http://dx.doi.org/10.1155/2023/7833555 |
| spellingShingle | Xinyuan Liu Jinjun Tang Fan Gao Xizhi Ding Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model Journal of Advanced Transportation |
| title | Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model |
| title_full | Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model |
| title_fullStr | Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model |
| title_full_unstemmed | Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model |
| title_short | Time and Distance Gaps of Primary-Secondary Crashes Prediction and Analysis Using Random Forests and SHAP Model |
| title_sort | time and distance gaps of primary secondary crashes prediction and analysis using random forests and shap model |
| url | http://dx.doi.org/10.1155/2023/7833555 |
| work_keys_str_mv | AT xinyuanliu timeanddistancegapsofprimarysecondarycrashespredictionandanalysisusingrandomforestsandshapmodel AT jinjuntang timeanddistancegapsofprimarysecondarycrashespredictionandanalysisusingrandomforestsandshapmodel AT fangao timeanddistancegapsofprimarysecondarycrashespredictionandanalysisusingrandomforestsandshapmodel AT xizhiding timeanddistancegapsofprimarysecondarycrashespredictionandanalysisusingrandomforestsandshapmodel |