An ensemble learning method for low visibility prediction on freeway using meteorological data
Abstract The prediction of low visibility is essential for proactive traffic safety management on freeways under fog conditions. However, few studies have developed prediction models for visibility on freeways at a short‐term time interval. This study proposes an ensemble learning approach to develo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-11-01
|
| Series: | IET Intelligent Transport Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/itr2.12404 |
| _version_ | 1797615885379174400 |
|---|---|
| author | Ben Zhai Yanli Wang Bing Wu |
| author_facet | Ben Zhai Yanli Wang Bing Wu |
| author_sort | Ben Zhai |
| collection | DOAJ |
| description | Abstract The prediction of low visibility is essential for proactive traffic safety management on freeways under fog conditions. However, few studies have developed prediction models for visibility on freeways at a short‐term time interval. This study proposes an ensemble learning approach to develop a short‐term prediction model of low visibility on freeways using meteorological data. Spearman's rank correlation coefficient is used to select meteorological variables related to low visibility. Random forests (RF) and extreme gradient boosting (XGB) are employed to develop visibility prediction models, and back propagation neural network (BPNN) and logistic regression (LR) are used for comparison. The models are evaluated over five prediction time intervals (5, 10, 15, 30, and 60 min). The results indicate that the RF models outperform the other models with precision of 73.9%, recall of 59.8% and F1 score of 0.65. Moreover, the prediction model with a 15‐min time interval shows better performance. With the proposed short‐term prediction of low visibility, it is expected that more crashes could be prevented with more appropriate proactive traffic safety management strategies. |
| first_indexed | 2024-03-11T07:33:19Z |
| format | Article |
| id | doaj.art-c92ee2eb70814975924f0f5f8cfb23aa |
| institution | Directory Open Access Journal |
| issn | 1751-956X 1751-9578 |
| language | English |
| last_indexed | 2024-03-11T07:33:19Z |
| publishDate | 2023-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Intelligent Transport Systems |
| spelling | doaj.art-c92ee2eb70814975924f0f5f8cfb23aa2023-11-17T05:48:56ZengWileyIET Intelligent Transport Systems1751-956X1751-95782023-11-0117112237225010.1049/itr2.12404An ensemble learning method for low visibility prediction on freeway using meteorological dataBen Zhai0Yanli Wang1Bing Wu2Key Laboratory of Road and Traffic Engineering of Ministry of Education Tongji University Shanghai ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education Tongji University Shanghai ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education Tongji University Shanghai ChinaAbstract The prediction of low visibility is essential for proactive traffic safety management on freeways under fog conditions. However, few studies have developed prediction models for visibility on freeways at a short‐term time interval. This study proposes an ensemble learning approach to develop a short‐term prediction model of low visibility on freeways using meteorological data. Spearman's rank correlation coefficient is used to select meteorological variables related to low visibility. Random forests (RF) and extreme gradient boosting (XGB) are employed to develop visibility prediction models, and back propagation neural network (BPNN) and logistic regression (LR) are used for comparison. The models are evaluated over five prediction time intervals (5, 10, 15, 30, and 60 min). The results indicate that the RF models outperform the other models with precision of 73.9%, recall of 59.8% and F1 score of 0.65. Moreover, the prediction model with a 15‐min time interval shows better performance. With the proposed short‐term prediction of low visibility, it is expected that more crashes could be prevented with more appropriate proactive traffic safety management strategies.https://doi.org/10.1049/itr2.12404intelligent transportation systemsprediction theoryroad safetysustainable development |
| spellingShingle | Ben Zhai Yanli Wang Bing Wu An ensemble learning method for low visibility prediction on freeway using meteorological data IET Intelligent Transport Systems intelligent transportation systems prediction theory road safety sustainable development |
| title | An ensemble learning method for low visibility prediction on freeway using meteorological data |
| title_full | An ensemble learning method for low visibility prediction on freeway using meteorological data |
| title_fullStr | An ensemble learning method for low visibility prediction on freeway using meteorological data |
| title_full_unstemmed | An ensemble learning method for low visibility prediction on freeway using meteorological data |
| title_short | An ensemble learning method for low visibility prediction on freeway using meteorological data |
| title_sort | ensemble learning method for low visibility prediction on freeway using meteorological data |
| topic | intelligent transportation systems prediction theory road safety sustainable development |
| url | https://doi.org/10.1049/itr2.12404 |
| work_keys_str_mv | AT benzhai anensemblelearningmethodforlowvisibilitypredictiononfreewayusingmeteorologicaldata AT yanliwang anensemblelearningmethodforlowvisibilitypredictiononfreewayusingmeteorologicaldata AT bingwu anensemblelearningmethodforlowvisibilitypredictiononfreewayusingmeteorologicaldata AT benzhai ensemblelearningmethodforlowvisibilitypredictiononfreewayusingmeteorologicaldata AT yanliwang ensemblelearningmethodforlowvisibilitypredictiononfreewayusingmeteorologicaldata AT bingwu ensemblelearningmethodforlowvisibilitypredictiononfreewayusingmeteorologicaldata |