Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models

Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traf...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sustainability 2024-09, Vol.16 (18), p.7903
Hauptverfasser: Qi, Ziyuan, Yao, Jingmeng, Zou, Xuan, Pu, Kairui, Qin, Wenwen, Li, Wu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 18
container_start_page 7903
container_title Sustainability
container_volume 16
creator Qi, Ziyuan
Yao, Jingmeng
Zou, Xuan
Pu, Kairui
Qin, Wenwen
Li, Wu
description Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traffic safety, thereby contributing to sustainable transportation systems. The focus of this study is to compare the interpretability of model performances with three statistical models (Ordered Logit, Partial Proportional Odds Model, and Multinomial Logit) and six machine learning models (Decision Tree, Random Forest, Gradient Boosting, Extra Trees, AdaBoost, and XGBoost) on two-lane mountain roads in Yunnan Province, China. Additionally, we assessed the ability of these models to uncover underlying causal relationships, particularly how accident causes affect severity. Using the SHapley Additive exPlanations (SHAP) method, we interpreted the influence of risk factors in the machine learning models. Our findings indicate that machine learning models, especially XGBoost, outperform statistical models in predicting accident severity. The results highlight that accident patterns are the most significant determinants of severity, followed by road-related factors and the type of colliding vehicles. Environmental factors like weather, however, have minimal impact. Notably, vehicle falling, head-on collisions, and longitudinal slope sections are linked to more severe accidents, while minor accidents are more frequent on horizontal curve sections and areas that combine curves and slopes. These insights can help traffic management agencies develop targeted measures to reduce accident rates and enhance road safety, which is critical for promoting sustainable transportation in mountainous regions.
doi_str_mv 10.3390/su16187903
format Article
fullrecord <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_3110713702</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A810790958</galeid><sourcerecordid>A810790958</sourcerecordid><originalsourceid>FETCH-LOGICAL-c257t-b94dcc1bb2284a4b408a73050a68c5eabd94bfa9159fcae280222739e862e3b93</originalsourceid><addsrcrecordid>eNpVkdtKAzEQhhdRsFRvfIIFrxRWc9hTvCvFaqEi2OrtMpud3aasiSZZT09vSgV1cjHJ8P3zM5koOqHkgnNBLt1Ac1oWgvC9aMRIQRNKMrL_534YHTu3ISE4p4Lmo-hrrt_QedWBV7qLZyC9sS6e67YfUMttbWrBreMlvqFV_jM2Or4zg_agtBlcvHo3yQI0xg8GGncV34Fcq_BcIFi9lT-hdYFb-uAQjCT0Qd9g746igxZ6h8c_eRw9zq5X09tkcX8zn04WiWRZ4ZNapI2UtK4ZK1NI65SUUPAwDOSlzBDqRqR1C4JmopWArCSMsYILLHOGvBZ8HJ3u-r5Y8zqEYauNGawOlhWnNHwNLwgL1MWO6qDHSunWeAsynAaflTQaWxXqkzIIBBFZGQRn_wSB8fjhOxicq-bLh__s-Y6V1jhnsa1erHoG-1lRUm13V_3ujn8DUq2Lyw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3110713702</pqid></control><display><type>article</type><title>Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Free E-Journal (出版社公開部分のみ)</source><creator>Qi, Ziyuan ; Yao, Jingmeng ; Zou, Xuan ; Pu, Kairui ; Qin, Wenwen ; Li, Wu</creator><creatorcontrib>Qi, Ziyuan ; Yao, Jingmeng ; Zou, Xuan ; Pu, Kairui ; Qin, Wenwen ; Li, Wu</creatorcontrib><description>Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traffic safety, thereby contributing to sustainable transportation systems. The focus of this study is to compare the interpretability of model performances with three statistical models (Ordered Logit, Partial Proportional Odds Model, and Multinomial Logit) and six machine learning models (Decision Tree, Random Forest, Gradient Boosting, Extra Trees, AdaBoost, and XGBoost) on two-lane mountain roads in Yunnan Province, China. Additionally, we assessed the ability of these models to uncover underlying causal relationships, particularly how accident causes affect severity. Using the SHapley Additive exPlanations (SHAP) method, we interpreted the influence of risk factors in the machine learning models. Our findings indicate that machine learning models, especially XGBoost, outperform statistical models in predicting accident severity. The results highlight that accident patterns are the most significant determinants of severity, followed by road-related factors and the type of colliding vehicles. Environmental factors like weather, however, have minimal impact. Notably, vehicle falling, head-on collisions, and longitudinal slope sections are linked to more severe accidents, while minor accidents are more frequent on horizontal curve sections and areas that combine curves and slopes. These insights can help traffic management agencies develop targeted measures to reduce accident rates and enhance road safety, which is critical for promoting sustainable transportation in mountainous regions.</description><identifier>ISSN: 2071-1050</identifier><identifier>EISSN: 2071-1050</identifier><identifier>DOI: 10.3390/su16187903</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accident prevention ; Accuracy ; Comparative analysis ; Environmental aspects ; Fatalities ; Forecasts and trends ; Injuries ; Machine learning ; Mountain roads ; Risk factors ; Roads &amp; highways ; Safety and security measures ; Statistical analysis ; Statistical models ; Traffic accidents ; Traffic accidents &amp; safety ; Variables ; Vehicles</subject><ispartof>Sustainability, 2024-09, Vol.16 (18), p.7903</ispartof><rights>COPYRIGHT 2024 MDPI AG</rights><rights>2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c257t-b94dcc1bb2284a4b408a73050a68c5eabd94bfa9159fcae280222739e862e3b93</cites><orcidid>0000-0002-8607-5454 ; 0000-0003-4982-2024</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Qi, Ziyuan</creatorcontrib><creatorcontrib>Yao, Jingmeng</creatorcontrib><creatorcontrib>Zou, Xuan</creatorcontrib><creatorcontrib>Pu, Kairui</creatorcontrib><creatorcontrib>Qin, Wenwen</creatorcontrib><creatorcontrib>Li, Wu</creatorcontrib><title>Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models</title><title>Sustainability</title><description>Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traffic safety, thereby contributing to sustainable transportation systems. The focus of this study is to compare the interpretability of model performances with three statistical models (Ordered Logit, Partial Proportional Odds Model, and Multinomial Logit) and six machine learning models (Decision Tree, Random Forest, Gradient Boosting, Extra Trees, AdaBoost, and XGBoost) on two-lane mountain roads in Yunnan Province, China. Additionally, we assessed the ability of these models to uncover underlying causal relationships, particularly how accident causes affect severity. Using the SHapley Additive exPlanations (SHAP) method, we interpreted the influence of risk factors in the machine learning models. Our findings indicate that machine learning models, especially XGBoost, outperform statistical models in predicting accident severity. The results highlight that accident patterns are the most significant determinants of severity, followed by road-related factors and the type of colliding vehicles. Environmental factors like weather, however, have minimal impact. Notably, vehicle falling, head-on collisions, and longitudinal slope sections are linked to more severe accidents, while minor accidents are more frequent on horizontal curve sections and areas that combine curves and slopes. These insights can help traffic management agencies develop targeted measures to reduce accident rates and enhance road safety, which is critical for promoting sustainable transportation in mountainous regions.</description><subject>Accident prevention</subject><subject>Accuracy</subject><subject>Comparative analysis</subject><subject>Environmental aspects</subject><subject>Fatalities</subject><subject>Forecasts and trends</subject><subject>Injuries</subject><subject>Machine learning</subject><subject>Mountain roads</subject><subject>Risk factors</subject><subject>Roads &amp; highways</subject><subject>Safety and security measures</subject><subject>Statistical analysis</subject><subject>Statistical models</subject><subject>Traffic accidents</subject><subject>Traffic accidents &amp; safety</subject><subject>Variables</subject><subject>Vehicles</subject><issn>2071-1050</issn><issn>2071-1050</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpVkdtKAzEQhhdRsFRvfIIFrxRWc9hTvCvFaqEi2OrtMpud3aasiSZZT09vSgV1cjHJ8P3zM5koOqHkgnNBLt1Ac1oWgvC9aMRIQRNKMrL_534YHTu3ISE4p4Lmo-hrrt_QedWBV7qLZyC9sS6e67YfUMttbWrBreMlvqFV_jM2Or4zg_agtBlcvHo3yQI0xg8GGncV34Fcq_BcIFi9lT-hdYFb-uAQjCT0Qd9g746igxZ6h8c_eRw9zq5X09tkcX8zn04WiWRZ4ZNapI2UtK4ZK1NI65SUUPAwDOSlzBDqRqR1C4JmopWArCSMsYILLHOGvBZ8HJ3u-r5Y8zqEYauNGawOlhWnNHwNLwgL1MWO6qDHSunWeAsynAaflTQaWxXqkzIIBBFZGQRn_wSB8fjhOxicq-bLh__s-Y6V1jhnsa1erHoG-1lRUm13V_3ujn8DUq2Lyw</recordid><startdate>20240901</startdate><enddate>20240901</enddate><creator>Qi, Ziyuan</creator><creator>Yao, Jingmeng</creator><creator>Zou, Xuan</creator><creator>Pu, Kairui</creator><creator>Qin, Wenwen</creator><creator>Li, Wu</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>4U-</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0002-8607-5454</orcidid><orcidid>https://orcid.org/0000-0003-4982-2024</orcidid></search><sort><creationdate>20240901</creationdate><title>Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models</title><author>Qi, Ziyuan ; Yao, Jingmeng ; Zou, Xuan ; Pu, Kairui ; Qin, Wenwen ; Li, Wu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c257t-b94dcc1bb2284a4b408a73050a68c5eabd94bfa9159fcae280222739e862e3b93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accident prevention</topic><topic>Accuracy</topic><topic>Comparative analysis</topic><topic>Environmental aspects</topic><topic>Fatalities</topic><topic>Forecasts and trends</topic><topic>Injuries</topic><topic>Machine learning</topic><topic>Mountain roads</topic><topic>Risk factors</topic><topic>Roads &amp; highways</topic><topic>Safety and security measures</topic><topic>Statistical analysis</topic><topic>Statistical models</topic><topic>Traffic accidents</topic><topic>Traffic accidents &amp; safety</topic><topic>Variables</topic><topic>Vehicles</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Qi, Ziyuan</creatorcontrib><creatorcontrib>Yao, Jingmeng</creatorcontrib><creatorcontrib>Zou, Xuan</creatorcontrib><creatorcontrib>Pu, Kairui</creatorcontrib><creatorcontrib>Qin, Wenwen</creatorcontrib><creatorcontrib>Li, Wu</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>University Readers</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>ProQuest - Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Sustainability</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Qi, Ziyuan</au><au>Yao, Jingmeng</au><au>Zou, Xuan</au><au>Pu, Kairui</au><au>Qin, Wenwen</au><au>Li, Wu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models</atitle><jtitle>Sustainability</jtitle><date>2024-09-01</date><risdate>2024</risdate><volume>16</volume><issue>18</issue><spage>7903</spage><pages>7903-</pages><issn>2071-1050</issn><eissn>2071-1050</eissn><abstract>Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traffic safety, thereby contributing to sustainable transportation systems. The focus of this study is to compare the interpretability of model performances with three statistical models (Ordered Logit, Partial Proportional Odds Model, and Multinomial Logit) and six machine learning models (Decision Tree, Random Forest, Gradient Boosting, Extra Trees, AdaBoost, and XGBoost) on two-lane mountain roads in Yunnan Province, China. Additionally, we assessed the ability of these models to uncover underlying causal relationships, particularly how accident causes affect severity. Using the SHapley Additive exPlanations (SHAP) method, we interpreted the influence of risk factors in the machine learning models. Our findings indicate that machine learning models, especially XGBoost, outperform statistical models in predicting accident severity. The results highlight that accident patterns are the most significant determinants of severity, followed by road-related factors and the type of colliding vehicles. Environmental factors like weather, however, have minimal impact. Notably, vehicle falling, head-on collisions, and longitudinal slope sections are linked to more severe accidents, while minor accidents are more frequent on horizontal curve sections and areas that combine curves and slopes. These insights can help traffic management agencies develop targeted measures to reduce accident rates and enhance road safety, which is critical for promoting sustainable transportation in mountainous regions.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/su16187903</doi><orcidid>https://orcid.org/0000-0002-8607-5454</orcidid><orcidid>https://orcid.org/0000-0003-4982-2024</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2071-1050
ispartof Sustainability, 2024-09, Vol.16 (18), p.7903
issn 2071-1050
2071-1050
language eng
recordid cdi_proquest_journals_3110713702
source MDPI - Multidisciplinary Digital Publishing Institute; Free E-Journal (出版社公開部分のみ)
subjects Accident prevention
Accuracy
Comparative analysis
Environmental aspects
Fatalities
Forecasts and trends
Injuries
Machine learning
Mountain roads
Risk factors
Roads & highways
Safety and security measures
Statistical analysis
Statistical models
Traffic accidents
Traffic accidents & safety
Variables
Vehicles
title Investigating Factors Influencing Crash Severity on Mountainous Two-Lane Roads: Machine Learning Versus Statistical Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A16%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Investigating%20Factors%20Influencing%20Crash%20Severity%20on%20Mountainous%20Two-Lane%20Roads:%20Machine%20Learning%20Versus%20Statistical%20Models&rft.jtitle=Sustainability&rft.au=Qi,%20Ziyuan&rft.date=2024-09-01&rft.volume=16&rft.issue=18&rft.spage=7903&rft.pages=7903-&rft.issn=2071-1050&rft.eissn=2071-1050&rft_id=info:doi/10.3390/su16187903&rft_dat=%3Cgale_proqu%3EA810790958%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3110713702&rft_id=info:pmid/&rft_galeid=A810790958&rfr_iscdi=true