Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data
Abstract Crash severity models play a crucial role in evaluating the influencing factors in the severity of traffic crashes. In this study, Extremely Randomised Tree (ERT) is used as a machine learning technique to analyse the severity of crashes. The crash data in the province of Khorasan Razavi, I...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-07-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-15693-7 |
_version_ | 1811224110350467072 |
---|---|
author | Farshid Afshar Seyedehsan Seyedabrishami Sara Moridpour |
author_facet | Farshid Afshar Seyedehsan Seyedabrishami Sara Moridpour |
author_sort | Farshid Afshar |
collection | DOAJ |
description | Abstract Crash severity models play a crucial role in evaluating the influencing factors in the severity of traffic crashes. In this study, Extremely Randomised Tree (ERT) is used as a machine learning technique to analyse the severity of crashes. The crash data in the province of Khorasan Razavi, Iran, for a period of 5 years from 2013 to 2017, is used for crash severity model development. The dataset includes traffic-related variables, vehicle specifications, vehicle movement, land use characteristics, temporal characteristics, and environmental variables. In this paper, Feature Importance Analysis (FIA), Partial Dependence Plots (PDP), and Individual Conditional Expectation (ICE) plots are utilised to analyse and interpret the results. According to the results, the involvement of vulnerable road users such as motorcyclists and pedestrians alongside traffic-related variables are among the most significant variables in crash severity. Results show that the presence of motorcycles can increase the probability of injury crashes by around 30% and almost double the probability of fatal crashes. Analysing the interaction of PDPs shows that driving speeds above 60 km/h in residential areas raises the probability of injury crashes by about 10%. In addition, at speeds higher than 70 km/h, the presence of pedestrians approximately increases the probability of fatal crashes by 6%. |
first_indexed | 2024-04-12T08:43:31Z |
format | Article |
id | doaj.art-0e63e355d0564bdca88ad1427f8eb9cb |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-12T08:43:31Z |
publishDate | 2022-07-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-0e63e355d0564bdca88ad1427f8eb9cb2022-12-22T03:39:46ZengNature PortfolioScientific Reports2045-23222022-07-0112111910.1038/s41598-022-15693-7Application of Extremely Randomised Trees for exploring influential factors on variant crash severity dataFarshid Afshar0Seyedehsan Seyedabrishami1Sara Moridpour2Faculty of Civil & Environmental Engineering, Tarbiat Modares UniversityFaculty of Civil & Environmental Engineering, Tarbiat Modares UniversityCivil and Infrastructure Engineering Discipline, RMIT UniversityAbstract Crash severity models play a crucial role in evaluating the influencing factors in the severity of traffic crashes. In this study, Extremely Randomised Tree (ERT) is used as a machine learning technique to analyse the severity of crashes. The crash data in the province of Khorasan Razavi, Iran, for a period of 5 years from 2013 to 2017, is used for crash severity model development. The dataset includes traffic-related variables, vehicle specifications, vehicle movement, land use characteristics, temporal characteristics, and environmental variables. In this paper, Feature Importance Analysis (FIA), Partial Dependence Plots (PDP), and Individual Conditional Expectation (ICE) plots are utilised to analyse and interpret the results. According to the results, the involvement of vulnerable road users such as motorcyclists and pedestrians alongside traffic-related variables are among the most significant variables in crash severity. Results show that the presence of motorcycles can increase the probability of injury crashes by around 30% and almost double the probability of fatal crashes. Analysing the interaction of PDPs shows that driving speeds above 60 km/h in residential areas raises the probability of injury crashes by about 10%. In addition, at speeds higher than 70 km/h, the presence of pedestrians approximately increases the probability of fatal crashes by 6%.https://doi.org/10.1038/s41598-022-15693-7 |
spellingShingle | Farshid Afshar Seyedehsan Seyedabrishami Sara Moridpour Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data Scientific Reports |
title | Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data |
title_full | Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data |
title_fullStr | Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data |
title_full_unstemmed | Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data |
title_short | Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data |
title_sort | application of extremely randomised trees for exploring influential factors on variant crash severity data |
url | https://doi.org/10.1038/s41598-022-15693-7 |
work_keys_str_mv | AT farshidafshar applicationofextremelyrandomisedtreesforexploringinfluentialfactorsonvariantcrashseveritydata AT seyedehsanseyedabrishami applicationofextremelyrandomisedtreesforexploringinfluentialfactorsonvariantcrashseveritydata AT saramoridpour applicationofextremelyrandomisedtreesforexploringinfluentialfactorsonvariantcrashseveritydata |