Deciphering Car Crash Dynamics in Greater Melbourne: a Multi-Model Machine Learning and Geospatial Analysis

doi:10.11947/j.JGGS.2024.0404

Abstract

Abstract:

In the continually evolving landscape of data-driven methodologies addressing car crash patterns, a holistic analysis remains critical to decode the complex nuances of this phenomenon. This study bridges this knowledge gap with a robust examination of car crash occurrence dynamics and the influencing variables in the Greater Melbourne area, Australia. We employed a comprehensive multi-model machine learning and geospatial analytics approach, unveiling the complicated interactions intrinsic to vehicular incidents. By harnessing Random Forest with SHAP (Shapley Additive Explanations), GLR (Generalized Linear Regression), and GWR (Geographically Weighted Regression), our research not only highlighted pivotal contributing elements but also enriched our findings by capturing often overlooked complexities. Using the Random Forest model, essential factors were emphasized, and with the aid of SHAP, we accessed the interaction of these factors. To complement our methodology, we incorporated hexagonalized geographic units, refining the granularity of crash density evaluations. In our multi-model study of car crash dynamics in Greater Melbourne, road geometry emerged as a key factor, with intersections showing a significant positive correlation with crashes. The average land surface temperature had variable significance across scales. Socio-economically, regions with a higher proportion of childless populations were identified as more prone to accidents. Public transit usage displayed a strong positive association with crashes, especially in densely populated areas. The convergence of insights from both Generalized Linear Regression and Random Forest's SHAP values offered a comprehensive understanding of underlying patterns, pinpointing high-risk zones and influential determinants. These findings offer pivotal insights for targeted safety interventions in Greater Melbourne, Australia.

Key words: car crash dynamics; hexagonalization; multi-model machine learning; spatial planning intervention

Christopher JOHNSON, ZHOU Heng, Richard TAY, SUN Qian(Chayn). Deciphering Car Crash Dynamics in Greater Melbourne: a Multi-Model Machine Learning and Geospatial Analysis[J]. Journal of Geodesy and Geoinformation Science, 2024, 7(4): 36-55.

Figures/Tables 14

Figure 1

Table 1

Figure 2

Table 2

Figure 3

Table 3

Figure 4

Figure 5

Table 4

Table 5

Figure 6

Table 6

Figure 7

Figure 8

References 26

[1]	World Health Organization. Road traffic injuries[EB/OL]. [2024-01-05]. https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries.
[2]	SUN Qian, XIA Jianhong, FOSTER J, et al. Unpacking older drivers' mobility at roundabouts: their visual-motor coordination through driver-vehicle-environment interactions[J]. International Journal of Sustainable Transportation, 2019, 13(9): 627-638.
[3]	SUN Qian, XIA Jianhong, FOSTER J, et al. A psycho-geoinformatics approach for investigating older adults' driving behaviours and underlying cognitive mechanisms[J]. European Transport Research Review, 2018, 10(2): 36.
[4]	LI Xiang, HUA Yinxin, LIU Wenbing. A method of road data aided inertial navigation by using learning to rank and ICCP algorithm[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4): 84-96. DOI: 10.11947/j.JGGS.2021.0407.
[5]	XU Fulong, LI Zishen, ZHANG Kefei, et al. An investigation of optimal machine learning methods for the prediction of ROTI[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2): 1-15. DOI: 10.11947/j.JGGS.2020.0201.
[6]	DUCKHAM M, SUN Qian, WORBOYS M F. GIS: a computing perspective[M]. 3rd ed. Boca Raton: CRC Press, 2023.
[7]	ASADI M, ULAK M B, GEURS K T, et al. A comprehensive analysis of the relationships between the built environment and traffic safety in the Dutch urban areas[J]. Accident Analysis & Prevention, 2022, 172: 106683.
[8]	DUMBAUGH E, ZHANG Yi. The relationship between community design and crashes involving older drivers and pedestrians[J]. Journal of Planning Education and Research, 2013, 33(1): 83-95.
[9]	ZHOU Heng, NORMAN R, KELOBONYE K, et al. Market segmentation approach to investigate existing and potential aviation markets[J]. Transport Policy, 2020, 99: 120-135.
[10]	ZHOU Heng, CHI Xiaoting, NORMAN R, et al. Tourists' urban travel modes: choices for enhanced transport and environmental sustainability[J]. Transportation Research Part D: Transport and Environment, 2024, 129: 104144.
[11]	AL-MISTAREHI B W, ALOMARI A H, IMAM R, et al. Using machine learning models to forecast severity level of traffic crashes by R Studio and ArcGIS[J]. Frontiers in Built Environment, 2022, 8: 860805.
[12]	TAVRIS D R, KUHN E M, LAYDE P M. Age and gender patterns in motor vehicle crash injuries: Importance of type of crash and occupant role[J]. Accident Analysis & Prevention, 2001, 33(2): 167-172.
[13]	WANG Yubian, ZHANG Wei. Analysis of roadway and environmental factors affecting traffic crash severities[J]. Transportation Research Procedia, 2017, 25: 2119-2125.
[14]	LIU Xin, XIA Jianhong. Locally analysing the risk factors for fatal single vehicle crashes hot spots in Western Australia[J]. International Journal of Crashworthiness, 2015, 20(6): 524-534.
[15]	LEE D, GULDMANN J M, VON RABENAU B. Interactions between the built and socio-economic environment and driver demographics: spatial econometric models of car crashes in the Columbus Metropolitan Area[J]. International Journal of Urban Sciences, 2018, 22(1): 17-37.
[16]	RHEE K A, KIM J K, LEE Y I, et al. Spatial regression analysis of traffic crashes in Seoul[J]. Accident Analysis & Prevention, 2016, 91: 190-199.
[17]	ELYASSAMI S, HAMID Y, HABUZA T. Road crashes analysis and prediction using gradient boosted and random forest trees[C]// Proceedings of the 6th IEEE Congress on Information Science and Technology. Agadir- Essaouira: IEEE, 2020: 2327-1884.
[18]	YU Juanjuan, HE Xiufeng, XU Jia, et al. An edge-assisted, object-oriented random forest approach for refined extraction of tea plantations using multi-temporal Sentinel-2 and high-resolution Gaofen-2 imagery[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(1): 31-46. DOI: 10.11947/j.JGGS.2023.0103.
[19]	ZHOU Heng, SONG Chunyu, CHI Xiaoting, et al. Refining hospitality in a post-pandemic landscape: tourist food choices through a latent class nested logit lens[J]. International Journal of Hospitality Management, 2024, 117: 103652.
[20]	BRIZ-REDÓN Á, MARTÍNEZ-RUIZ F, MONTES F. Investigation of the consequences of the modifiable areal unit problem in macroscopic traffic safety analysis: a case study accounting for scale and zoning[J]. Accident Analysis & Prevention, 2019, 132: 105276.
[21]	MUSSONE L, BASSANI M, MASCI P. Analysis of factors affecting the severity of crashes in urban road intersections[J]. Accident Analysis & Prevention, 2017, 103: 112-122.
[22]	GAO Jinghong, CHEN Xiaojun, WOODWARD A, et al. The association between meteorological factors and road traffic injuries: a case analysis from Shantou city, China[J]. Scientific Reports, 2016, 6(1): 37300.
[23]	EL-BASYOUNY K, BARUA S, ISLAM M T. Investigation of time and weather effects on crash types using full Bayesian multivariate Poisson lognormal models[J]. Accident Analysis & Prevention, 2014, 73: 91-99.
[24]	MURPHY A, XIA Jianhong. Risk analysis of animal-vehicle crashes: a hierarchical Bayesian approach to spatial modelling[J]. International Journal of Crashworthiness, 2016, 21(6): 614-626.
[25]	ELLISON A B, GREAVES S P, BLIEMER M C J. Driver behaviour profiles for road safety analysis[J]. Accident Analysis & Prevention, 2015, 76: 118-132.
[26]	HASANAT-E-RABBI S, HAMIM O F, DEBNATH M, et al. Exploring the relationships between demographics, road safety attitudes, and self-reported pedestrian behaviours in Bang-ladesh[J]. Sustainability, 2021, 13(19): 10640.