This study addresses the critical issue of road safety in urban environments, with a specific focus on the Greater London Area. Utilizing a novel, theory-driven approach, the study investigates the multifaceted impact of urban fabric factors on road safety, operationalized through a severity-weighted index of road accident frequency per capita. Through factorial analysis, six key factors (Urban Integration, Socioeconomic Challenges, Urban Amenities, Commuter Patterns, Housing and Mobility Barriers, and Major Urban Infrastructure) are identified. These factors are examined in relation to road safety using a structural equation model to uncover theoretical relationships, which inform predictive modeling with an XGBoost machine learning framework, enhanced by SHAP value analysis. Our findings reveal significant insights into the interplay between urban physical and social environments and road safety, revealing that integrated urban development strategies—encompassing improved urban integration, enhanced sustainable density, robust infrastructure development, alleviation of socioeconomic disparities, fostering of local employment, and integration of residents with transportation—are imperative for increasing road safety.
AbdallaIMBarkerDRaesideR (1997) Road accident characteristics and socio-economic deprivation. Traffic Engineering and Control38(12): 672–676.
2.
AbdulmawjoudAAJamelMGAl-TaeiAA (2021) Traffic flow parameters development modelling at traffic calming measures located on arterial roads. Ain Shams Engineering Journal12(1): 437–444.
3.
AhmedSHossainMDARaySK, et al. (2023) A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance. Transportation Research Interdisciplinary Perspectives19: 100814.
4.
Aldala’inSAAbdul SukorNSObaidatMT, et al. (2023) Road accident hotspots on Jordan’s highway based on geometric designs using structural equation modeling. Applied Sciences13(14): 8095.
5.
AliYHussainFIrfanM, et al. (2021) An eXtreme Gradient Boosting model for predicting dynamic modulus of asphalt concrete mixtures. Construction and Building Materials295: 123642.
6.
AlonsoW (1964) Location and Land Use: Toward a General Theory of Land Rent. Cambridge: Harvard University Press.
AndersonTK (2009) Kernel density estimation and K-means clustering to profile road accident hotspots. Accident Analysis & Prevention41(3): 359–364.
9.
BentoAMCropperMLMobarakAM, et al. (2005) The effects of urban spatial structure on travel demand in the United States. The Review of Economics and Statistics87(3): 466–478.
10.
BocarejoJPVelasquezJMDíazCA, et al. (2012) Impact of bus rapid transit systems on road safety: lessons from Bogotá, Colombia. Transportation Research Record2317(1): 1–7.
11.
BustosCRhoadsDLapedrizaA, et al. (2022) Predicting the impact of urban change in pedestrian and road safety. arXiv preprint arXiv:2202.01781.
12.
ChenTGuestrinC (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining,785–794.
DumbaughERaeR (2009) Safe urban form: revisiting the relationship between community design and traffic safety. Journal of the American Planning Association75(3): 309–329.
15.
EdererDJPanikRTBotchweyN, et al. (2023) The Safe Systems Pyramid: a new framework for traffic safety. Transportation Research Interdisciplinary Perspectives21: 100905.
16.
EwingRDumbaughE (2009) The built environment and traffic safety: a review of empirical evidence. Journal of Planning Literature23(4): 347–367.
17.
EwingRSchieberRAZegeerCV (2003) Urban sprawl as a risk factor in motor vehicle occupant and pedestrian fatalities. American Journal of Public Health93(9): 1541–1545.
18.
FanCChenMWangX, et al. (2021) A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data. Frontiers in Energy Research9: 29.
19.
FayazMAbadiAKhodakarimS, et al. (2020) The Data-Driven Pattern for Healthy Behaviors of Car Drivers Based on Daily Records of Traffic Count Data from 2018 to 2019 Near Airports. A Functional Data Analysis.
20.
Gálvez-PérezDGuiraoBOrtuñoA, et al. (2022) The influence of built environment factors on elderly pedestrian road safety in cities: the experience of Madrid. International Journal of Environmental Research and Public Health19(4): 2280.
21.
GhadiMQTörökÁ (2021) Evaluation of the impact of spatial and environmental accident factors on severity patterns of road segments. Periodica Polytechnica Transportation Engineering49(2): 146–155.
22.
GibberdF (1982) Harlow: the design of a new town. Town Planning Review53(1): 29.
23.
GolobTF (2003) Structural equation modeling for travel behavior research. Transportation Research Part B: Methodological37(1): 1–25.
GrundyCSteinbachREdwardsP, et al. (2009) Effect of 20 mph traffic speed zones on road injuries in London, 1986-2006: Controlled interrupted time series analysis. BMJ339: b4469.
26.
GurerTK (2012). A theory for sustainability of townscape: typomorphology. In Green and Ecological Technologies for Urban Planning: Creating Smart Cities (pp. 293–308). Hershey: IGI Global, 1418–1432.
27.
HairJFBlackWCBabinBJ, et al. (2010) Advanced diagnostics for multiple regression: a supplement to multivariate data analysis. Advanced Diagnostics for Multiple Regression: A Supplement to Multivariate Data Analysis. Englewood Cliffs, NJ: Prentice Hall.
28.
HillBD (2011) Sequential Kaiser-meyer-olkin Procedure as an Alternative for Determining the Number of Factors in Common-factor Analysis: a Monte Carlo Simulation. Oklahoma State University ProQuest Dissertation & Theses.
29.
HullRBLamMVigoG (1994) Place identity: symbols of self in the urban fabric. Landscape and Urban Planning28(2–3): 109–120.
30.
JonesDJhaMK (2010) The effect of urban form on traffic accident incidence. Recent Advances in Computer Engineering and Applications. Cambridge, MA: Harvard University, 212–222.
31.
JordahlKVan den BosscheJFleischmannM, et al. (2020) geopandas/geopandas: v0.8.1 (Version v0.8.1). Zenodo. doi: 10.5281/zenodo.3946761.
32.
KandoganYJohnsonSD (2016) Role of economic and political freedom in the emergence of global middle class. International Business Review25(3): 711–725.
33.
KarjalainenLETiituMLyytimäkiJ, et al. (2023) Going carless in different urban fabrics: socio-demographics of household car ownership. Transportation50(1): 107–142.
34.
KassuAHasanM (2020) Factors associated with traffic crashes on urban freeways. Transportation Engineering2: 100014.
35.
KhanAGajbhiyeN (2022) Survey based road safety analysis to understand the perspective of the general public. International Journal of Life Science and Pharma Research12(1): L32–37.
36.
KlemL (1995) Path Analysis. Reading and understanding multivariate statistics. Worcester, MA: American Psychological Association, 65–97.
37.
KrierRRoweC (1979) Urban Space. London: Academy Editions, 17.
38.
LeeJChaeJYoonT, et al. (2018) Traffic accident severity analysis with rain-related factors using structural equation modeling – a case study of Seoul City. Accident Analysis & Prevention112: 1–10.
39.
LiYChengHZengZ, et al. (2021, September) Autonomous vehicles drive into shared spaces: ehmi design concept focusing on vulnerable road users. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), Indianapolis, IN, 19–22 September 2021. IEEE, 1729–1736.
40.
LiuMXuYHuY, et al. (2014) A century of the evolution of the urban area in Shenyang, China. PLoS One9(6): e98847.
41.
LinDAllanACuiJ, et al. (2015) The impact of polycentric urban development on commuting behaviour in urban China: Evidence from four sub-centres of Beijing. Habitat International50: 195–205.
42.
LiuJDasSKhanMN (2024) Decoding the impacts of contributory factors and addressing social disparities in crash frequency analysis. Accident Analysis & Prevention194: 107375.
43.
McCartyDKimHW (2024) Risky behaviors and road safety: an exploration of age and gender influences on road accident rates. PLoS One19(1): e0296663.
44.
MehtaKJainSAgarwalA, et al., (2022). Road Accident Prediction Using Xgboost, 2022 International Conference on Emerging Techniques in Computational Intelligence (ICETCI), Hyderabad, India, 2022, pp. 50–56.
45.
MeshcheryakovGIgolkinaAASamsonovaMG (2021) Semopy 2: a structural equation modeling package with random effects in python. arXiv preprint arXiv:2106.01140.
46.
ModipaM (2023). Road traffic accidents in South Africa: challenges and solutions. International Journal of Research in Business and Social Science (2147–4478), 12(8), 557-565.
47.
MofolasayoA (2024) Towards ‘vision-zero’ in road traffic fatalities: the need for reasonable degrees of automation to complement human efforts in driving operation. Systems12(2): 40.
48.
MohanD (2008) Traffic safety and city structure: lessons for the future. Salud Publica de Mexico50(suppl 1): s93–s100.
49.
NaumannRBSandtLKumferW, et al. (2020) Systems thinking in the context of road safety: can systems tools help us realize a true “Safe Systems” approach?Current Epidemiology Reports7: 343–351.
50.
NolandRBQuddusMA (2004) A spatially disaggregate analysis of road casualties in England. Accident Analysis & Prevention36(6): 973–984.
51.
ParkKHwangSSLeeJS, et al. (2010) Individual and areal risk factors for road traffic injury deaths: nationwide study in South Korea. Asia-Pacific Journal of Public Health22(3): 320–331.
52.
ParsaABMovahediATaghipourH, et al. (2020) Toward safer highways, application of XGBoost and shap for real-time accident detection and feature analysis. Accident Analysis & Prevention136: 105405.
53.
PedregosaFVaroquauxGGramfortA, et al. (2011) Scikit-learn: machine learning in Python. The Journal of Machine Learning Research12: 2825–2830.
54.
PezeshknejadPRowangouldD (2024) Evaluating safety and compliance of pedestrian crossings in rural contexts: a before and after study of RRFBs and LED-embedded signs. Accident Analysis & Prevention198: 107462.
55.
ProshanskyHM (1983) Place identity: physical world socialisation of the self. Journal of Environmental Psychology3: 299–313.
56.
QianKLiY (2023) Safer traffic recovery from the pandemic in London–spatiotemporal data mining of car crashes. Applied Spatial Analysis and Policy17: 1–27.
57.
RinghandMVollrathM (2019) Effect of complex traffic situations on route choice behaviour and driver stress in residential areas. Transportation Research Part F: Traffic Psychology and Behaviour60: 274–287.
58.
RothenfluhMMenendezM (2016) Application of a network safety management tool in urban areas: Zurich, Switzerland, case study. Transportation Research Record2582(1): 34–41.
59.
SempleTRodriguesLHarveyJ, et al. (2024) An empirical critique of the low income low energy efficiency approach to measuring fuel poverty. Energy Policy186: 114014.
60.
Serrano-LópezRLinares-UnamunzagaA (2021) Connections between mobility and urban fabrics in the city of Burgos (Spain). Transportation Research Procedia58: 95–102.
61.
SheykhfardAHaghighiFPapadimitriouE, et al. (2021) Review and assessment of different perspectives of vehicle-pedestrian conflicts and crashes: passive and active analysis approaches. Journal of Traffic and Transportation Engineering8(5): 681–702.
62.
StojanovskiT (2018, April). What explains neighborhood type statistically? Mixing typo-morphological and spatial analytic approaches in urban morphology. In 24th ISUF International Conference. Book of Papers. Editorial Universitat Politècnica de València, 1265–1272.
63.
StojanovskiT (2019) Swedish typo-morphology–morphological conceptualizations and implication for urban design. ICONARP International Journal of Architecture and Planning7: 135–157.
64.
SufianMAVaradarajanJ (2023) Enhancing prediction and analysis of UK road traffic accident severity using AI: integration of machine learning, econometric techniques, and time series forecasting in public health research. arXiv preprint arXiv:2309.13483.
TaherdoostHSahibuddinSJalaliyoonN (2022) Exploratory factor analysis; concepts and theory. Advances in Applied and Pure Mathematics27: 375–382.
67.
TobiasSCarlsonJE (1969) Brief report: Bartlett's test of sphericity and chance findings in factor analysis. Multivariate Behavioral Research4(3): 375–377.
68.
Vorko-JovićAKernJBiloglavZ (2006) Risk factors in urban road traffic accidents. Journal of Safety Research37(1): 93–98.
69.
WhitehandJWRMortonNJ (2003) Fringe belts and the recycling of urban land: an academic concept and planning practice. Environment and Planning B: Planning and Design30(6): 819–839.
70.
WhitehandJWRSamuelsIConzenMP (2009) Conzen, Mrg 1960: Alnwick, Northumberland: A Study in Town-Plan Analysis. Institute of British Geographers Publication 27. London: George Philip. Progress in Human Geography 33(6): 859–864.
71.
WongCZhengWQiaoM (2020) Urban expansion and neighbourhood commuting patterns in the Beijing metropolitan region: a multilevel analysis. Urban Studies57(13): 2773–2793.
72.
ZiakopoulosAYannisG (2020) A review of spatial approaches in road safety. Accident Analysis & Prevention135: 105323.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
