A Bayesian belief networks approach to prioritizing road safety mitigation measures for eco-mobility modes
Fatmah Alfeil Alyammahia, Luqman Ali, Md Didarul Alam, Hamad AlJassmi
Abstract. This study presents an innovative decision-making approach that enables the prioritization of road safety measures for eco-mobility users—pedestrians, cyclists and light-electric micromobility riders—in Abu Dhabi. The analysis uses 2,032 eco-mobility crash records from 2020–2023, comprising pedestrian, bicycle, and light electric micro-mobility incidents, supplied by Abu Dhabi Police and the Department of Municipalities and Transport. A supervised Bayesian Belief Network (BBN) was constructed around six empirically estimated variables: visibility, predictability, road curvature, obstructions, lighting and speed limit. Maximum-likelihood conditional-probability tables were derived from the cleaned dataset; Beta priors were applied only where cell counts were sparse. Ten conventional machine-learning models, including Random Forest, Gradient Boosting, Support Vector Machine (SVM) and Long Short-Term Memory (LSTM), were trained on the same features for benchmarking. The BBN achieved the strongest overall results (precision = 0.999; recall = 0.998; R² = 0.998), outperforming all other models by at least four percentage points on F1-score. Scenario analysis showed that maintaining high visibility and high predictability lowers crash probability by 90% whereas sharp curvature and major obstructions are more than triple risk. To translate these probabilistic findings into action, a cost-benefit module estimated benefit-cost ratios for 12 candidate countermeasures. The highest-ranking interventions were 30 km h⁻¹ traffic-calming packages in school and residential zones (median 15% crash reduction; Benefit-cost Ratio (BCR) = 3.7) and targeted enforcement of pedestrian right-of-way laws (12.5% reduction; BCR = 2.9). The combined BBN–economic framework offers Abu Dhabi planners a transparent, data-driven tool for sequencing low-carbon mobility safety investments under budget constraints. Beyond the local case, the methodology can be adapted to other cities that aim to improve soft-mobility safety while progressing toward Vision-Zero objectives.
Keywords
Road Safety, Bayesian Belief Network (BBN), E-Scooters, Cost-Benefit Analysis, Eco-Mobility Modes, Policy Recommendation, Decision-Making
Published online 6/20/2026, 13 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Fatmah Alfeil Alyammahia, Luqman Ali, Md Didarul Alam, Hamad AlJassmi, A Bayesian belief networks approach to prioritizing road safety mitigation measures for eco-mobility modes, Materials Research Proceedings, Vol. 67, pp 475-487, 2026
DOI: https://doi.org/10.21741/9781644904176-63
The article was published as article 63 of the book Climate Action and Sustainability
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] “Micro-mobility solutions: how could they fit in tomorrow’s city?,” Alcimed. Accessed: Sept. 22, 2025. [Online]. Available: https://www.alcimed.com/en/insights/micro-mobility-solutions-in-tomorrow-city/
[2] “UAE recorded over 940 pedestrian accidents last year, rev…” Accessed: Sept. 22, 2025. [Online]. Available: https://www.gulftoday.ae/news/2025/06/04/uae-recorded-over-940-pedestrian-accidents-last-year-reveal-abu-dhabi-police
[3] A. Ramahi, “UAE summer temperatures surge near record highs after hottest ever spring,” Reuters, Aug. 04, 2025. Accessed: Sept. 22, 2025. [Online]. Available: https://www.reuters.com/sustainability/climate-energy/uae-summer-temperatures-surge-near-record-highs-after-hottest-ever-spring-2025-08-04/
[4] “Zero road deaths by 2030,” Khaleej Times. Accessed: Sept. 22, 2025. [Online]. Available: https://www.khaleejtimes.com/uae/transport/zero-road-deaths-by-2030
[5] M. Ismail, S. Alrabaee, K.-K. R. Choo, L. Ali, and S. Harous, “A Comprehensive Evaluation of Machine Learning Algorithms for Web Application Attack Detection with Knowledge Graph Integration,” Mob. Netw. Appl., vol. 29, no. 3, pp. 1008–1037, June 2024. https://doi.org/10.1007/s11036-024-02367-z.
[6] L. Ali, F. Sallabi, W. Khan, F. Alnajjar, and H. Aljassmi, “A Deep Learning-based Multi-model Ensemble Method for Crack Detection in Concrete Structures,” in ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction, Waterloo, Canada: IAARC Publications, 2021, pp. 410–418. Accessed: Sept. 24, 2025. [Online]. Available: https://www.proquest.com/docview/2642457725/abstract/BBB45B086522489FPQ/1
[7] L. Ali, T. Kasetkasem, F. G. Khan, T. Chanwimaluang, and H. Nakahara, “Identification of inpainted satellite images using evalutionary artificial neural network (EANN) and k-nearest neighbor(KNN) algorithm,” in 2017 8th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES), May 2017, pp. 1–6. doi: 10.1109/ICTEmSys.2017.7958765.
[8] L. Ali, F. Alnajjar, M. Swavaf, O. Elharrouss, A. Abd-alrazaq, and R. Damseh, “Evaluating segment anything model (SAM) on MRI scans of brain tumors,” Sci. Rep., vol. 14, no. 1, p. 21659, Sept. 2024. https://doi.org/10.1038/s41598-024-72342-x.
[9] L. Ali, H. AlJassmi, M. Swavaf, W. Khan, and F. Alnajjar, “Rs-net: Residual Sharp U-Net architecture for pavement crack segmentation and severity assessment,” J. Big Data, vol. 11, no. 1, p. 116, Aug. 2024. https://doi.org/10.1186/s40537-024-00981-y.
[10] M. Ismail, S. Alrabaee, S. Harous, and K.-K. R. Choo, “Empirical Evaluations of Machine Learning Effectiveness in Detecting Web Application Attacks,” presented at the Future Access Enablers for Ubiquitous and Intelligent Infrastructures. 7th EAI International Conference, FABULOUS 2023, Bratislava, Slovakia, October 24–26, 2023, Proceedings, Dec. 2023. Accessed: Sept. 24, 2025. [Online]. Available: https://eudl.eu/doi/10.1007/978-3-031-50051-0_8
[11] P. Maghelal, A. H. Ali, E. Azar, R. Jayaraman, and K. Khalaf, “Severity of vehicle-to-vehicle accidents in the UAE: An exploratory analysis using machine learning algorithms,” Heliyon, vol. 9, no. 10, p. e20694, Oct. 2023. https://doi.org/10.1016/j.heliyon.2023.e20694.
[12] L. Ali, S. Harous, N. Zaki, W. Khan, F. Alnajjar, and H. A. Jassmi, “Performance Evaluation of different Algorithms for Crack Detection in Concrete Structures,” in 2021 2nd International Conference on Computation, Automation and Knowledge Management (ICCAKM), Jan. 2021, pp. 53–58. doi: 10.1109/ICCAKM50778.2021.9357717.
[13] D. Banister, “The sustainable mobility paradigm,” Transp. Policy, vol. 15, no. 2, pp. 73–80, Mar. 2008. https://doi.org/10.1016/j.tranpol.2007.10.005.
[14] M. J. Nieuwenhuijsen and H. Khreis, “Car free cities: Pathway to healthy urban living,” Environ. Int., vol. 94, pp. 251–262, Sept. 2016. https://doi.org/10.1016/j.envint.2016.05.032.
[15] “Global status report on road safety 2018.” Accessed: Sept. 24, 2025. [Online]. Available: https://www.who.int/publications/i/item/9789241565684
[16] “Pedestrians-deaths-decreased-by-30-5–in-Abu-Dhabi.” Accessed: Sept. 24, 2025. [Online]. Available: https://www.adpolice.gov.ae/Media Center/News/2021/06/29/Pedestrians-deaths-decreased-by-30-5–in-Abu-Dhabi
[17] “Statistical and Econometric Methods for Transportation Data Analysis -.” Accessed: Sept. 24, 2025. [Online]. Available: https://www.routledge.com/Statistical-and-Econometric-Methods-for-Transportation-Data-Analysis/Washington-Karlaftis-Mannering-Anastasopoulos/p/book/9780367199029?srsltid=AfmBOoqv9_Ov1_pZbjpolqvE5IEWG1XMDW-b0a_up_5ZPFbylDa0Igf7
[18] J. de Oña, R. O. Mujalli, and F. J. Calvo, “Analysis of traffic accident injury severity on Spanish rural highways using Bayesian networks,” Accid. Anal. Prev., vol. 43, no. 1, pp. 402–411, Jan. 2011. https://doi.org/10.1016/j.aap.2010.09.010.
[19] J. Sun and J. Sun, “A dynamic Bayesian network model for real-time crash prediction using traffic speed conditions data,” Transp. Res. Part C Emerg. Technol., vol. 54, pp. 176–186, May 2015. https://doi.org/10.1016/j.trc.2015.03.006.
[20] J. Niyogisubizo et al., “Predicting traffic crash severity using hybrid of balanced bagging classification and light gradient boosting machine,” Intell. Data Anal., vol. 27, no. 1, pp. 79–101, Jan. 2023. https://doi.org/10.3233/IDA-216398.
[21] I. Aldhari, M. Almoshaogeh, A. Jamal, F. Alharbi, M. Alinizzi, and H. Haider, “Severity Prediction of Highway Crashes in Saudi Arabia Using Machine Learning Techniques,” Appl. Sci., vol. 13, no. 1, p. 233, Jan. 2023. https://doi.org/10.3390/app13010233.
[22] W. Wijnen et al., “An analysis of official road crash cost estimates in European countries,” Saf. Sci., vol. 113, pp. 318–327, Mar. 2019. https://doi.org/10.1016/j.ssci.2018.12.004.
[23] B. N. Persaud, R. A. Retting, P. E. Garder, and D. Lord, “Safety Effect of Roundabout Conversions in the United States: Empirical Bayes Observational Before-After Study,” Transp. Res. Rec., vol. 1751, no. 1, pp. 1–8, Jan. 2001. https://doi.org/10.3141/1751-01.
[24] T. Götschi, J. Garrard, and B. Giles-Corti, “Cycling as a Part of Daily Life: A Review of Health Perspectives,” Transp. Rev., vol. 36, no. 1, pp. 45–71, Jan. 2016. https://doi.org/10.1080/01441647.2015.1057877.
[25] R. Johansson, “Vision Zero – Implementing a policy for traffic safety,” Saf. Sci., vol. 47, no. 6, pp. 826–831, July 2009. https://doi.org/10.1016/j.ssci.2008.10.023.
