Abstract
Airport construction under non-stop operations presents unique safety challenges due to complex multi-factor interactions that traditional qualitative methods cannot adequately address. To address this, a study was conducted on 412 construction events (comprising 103 risk incidents and 309 routine events) at a major international hub airport between 2019 and 2024. First, a risk factor system encompassing six key categories, including personnel, environment, equipment, management, facilities, and operations, was developed, represented by 42 indicator variables. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Subsequently, the XGBoost classifier was trained, achieving an accuracy of 92.7%, an Area Under the Curve (AUC) of 0.875, and a recall rate of 85.7%. For model interpretability, SHapley Additive exPlanations (SHAP) values were utilized to quantify feature contributions and elucidate the risk transmission mechanism. Five core risk factors were identified: flight density, visibility, the timeliness of NOTAM release, peak hours, and the experience of construction personnel. Key thresholds were determined: flight density of 35 flights per hour, visibility of 3 km, and a 2-h delay in NOTAM release. SHAP analysis evaluated the synergy of operational pressure variables. These findings provide a foundation for integration into operational risk warning systems, supporting differentiated risk management and offering a data-driven approach to balancing efficiency with construction safety.
Similar content being viewed by others
Data availability
All relevant data are within the manuscript. The coding data and statistical analysis results are available upon request from the corresponding author.
Code availability
The custom code for the XGBoost-based risk prediction model, including data preprocessing, model training, hyperparameter optimization, and SHAP analysis scripts, was developed using Python (version 3.9 or above) with the following core packages: XGBoost (≥ 2.1), scikit-learn (≥ 1.5), imbalanced-learn (≥ 0.13), and SHAP (≥ 0.46). The source code is publicly available on GitHub at https://github.com/XianYang7602/airport-construction-risk-prediction and has been archived in Zenodo (https://doi.org/10.5281/zenodo.19058727).
References
Circular, A. & No, A. 150/5370-2G Operational Safety on Airports during Construction. US Department of Transportation, Federal Aviation Administration (2017).
Dizdar, E. N. & Ünver, M. The assessment of occupational safety and health in Turkey by applying a decision-making method; MULTIMOORA. Hum. Ecol. Risk Assess. 26, 1693–1704. https://doi.org/10.1080/10807039.2019.1600399 (2019).
Council, I. C. A. O. Annex 19 to the Convention on International Civil Aviation: Safety Management. (International Civil Aviation Organization, 2013).
Sipos, A. in International Aviation Law: Regulations in Three Dimensions 139–202 (Springer, 2024). https://doi.org/10.1007/978-3-031-39066-1
Doc, I. 9859 Safety Management Manual. International Civil Aviation Organization, Montreal, Canada (2018).
Dizdar, E. N. & Koçar, O. Evaluation of risks of OSH management system with artificial neural networks. Acad. Platform-J. Eng. Sci. 6, 73–83. https://doi.org/10.21541/apjes.426502 (2018).
Dizdar, E. N. & Koçar, O. Artificial neural network-based risk assessment for occupational accidents in the shipbuilding industry in Turkey. Neural Comput. Appl. 36, 20457–20471. https://doi.org/10.1007/s00521-024-10292-1 (2024).
Alharasees, O., Rohacs, D., Muller, A. & Kale, U. Towards greener skies: Evaluating sustainable aviation fuel alternatives. Geo J. Tour. Geosites 59, 551–562. https://doi.org/10.30892/gtg.59204-1436 (2025).
Wiegmann, D. A. & Shappell, S. A. Human error analysis of commercial aviation accidents: Application of the Human Factors Analysis and Classification System (HFACS). Aviat. Space Environ. Med. 72, 1006–1016 (2001).
Alharasees, O., Rohacs, D. & Kale, U. Aviation MRO operators assessment by SHELL model. In: Novel Techniques in Maintenance, Repair, and Overhaul, Springer (2024). https://doi.org/10.1007/978-3-031-42041-2_20
Wu, Y., Zhang, S., Zhang, X., Lu, Y. & Xiong, Z. Analysis on coupling dynamic effect of human errors in aviation safety. Accid. Anal. Prev. 192, 107277. https://doi.org/10.1016/j.aap.2023.107277 (2023).
Alharasees, O. & Kale, U. Human factors and AI in UAV systems: Enhancing operational efficiency through AHP and real-time physiological monitoring. J. Intell. Rob. Syst. 111, 5. https://doi.org/10.1007/s10846-024-02188-y (2024).
Zolfaghari, F., Alharasees, O., Kilikevičius, A., & Kale, U. Adaptive pilot monitoring: unsupervised artifact detection and atypical state identification in multimodal physiological signals. In 2025 New Trends in Aviation Development (NTAD) (2025). https://doi.org/10.1109/NTAD67887.2025.11302625
Alharasees, O., Kilikevičius, A. & Kale, U. Real-flight monitoring of vital physiological parameters in pilots: implications for performance, training, and safety in aviation. in Proceedings of the 4th Cognitive Mobility Conference. COGMOB 2025 (eds Zöldy, M., Szászi, I., Balasubramanian, D. & Török, Á.) Lecture Notes in Networks and Systems, vol. 1768, 139–148 (Springer, 2026). https://doi.org/10.1007/978-3-032-13898-9_33
Chen, N., Sun, Y., Wang, Z. & Peng, C. Identification of flight accidents causative factors base on SHELLO and improved entropy gray correlation method. Heliyon (2023). https://doi.org/10.1016/j.heliyon.2023.e16484
Boyd, D. D. In-flight decision-making by general aviation pilots operating in areas of extreme thunderstorms. Aerosp. Med. Hum. Perform. 88, 1066–1072. https://doi.org/10.3357/AMHP.4932.2017 (2017).
Demir, G., Moslem, S. & Duleba, S. Artificial intelligence in aviation safety: Systematic review and biometric analysis. Int. J. Comput. Intell. Syst. 17, 279. https://doi.org/10.1007/s44196-024-00671-w (2024).
Tikayat Ray, A., Misra, A., Olive, X. & Cuadra, C. Natural language processing (NLP) in aviation safety: Systematic review of research and outlook into the future. Aerospace 10, 600. https://doi.org/10.3390/aerospace10070600 (2023).
Akay, T. & Tarhan, C. The effect of global warming and climate changes on aircraft accidents between 2010–2022. Aircr. Eng. Aerosp. Technol. 96, 215–222. https://doi.org/10.1108/AEAT-03-2023-0081 (2024).
Kwasiborska, A., Grabowski, M., Sedláčková, A. N. & Novák, A. The influence of visibility on the opportunity to perform flight operations with various categories of the instrument landing system. Sensors 23, 7953 (2023).
Al-Ghzawi, M. & El-Rayes, K. Machine learning for predicting the impact of construction activities on air traffic operations during airport expansion projects. Autom. Constr. 158, 105189. https://doi.org/10.1016/j.autcon.2023.105189 (2024).
Gondia, A., Moussa, A., Ezzeldin, M. & El-Dakhakhni, W. Machine learning-based construction site dynamic risk models. Technol. Forecast. Soc. Change 189, 122347. https://doi.org/10.1016/j.techfore.2023.122347 (2023).
Zhang, X., Zhong, S. & Mahadevan, S. Airport surface movement prediction and safety assessment with spatial–temporal graph convolutional neural network. Transp. Res. Part C Emerg. Technol. 144, 103873. https://doi.org/10.1016/j.trc.2022.103873 (2022).
Eleimat, M., Alharasees, O. & Őszi, A. Advancements in airport security technologies: A patent analysis. In: 2024 Mediterranean Smart Cities Conference (MSCC), IEEE (2024). https://doi.org/10.1109/MSCC62288.2024.10696990
Alharasees, O., Kale, U., Rohacs, J. & Rohacs, D. Renewable energy systems for airports and aerodromes: A comprehensive patent review and technological analysis. In The Future of Electric Aviation and Artificial Intelligence (eds Karakoc, T. H. et al.) 139–144 (Springer, 2025). https://doi.org/10.1007/978-3-031-62094-2_21.
Chen, T. & Guestrin, C. XGBoost: A scalable tree boosting system. in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785–794 (Association for Computing Machinery, 2016). https://doi.org/10.1145/2939672.2939785
Bentéjac, C., Csörgő, A. & Martínez-Muñoz, G. A comparative analysis of gradient boosting algorithms. Artif. Intell. Rev. 54, 1937–1967. https://doi.org/10.1007/s10462-020-09896-5 (2021).
Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357. https://doi.org/10.1613/jair.953 (2002).
Imani, M., Beikmohammadi, A. & Arabnia, H. R. Comprehensive analysis of random forest and XGBoost performance with SMOTE, ADASYN, and GNUS under varying imbalance levels. Technologies 13, 88. https://doi.org/10.3390/technologies13030088 (2025).
Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56–67. https://doi.org/10.1038/s42256-019-0138-9 (2020).
Li, X. et al. SHAP-driven insights into multimodal data: Behavior phase prediction for industrial safety applications. Sci. Rep. 15, 34965. https://doi.org/10.1038/s41598-025-18889-9 (2025).
Breiman, L. Random forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324 (2001).
Efron, B. & Tibshirani, R. J. An Introduction to the Bootstrap (Chapman & Hall, 1993). https://doi.org/10.1201/9780429246593.
Tixier, A.J.-P., Hallowell, M. R., Rajagopalan, B. & Bowman, D. Application of machine learning to construction injury prediction. Autom. Constr. 69, 102–114. https://doi.org/10.1016/j.autcon.2016.05.016 (2016).
Baker, H., Hallowell, M. R. & Tixier, A.J.-P. AI-based prediction of independent construction safety outcomes from universal attributes. Autom. Constr. 118, 103146. https://doi.org/10.1016/j.autcon.2020.103146 (2020).
Kang, K. & Ryu, H. Predicting types of occupational accidents at construction sites in Korea using random forest model. Saf. Sci. 120, 226–236. https://doi.org/10.1016/j.ssci.2019.06.034 (2019).
Liu, H., Hu, M. & Yang, L. A new risk level identification model for aviation safety. Eng. Appl. Artif. Intell. 136, 108901. https://doi.org/10.1016/j.engappai.2024.108901 (2024).
Nanyonga, A., Turhan, U. & Wild, G. A systematic review of machine learning analytic methods for aviation accident research. Sci 7, 124. https://doi.org/10.3390/sci7030124 (2025).
Matharaarachchi, S., Domaratzki, M. & Muthukumarana, S. Enhancing SMOTE for imbalanced data with abnormal minority instances. Mach. Learn. Appl. 18, 100597. https://doi.org/10.1016/j.mlwa.2024.100597 (2024).
Elreedy, D., Atiya, A. F. & Kamalov, F. A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Mach. Learn. 113, 4903–4923. https://doi.org/10.1007/s10994-022-06296-4 (2024).
Fultz, A. J. & Ashley, W. S. Fatal weather-related general aviation accidents in the United States. Phys. Geogr. 37, 291–312. https://doi.org/10.1080/02723646.2016.1211854 (2016).
Muschalik, M. et al. Shapiq: Shapley interactions for machine learning. Adv. Neural Inf. Process. Syst. 37, 130324–130357. https://doi.org/10.52202/079017-4141 (2024).
Hajian-Tilaki, K. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian J. Intern. Med. 4, 627 (2013).
Grinsztajn, L., Oyallon, E. & Varoquaux, G. Why do tree-based models still outperform deep learning on typical tabular data?. Adv. Neural Inf. Process. Syst. 35, 507–520. https://doi.org/10.48550/arXiv.2207.08815 (2022).
Shwartz-Ziv, R. & Armon, A. Tabular data: Deep learning is not all you need. Inf. Fusion 81, 84–90. https://doi.org/10.1016/j.inffus.2021.11.011 (2022).
LemaÃŽtre, G., Nogueira, F. & Aridas, C. K. Imbalanced-learn: A Python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18, 1–5. https://doi.org/10.48550/arXiv.1609.06570 (2017).
Molnar, C. Interpreting machine learning models with SAP: A guide with python examples and theory on Shapley values. (Chistoph Molnar c/o MUCBOOK, Heidi Seibold, 2023).
Arrieta, A. B. et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115. https://doi.org/10.1016/j.inffus.2019.12.012 (2020).
Poh, C. Q., Ubeynarayana, C. U. & Goh, Y. M. Safety leading indicators for construction sites: A machine learning approach. Autom. Constr. 93, 375–386. https://doi.org/10.1016/j.autcon.2018.03.022 (2018).
Liu, J., Luo, H. & Liu, H. Deep learning-based data analytics for safety in construction. Autom. Constr. 140, 104302. https://doi.org/10.1016/j.autcon.2022.104302 (2022).
Alharasees, O. & Kale, U. Selection of sustainable aviation fuels: An expert-based comparative approach. In International Symposium On Sustainable Aviation. 43–49 (Springer, 2025). https://doi.org/10.1007/978-3-031-70694-3_9
Malekloo, A., Liu, X. C. & Sacharny, D. AI‐enabled airport runway pavement distress detection using dashcam imagery. Comput. Aided Civ. Infrastruct. Eng. 39, 2481–2499. https://doi.org/10.1111/mice.13200 (2024).
Kirwan, B. The impact of artificial intelligence on future aviation safety culture. Future Transp. 4, 349–379. https://doi.org/10.3390/futuretransp4020018 (2024).
Funding
The authors received no specific funding for this work.
Author information
Authors and Affiliations
Contributions
X.Y. conceived and designed the study, collected and analyzed the data, developed the machine learning models, interpreted the results, and wrote the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Yang, X. Machine learning model for multi-factor risk prediction in airport construction under non-stop operations. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45250-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45250-5
