Artificial Intelligence-Enabled Risk Forecasting in Air Traffic Control: An Interpretable Machine-Learning Framework for Safety Management
Keywords:
Air traffic control, Machine learning, Explainable AI, Safety management systems, Decision-curve analysisAbstract
This study aimed to develop and evaluate a human-interpretable artificial intelligence (AI) model for short-term operational risk forecasting in air traffic control (ATC). To do so, it compared logistic and Poisson regression models with random forest and gradient boosting classifiers using a transparently generated synthetic dataset designed to reflect realistic workload, weather, staffing, and sector complexity conditions. Model performance was assessed through cross-validation, calibration analysis, sensitivity to class imbalance, and decision-curve analysis. Among the tested approaches, gradient boosting achieved the best predictive performance, with an area under the curve of 0.93, and provided the most reliable probability estimates, outperforming the regression-based baseline models. Explainability analysis using Shapley additive explanations showed that the most influential predictors were controller workload, weather severity, sector complexity, and staffing ratio, which is consistent with established human factors theory. Decision-curve analysis also indicated measurable operational benefit at realistic alert thresholds, supporting potential applications in dynamic staffing and flow management. These findings suggest that responsible AI can strengthen safety management systems by providing accurate, transparent, and reproducible risk forecasts while supporting regulatory expectations for documentation, calibration, and interpretability.
References
[EASA] European Union Aviation Safety Agency (2024) EASA artificial intelligence concept paper issue 2 [accessed Sep 15 2025]. https://www.easa.europa.eu/en/document-library/general-publications/easa-artificial-intelligence-concept-paper-issue-2
[FAA] Federal Aviation Administration (2024) Roadmap for artificial intelligence safety assurance [accessed Sep 15 2025]. https://www.faa.gov/aircraft/air_cert/step/roadmap_for_AI_safety_assurance
[ICAO] International Civil Aviation Organization (2025) The impact of artificial intelligence on the aviation sector. Assembly - 42nd Session. [accessed Sep 15 2025]. https://www.icao.int/sites/default/files/Meetings/a42/Documents/WP/wp_389_en.pdf
Abdollahpour N, Moallem M, Narimani M (2025) Real-time safety alerting system for dynamic, safety-critical environments. Automation 6(3):43. https://doi.org/10.3390/automation6030043
Buttaboni C, Floridi L (2025). A taxonomy of AI opacity in the EU: rethinking transparency, traceability, interpretability, and explainability. SSRN. https://doi.org/10.2139/ssrn.5364019
Collen A, Szanto IC, Benyahya M, Genge B, Nijdam NA (2022) Integrating human factors in the visualisation of usable transparency for dynamic risk assessment. Information 13(7):340. https://doi.org/10.3390/info13070340
Degas A, Islam MR, Hurter C, Barua S, Rahman H, Poudel M, Arico P (2022) A survey on artificial intelligence (AI) and explainable AI in air traffic management: current trends and development with future research trajectory. Appl Sci 12(3):1295. https://doi.org/10.3390/app12031295
Dekker S (2011) The field guide to understanding ‘human error’. 2nd ed. Boca Raton: CRC Press.
Delikhoon M, Zarei E, Banda OV, Faridan M, Habibi E (2022) Systems thinking accident analysis models: a systematic review for sustainable safety management. Sustainability 14(10):5869. https://doi.org/10.3390/su14105869
Du S, Zhong G, Wang F, Pang B, Zhang H, Jiao Q (2024) Safety risk modeling and assessment of civil unmanned aircraft system operations: a comprehensive review. Drones 8(8):354. https://doi.org/10.3390/drones8080354
Duan C, Hu M, Yang L, Gao Q (2023) Core competency quantitative evaluation of air traffic controller in multi-post mode. Appl Sci 13(18):10246. https://doi.org/10.3390/app131810246
Eichenseer P, Hans L, Winkler H (2025) A data-driven machine learning model for forecasting delivery positions in logistics for workforce planning. Supply Chain Anal 9:100099. https://doi.org/10.1016/j.sca.2024.100099
Ewertowski T, Berlik M, Sławińska M (2024) The effectiveness of operational residual risk assessment: the case of general aviation organizations in enhancing flight safety in alignment with sustainability. Sustainability 16(23):10606. https://doi.org/10.3390/su162310606
Fulton R, Fulton D, Hayes N, Kaplan S (2024) The transformation risk-benefit model of artificial intelligence: balancing risks and benefits through practical solutions and use cases. arXiv:2406.11863. https://doi.org/10.5121/ijaia.2024.15201
Gu Y, Dou M (2024) Nonlinear and threshold effects on station-level ridership: insights from disproportionate weekday-toweekend impacts. ISPRS Int J Geo-Inf 13(10):365. https://doi.org/10.3390/ijgi13100365
Hassija V, Chamola V, Mahapatra A, Singal A, Goel D, Huang K, Hussain A (2024) Interpreting black-box models: a review on explainable artificial intelligence. Cogn Comput 16(1):45-74. https://doi.org/10.1007/s12559-023-10179-8
Hatıpoğlu I, Tosun O (2024) Predictive modeling of flight delays at an airport using machine learning methods. Appl Sci 14(13):5472. https://doi.org/10.3390/app14135472
Herrmann T, Pfeiffer S (2023) Keeping the organization in the loop: a socio-technical extension of human-centered artificial intelligence. AI Soc 38(4):1523-1542. https://doi.org/10.1007/s00146-022-01391-5
Hollnagel E (2012) FRAM: the functional resonance analysis method: modeling complex socio-technical systems. Farnham: Ashgate Publishing.
Illiashenko O, Kharchenko V, Babeshko I, Fesenko H, Di Giandomenico F (2023) Security-informed safety analysis of autonomous transport systems considering AI-powered cyberattacks and protection. Entropy 25(8):1123. https://doi.org/10.3390/e25081123
Kabashkin I (2024) The iceberg model for integrated aircraft health monitoring based on AI, blockchain, and data analytics. Electronics 13(19):3822. https://doi.org/10.3390/electronics13193822
Kabashkin I, Shoshin L (2024) Artificial intelligence of things as new paradigm in aviation health monitoring systems. Future Internet 16(8):276. https://doi.org/10.3390/fi16080276
Kabir S, Hossain MS, Andersson K (2025) A review of explainable artificial intelligence from the perspectives of challenges and opportunities. Algorithms 18(9):556. https://doi.org/10.3390/a18090556
Khattak A, Chan PW, Chen F, Peng H, Mongina Matara C (2023) Missed approach, a safety-critical go around procedure in aviation: prediction based on machine learning-ensemble imbalance learning. Adv Meteorol 2023(1):9119521. https://doi.org/10.1155/2023/9119521
Kováčiková K, Novák A, Kováčiková M, Novak Sedlackova A (2025) A bibliometric analysis of the impact of extreme weather on air transport operations. Atmosphere 16(6):740. https://doi.org/10.3390/atmos16060740
Loi CL, Wu CC, Liang YC (2024) Prediction of tropical cyclogenesis based on machine learning methods and its SHAP interpretation. J Adv Model Earth Syst 16(3):e2023MS003637. https://doi.org/10.1029/2023MS003637
Ma Y, Xu J, Gao C, Mu M, E G, Gu C (2022) Review of research on road traffic operation risk prevention and control. Int J Environ Res Public Health 19(19):12115. https://doi.org/10.3390/ijerph191912115
Mahbooba B, Timilsina M, Sahal R, Serrano M (2021) Explainable artificial intelligence (XAI) to enhance trust management in intrusion detection systems using decision tree model. Complexity 2021(1):6634811. https://doi.org/10.1155/2021/6634811
Nanyonga A, Wasswa H, Joiner K, Turhan U, Wild G (2025) Explainable supervised learning models for aviation predictions in Australia. Aerospace 12(3):223. https://doi.org/10.3390/aerospace12030223
Nourani M, Roy C, Block JE, Honeycutt DR, Rahman T, Ragan E, Gogate V (2021) Anchoring bias affects mental model formation and user reliance in explainable AI systems. In: Proc 26th Int Conf Intell User Interfaces:340-350. https://doi.org/10.1145/3397481.3450639
Oo KT, Oo KL (2022) Analysis of the most common aviation weather hazard and its key mechanisms over the Yangon flight information region. Adv Meteorol 2022(1):5356563. https://doi.org/10.1155/2022/5356563
Pelosi D, Cacciagrano D, Piangerelli M (2025) Explainability and interpretability in concept and data drift: a systematic literature review. Algorithms 18(7):443. https://doi.org/10.3390/a18070443
Perez-Cerrolaza J, Abella J, Borg M, Donzella C, Cerquides J, Cazorla FJ, et al. (2024) Artificial intelligence for safety-critical systems in industrial and transportation domains: a survey. ACM Comput Surv 56(7):1-40. https://doi.org/10.1145/3626314
Pothana P, Snyder P, Vidhyadharan S, Ullrich M, Thornby J (2025) Air traffic trends and UAV safety: leveraging automatic dependent surveillance-broadcast data for predictive risk mitigation. Aerospace 12(4):284. https://doi.org/10.3390/aerospace12040284
Reason J (1990) Human error. Cambridge: Cambridge University Press.
Reitmann S, Schultz M (2022) An adaptive framework for optimization and prediction of air traffic management (sub-) systems with machine learning. Aerospace 9(2):77. https://doi.org/10.3390/aerospace9020077
Rodrigues RB. KunturSat: AI-enabled risk forecasting in air traffic control [supplementary material]. Mendeley Data; 2025. https://doi.org/10.17632/74ktzghth6.1
Romeo G, Conti D (2025) Exploring automation bias in human-AI collaboration: a review and implications for explainable AI. AI Soc 1-20. https://doi.org/10.1007/s00146-025-02422-7
Susanu CA, Raibulet C, Alam S, Lulli G (no date) Machine learning in air traffic management for trajectory optimization and aviation safety-a systematic literature review. SSRN. https://doi.org/10.2139/ssrn.5256104
Taheri M, Bigdeli M, Imanian H, Mohammadian A (2025) An overview of evapotranspiration estimation models utilizing artificial intelligence. Water 17(9):1384. https://doi.org/10.3390/w17091384
Thekkekara JP, Yongchareon S, Liesaputra V (2024) An attention-based CNN-BiLSTM model for depression detection on social media text. Expert Syst Appl 249:123834. https://doi.org/10.1016/j.eswa.2024.123834
Wiggerthale J, Reich C (2024) Explainable machine learning in critical decision systems: ensuring safe application and correctness. AI 5(4):2864-2896. https://doi.org/10.3390/ai5040138
Zhang C, Liu C, Liu H, Jiang C, Fu L, Wen C, Cao W (2022) Incorporation of pilot factors into risk analysis of civil aviation accidents from 2008 to 2020: a data-driven Bayesian network approach. Aerospace 10(1):9. https://doi.org/10.3390/aerospace10010009
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Raul Bonadia Rodrigues, Cory Michael Creen
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons — Attribution 4.0 International — CC BY 4.0. Authors are free to Share (copy and redistribute the material in any medium or format) and Adapt (remix, transform, and build upon the material for any purpose, even commercially). JATM allow the authors to retain publishing rights without restrictions.
