Aviation accident and incident forecasting combining occurrence investigation and meteorological data using machine learning
Abstract
Studies on safety in aviation are necessary for the development of new technologies to forecast and prevent aeronautical accidents and incidents. When predicting these occurrences, the literature frequently considers the internal characteristics of aeronautical operations, such as aircraft telemetry and flight procedures, or external characteristics, such as meteorological conditions, with only few relationships being identified between the two. In this study, data from 6,188 aeronautical occurrences involving accidents, incidents, and serious incidents, in Brazil between January 2010 and October 2021, as well as meteorological data from two automatic weather stations, totaling more than 2.8 million observations, were investigated using machine learning tools. For data analysis, decision tree, extra trees, Gaussian naive Bayes, gradient boosting, and k-nearest neighbor classifiers with a high identification accuracy of 96.20% were used. Consequently, the developed algorithm can predict occurrences as functions of operational and meteorological patterns. Variables such as maximum take-off weight, aircraft registration and model, and wind direction are among the main forecasters of aeronautical accidents or incidents. This study provides insight into the development of new technologies and measures to prevent such occurrences.
Keyword : air transport, artificial intelligence, aviation accident, aviation incident, innovation, machine learning, safety
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Aeronautical Accident Investigation and Prevention Center. (2019). Final Report A – 036/CENIPA/2019. http://sistema.cenipa.aer.mil.br/cenipa/paginas/relatorios/rf/en/PROCW_03MAR2019_AC.ING..pdf
Aeronautical Accident Investigation and Prevention Center. (2013). Final Report I – 235/CENIPA/2013. http://sistema.cenipa.aer.mil.br/cenipa/paginas/relatorios/rf/en/RF_I-235CENIPA2013_A6EWI_Englis_Version.pdf
Aeronautical Accident Investigation and Prevention Center. (2021). Ocorrências aeronáuticas na aviação civil brasileira. https://www2.fab.mil.br/cenipa/index.php/estatisticas
Air Navigation Management Center. (2022) Portal Operacional. CGNA. http://portal.cgna.decea.mil.br/
Ahmadi, N., Romoser, M., & Salmon, C. (2022). Improving the tactical scanning of student pilots: A gaze-based training intervention for transition from visual flight into instrument meteorological conditions. Applied Ergonomics, 100, 103642. https://doi.org/10.1016/j.apergo.2021.103642
Alves, C. J. P., Silva, E. J., Müller, C., Borille, G. M. R., Guterres, M. X., Arraut, E. M., Peres, M. S., & Santos, R. J. (2020). Towards an objective decision-making framework for regional airport site selection. Journal of Air Transport Management, 89, 101888. https://doi.org/10.1016/j.jairtraman.2020.101888
Bandeira, M. C. G. S. P., Correia, A. R., & Martins, M. R. (2018). General model analysis of aeronautical accidents involving human and organizational factors. Journal of Air Transport Management, 69, 137–146. https://doi.org/10.1016/j.jairtraman.2018.01.007
Barua, L., & Zou, B. (2021). Planning maintenance and rehabilitation activities for airport pavements: A combined supervised machine learning and reinforcement learning approach. International Journal of Transportation Science and Technology, 11(2), 423–435. https://doi.org/10.1016/j.ijtst.2021.05.006
Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
Caetano, M., Silva, E. J., Vieira, D. J., Alves, C. J. P., & Müller, C. (2022). Criteria prioritization for investment policies in General Aviation aerodromes. Regional Science Policy & Practice, 14(6), 211–233. https://doi.org/10.1111/rsp3.12538
Choi, S., & Kim, Y. J. (2021). Artificial neural network models for airport capacity prediction. Journal of Air Transport Management, 97, 102146. https://doi.org/10.1016/j.jairtraman.2021.102146
Dalmau, R., Ballerini, F., Naessens, H., Belkoura, S., & Wangnick, S. (2021). An explainable machine learning approach to improve take-off time predictions. Journal of Air Transport Management, 95, 102090. https://doi.org/10.1016/j.jairtraman.2021.102090
Gosling, G. D. (1987). Identification of artificial intelligence applications in air traffic control. Transportation Research Part A: General, 21(1), 27–38. https://doi.org/10.1016/0191-2607(87)90021-5
Herrema, F., Curran, R., Hartjes, S., Ellejmi, M., Bancroft, S., & Schultz, M. (2019). A machine learning model to predict runway exit at Vienna airport. Transportation Research Part E: Logistics and Transportation Review, 131, 329–342. https://doi.org/10.1016/j.tre.2019.10.002
International Civil Aviation Organization. (2020). Annex 13 – Aircraft Accident and Incident Investigation (12th ed.). ICAO.
Instituto Nacional de Meteorologia. (2021). Histórico de dados meteorológico. https://portal.inmet.gov.br/
Martins, A. P. G. (2016). A review of important cognitive concepts in aviation. Aviation, 20(2), 65–84. https://doi.org/10.3846/16487788.2016.1196559
Medvedev, A. (2013). Airplane catastrophe as a result of operational errors and violations. Aviation, 17(2), 70–75. https://doi.org/10.3846/16487788.2013.805866
Pacheco, Jr., G., Camargo, M., & Halawi, L. (2020). An evaluation of the operational restrictions imposed to Congonhas airport by civil aviation instruction 121-1013. International Journal of Aviation, Aeronautics, and Aerospace, 7(2).
Patriarca, R., Di Gravio, G., Cioponea, R., & Licu, A. (2022). Democratizing business intelligence and machine learning for air traffic management safety. Safety Science, 146, 105530. https://doi.org/10.1016/j.ssci.2021.105530
Post, J. (2021). The next generation air transportation system of the United States: Vision, accomplishments, and future directions. Engineering, 7(4), 427–430. https://doi.org/10.1016/j.eng.2020.05.026
Puranik, T. G., & Mavris, N. (2018). Anomaly detection in general-aviation operations using energy metrics and flight-data records. Journal of Aerospace Information Systems, 15(1), 22–35. https://doi.org/10.2514/1.I010582
Puranik, T. G., & Mavris, N. (2020). Identification of instantaneous anomalies in general aviation operations using energy metrics. Journal of Aerospace Information Systems, 17(1), 51–65. https://doi.org/10.2514/1.I010772
Puranik, T. G., Rodriguez, N., & Mavris, N. (2020). Towards online prediction of safety-critical landing metrics in aviation using supervised machine learning. Transportation Research Part C: Emerging Technologies, 120, 102819. https://doi.org/10.1016/j.trc.2020.102819
Rodríguez-Sanz, A., Comendador, F. G., Valdés, R. A., Pérez-Castán, J., Montes, R. B., & Serrano, S. C. (2019). Assessment of airport arrival congestion and delay: Prediction and reliability. Transportation Research Part C: Emerging Technologies, 98, 255–283. https://doi.org/10.1016/j.trc.2018.11.015
Rodríguez-Sanz, A., Marcos, A. F., Pérez-Castán, J. A., Comendador, F. G., Valdés, R. A., & Loreiro, A. P. (2021). Queue behavioural patterns for passengers at airport terminals: A machine learning approach. Journal of Air Transport Management, 90, 101940. https://doi.org/10.1016/j.jairtraman.2020.101940
Schultz, M., Reitmann, S., & Alam, S. (2021). Predictive classification and understanding of weather impact on airport performance through machine learning. Transportation Research Part C: Emerging Technologies, 131, 103119. https://doi.org/10.1016/j.trc.2021.103119
Sineglazov, V., Chumachenko, E., & Gorbatyuk, V. (2013). An algorithm for solving the problem of forecasting. Aviation, 17(1), 9–13. https://doi.org/10.3846/16487788.2013.777219
Stogsdill, M. (2022). When outcomes are not enough: An examination of abductive and deductive logical approaches to risk analysis in aviation. Risk Analysis, 42(8), 1806–1814. https://doi.org/10.1111/risa.13681
Stogsdill, M., Baranzini, D., & Ulfvengren, P. (2021). Development of a metric concept that differentiates between normal and abnormal operational aviation data. Risk Analysis, 42(8), 1815–1833. https://doi.org/10.1111/risa.13680
Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. The MIT Press.
Truong, D., & Choi, W. (2020). Using machine learning algorithms to predict the risk of small Unmanned Aircraft System violations in the National Airspace System. Journal of Air Transport Management, 86, 101822. https://doi.org/10.1016/j.jairtraman.2020.101822
Xu, Z., Saleh, J. H., & Subagia, R. (2020). Machine learning for helicopter accident analysis using supervised classification: Inference, prediction, and implications. Reliability Engineering and System Safety, 204, 107210. https://doi.org/10.1016/j.ress.2020.107210
Wan, M., Liang, Y., Yan, L., & Zhou, T. (2021). Bibliometric analysis of human factors in aviation accident using MKD. IET Image Processing, 1–9. https://doi.org/10.1049/ipr2.12167