Skip to main content
Search
Search
Quick Search anywhere
Quick Search fdjslkfh
Advanced search
Cart
Join AIAA Institution Login
Skip main navigation
Journal of Aerospace Information Systems logo
Skip to article control options
No AccessFull-Length Papers

Risk Assessment Procedure of Final Approach to Landing Using Deep Learning

Published Online:9 Dec 2023https://doi.org/10.2514/1.I011177

Abstract

Flight safety is the highest priority of all involved in aviation. All civil aviation authorities around the world have the responsibility to guarantee flight safety, but the flight data are considered confidential and regarded as trade secrets by airlines. Therefore, the publicly available sources are employed in the study to investigate the risk and related factors of flight safety during the approach to landing. Automatic Dependent Surveillance–Broadcast flight trajectory data and the Meteorological Terminal Aviation Routine Weather Report are used to analyze the risk associated with the final approach to landing. This study presents a procedure to conduct the data mining and risk assessment of flights landing at Taipei Songshan Airport (TSA). A deep learning method is adopted to tackle the problems associated with nonlinear regression that cannot be addressed by traditional statistical regression methods. The trajectory and glide path angle deviations of each flight are determined and applied to the model training. These two deviation variables are regarded as the evaluation standards, while the weather conditions are used as risk factors. Each weather factor in the deep learning models is weighted by the permutation feature importance analysis to capture how much influence each factor has on predictions from the model. The results show that the estimation accuracy of trajectory deviation with the 10-input model and glide path angle deviation with the 11-input model is over 90 and 95%, respectively. The trajectory deviations of runway 10 have higher impacts from temperature, precipitations, and crosswind.

References

  • [1] Boeing, “Statistical Summary of Commercial Jet Airplane Accidents: Worldwide Operations | 1959-2019,” Boeing Commercial Airplanes, Seattle, WA, 2019. Google Scholar

  • [2] “Taiwan Aviation Occurrence Statistics 2010–2019,” Taiwan Transportation Safety Board, New Taipei City, Taiwan, 2020, https://www.ttsb.gov.tw/media/4578/taiwan-aviation-occurrence-statistics-2010-2019.pdf. Google Scholar

  • [3] Mazon J., Rojas J., Lozano M., Pino D., Prats X. and Miglietta M., “Influence of Meteorological Phenomena on Worldwide Aircraft Accidents, 1967–2010,” Meteorological Applications, Vol. 25, No. 2, 2018, pp. 236–245. https://doi.org/10.1002/met.1686 CrossrefGoogle Scholar

  • [4] Sheridan K., Puranik T. G., Mangortey E., Pinon-Fischer O. J., Kirby M. and Mavris D. N., “An Application of DBSCAN Clustering for Flight Anomaly Detection During the Approach Phase,” AIAA Scitech 2020 Forum, AIAA Paper 2020-1851, Jan. 2020. LinkGoogle Scholar

  • [5] Smart E., Brown D. and Denman J., “A Two-Phase Method of Detecting Abnormalities in Aircraft Flight Data and Ranking Their Impact on Individual Flights,” IEEE Transactions on Intelligent Transportation Systems, Vol. 13, No. 3, 2012, pp. 1253–1265. https://doi.org/10.1109/TITS.2012.2188391 CrossrefGoogle Scholar

  • [6] ICAO, “9871: Technical Provisions for Mode S Services and Extended Squitter, AN/464,” ICAO, Doc 9871, 2008. Google Scholar

  • [7] Schäfer M., Strohmeier M., Lenders V., Martinovic I. and Wilhelm M., “Bringing Up OpenSky: A Large-Scale ADS-B Sensor Network for Research,” IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks, Inst. of Electrical and Electronics Engineers, New York, April 2014, pp. 83–94. Google Scholar

  • [8] Eldawy E. O. and Mokhtar H. M. O., “Clustering-Based Trajectory Outlier Detection,” International Journal of Advanced Computer Science and Applications, Vol. 11, No. 5, 2020, pp. 133–139. https://doi.org/10.14569/IJACSA.2020.0110520 CrossrefGoogle Scholar

  • [9] Olive X. and Basora L., “Identifying Anomalies in Past En-Route Trajectories with Clustering and Anomaly Detection Methods,” 13th USA/Europe Air Traffic Management Research and Development Seminar (ATM2019), Vienna, Austria, June 2019, https://www.atmseminar.org/past-seminars/13th-seminar/papers-and-presentations/. Google Scholar

  • [10] Jan S.-S. and Chen Y.-T., “Establishing Unusual-Weather Detection System Prototype Using Onboard Sensor Information,” Journal of Aircraft, Vol. 56, No. 4, 2019, pp. 1281–1290. https://doi.org/10.2514/1.C034630 LinkGoogle Scholar

  • [11] Guo Z., Yin C., Zeng W., Tan X. and Bao J., “Data-Driven Method for Detecting Flight Trajectory Deviation Anomaly,” Journal of Aerospace Information Systems, Vol. 19, No. 12, 2022, pp. 799–810. https://doi.org/10.2514/1.I011124 LinkGoogle Scholar

  • [12] Shi Z., Xu M., Pan Q., Yan B. and Zhang H., “LSTM-Based Flight Trajectory Prediction,” 2018 International Joint Conference on Neural Networks (IJCNN), Inst. of Electrical and Electronics Engineers, New York, July 2018, pp. 1–8. Google Scholar

  • [13] Zhao Z., Zeng W., Quan Z., Chen M. and Yang Z., “Aircraft Trajectory Prediction Using Deep Long Short-Term Memory Networks,” Proceedings of the 19th COTA International Conference of Transportation Professionals, American Soc. of Civil Engineers (ASCE), VA, 2019, pp. 124–135. Google Scholar

  • [14] Shi Z., Xu M. and Pan Q., “4-D Flight Trajectory Prediction with Constrained LSTM Network,” IEEE Transactions on Intelligent Transportation Systems, Vol. 22, No. 11, 2020, pp. 7242–7255. https://doi.org/10.1109/TITS.2020.3004807 CrossrefGoogle Scholar

  • [15] Ghazi G. and Botez R. M., “Aircraft Mathematical Model Identification for Flight Trajectories and Performance Analysis in Cruise,” Journal of Aerospace Information Systems, Vol. 19, No. 8, 2022, pp. 530–549. https://doi.org/10.2514/1.I011050 LinkGoogle Scholar

  • [16] Gui G., Liu F., Sun J., Yang J., Zhou Z. and Zhao D., “Flight Delay Prediction Based on Aviation Big Data and Machine Learning,” IEEE Transactions on Vehicular Technology, Vol. 69, No. 1, 2019, pp. 140–150. https://doi.org/10.1109/TVT.2019.2954094 CrossrefGoogle Scholar

  • [17] Murça M. C. R., Hansman R. J., Li L. and Ren P., “Flight Trajectory Data Analytics for Characterization of Air Traffic Flows: A Comparative Analysis of Terminal Area Operations Between New York, Hong Kong and Sao Paulo,” Transportation Research Part C: Emerging Technologies, Vol. 97, Dec. 2018, pp. 324–347. https://doi.org/10.1016/j.trc.2018.10.021 CrossrefGoogle Scholar

  • [18] Olive X. and Morio J., “Trajectory Clustering of Air Traffic Flows around Airports,” Aerospace Science and Technology, Vol. 84, Jan. 2019, pp. 776–781. https://doi.org/10.1016/j.ast.2018.11.031 CrossrefGoogle Scholar

  • [19] Schultz M., Olive X., Rosenow J., Fricke H. and Alam S., “Analysis of Airport Ground Operations Based on ADS-B Data,” 2020 International Conference on Artificial Intelligence and Data Analytics for Air Transportation (AIDA-AT), Inst. of Electrical and Electronics Engineers, New York, Feb. 2020, pp. 1–9. Google Scholar

  • [20] Renz-Wieland A. and Wallenburg H., “Airport Quality: Holding and Go-Arounds,” TR, Centrum Wiskunde & Informatica (CWI), Amsterdam, The Netherlands, 2016. Google Scholar

  • [21] De Leege A., Van Paassen M. and Mulder M., “Using Automatic Dependent Surveillance-Broadcast for Meteorological Monitoring,” Journal of Aircraft, Vol. 50, No. 1, 2013, pp. 249–261. https://doi.org/10.2514/1.C031901 LinkGoogle Scholar

  • [22] Fan Y., “Analysis of Influence of Clear Air Turbulence on Aircraft,” Open Journal of Transportation Technologies, Vol. 8, No. 1, 2019, pp. 1–10. https://doi.org/10.12677/OJTT.2019.81001 CrossrefGoogle Scholar

  • [23] Gui G., Zhou Z., Wang J., Liu F. and Sun J., “Machine Learning Aided Air Traffic Flow Analysis Based on Aviation Big Data,” IEEE Transactions on Vehicular Technology, Vol. 69, No. 5, 2020, pp. 4817–4826. https://doi.org/10.1109/TVT.2020.2981959 CrossrefGoogle Scholar

  • [24] Wang Z., A Methodology for Nowcasting Unstable Approaches, Ph.D. Dissertation, Dept. of Systems Engineering and Operations Research, George Mason Univ., Fairfax, VA, 2016, Abstract. Google Scholar

  • [25] “Unstable Approaches, Risk Mitigation Policies, Procedures and Best Practices,” International Air Transport Assoc., Montreal, Canada, 2017, https://www.iata.org/contentassets/7a5cd514de9c4c63ba0a7ac21547477a/iata-guidance-unstable-approaches.pdf. Google Scholar

  • [26] Olive X. and Bieber P., “Quantitative Assessments of Runway Excursion Precursors Using Mode S Data,” 8th International Conference on Research in Air Transportation (ICRAT), June 2018, https://www.icrat.org/previous-conferences/8th-international-conference/papers/. Google Scholar

  • [27] Sarcià S. A., Cantone G. and Basili V. R., “A Statistical Neural Network Framework for Risk Management Process-From the Proposal to its Preliminary Validation for Efficiency,” International Conference on Software and Data Technologies, Vol. 2, SCITEPRESS, Setúbal, Portugal, 2007, pp. 168–177. Google Scholar

  • [28] Bati F. and Withington L., “Application of Machine Learning for Aviation Safety Risk Metric,” 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC), Inst. of Electrical and Electronics Engineers, New York, Sept. 2019, pp. 1–9. Google Scholar

  • [29] Tsai P. and Lai Y., “Risk Assessment of Final Approach Phase with ADS-B Trajectory Data and Weather Information Using Artificial Neural Network,” 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), Inst. of Electrical and Electronics Engineers, New York, Sept. 2021, pp. 1245–1250. Google Scholar

  • [30] “Algorithm to Describe Weather Conditions at European Airports,” EUROCONTROL, FINAL ed., Brussels, Belgium, 2011. Google Scholar

  • [31] Schultz M., Lorenz S., Schmitz R. and Delgado L., “Weather Impact on Airport Performance,” Aerospace, Vol. 5, No. 4, 2018, p. 109. https://doi.org/10.3390/aerospace5040109 CrossrefGoogle Scholar

  • [32] Proud S. R., “Go-Around Detection Using Crowd-Sourced ADS-B Position Data,” Aerospace, Vol. 7, No. 2, 2020, p. 16. https://doi.org/10.3390/aerospace7020016 CrossrefGoogle Scholar

  • [33] Breiman L., “Random Forests,” Machine Learning, Vol. 45, No. 1, 2001, pp. 5–32. https://doi.org/10.1023/A:1010933404324 CrossrefGoogle Scholar

  • [34] Altmann A., Toloşi L., Sander O. and Lengauer T., “Permutation Importance: A Corrected Feature Importance Measure,” Bioinformatics, Vol. 26, No. 10, 2010, pp. 1340–1347. https://doi.org/10.1093/bioinformatics/btq134 CrossrefGoogle Scholar

  • [35] Kaneko H., “Cross‐Validated Permutation Feature Importance Considering Correlation Between Features,” Analytical Science Advances, Vol. 3, Nos. 9–10, 2022, pp. 278–287. https://doi.org/10.1002/ansa.202200018 CrossrefGoogle Scholar

  • [36] Ackley J. L., Puranik T. G. and Mavris D., “A Supervised Learning Approach for Safety Event Precursor Identification in Commercial Aviation,” AIAA Aviation 2020 Forum, AIAA Paper 2020-2880, 2020. Google Scholar

  • [37] Norton J., “An Introduction to Sensitivity Assessment of Simulation Models,” Environmental Modelling & Software, Vol. 69, July 2015, pp. 166–174. https://doi.org/10.1016/j.envsoft.2015.03.020 CrossrefGoogle Scholar

  • [38] Pianosi F., Beven K., Freer J., Hall J. W., Rougier J., Stephenson D. B. and Wagener T., “Sensitivity Analysis of Environmental Models: A Systematic Review with Practical Workflow,” Environmental Modelling & Software, Vol. 79, May 2016, pp. 214–232. https://doi.org/10.1016/j.envsoft.2016.02.008 CrossrefGoogle Scholar

Previous article
Next article