The Evolution and Taxonomy of Deep Learning Models for Aircraft Trajectory Prediction: A Review of Performance and Future Directions
Source abstract
Abstract
Accurate aircraft trajectory prediction is fundamental to air traffic management, operational safety, and intelligent aerospace systems. With the growing availability of flight data, deep learning has emerged as a powerful tool for modeling the spatiotemporal complexity of 4D trajectories. This paper presents a comprehensive review of deep learning-based approaches for aircraft trajectory prediction, focusing on their evolution, taxonomy, performance, and future directions. We classify existing models into five groups—RNN-based, attention-based, generative, graph-based, and hybrid and integrated models—and evaluate them using standardized metrics such as the RMSE, MAE, ADE, and FDE. Common datasets, including ADS-B and OpenSky, are summarized, along with the prevailing evaluation metrics. Beyond model comparison, we discuss real-world applications in anomaly detection, decision support, and real-time air traffic management, and highlight ongoing challenges such as data standardization, multimodal integration, uncertainty quantification, and self-supervised learning. This review provides a structured taxonomy and forward-looking perspectives, offering valuable insights for researchers and practitioners working to advance next-generation trajectory prediction technologies.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Traffic and Road Safety · Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information Security at Paichai University, Daejeon 35345, Republic of Korea
Funding
Institute of Information & Communications Technology Planning & Evaluation · Korean government
References (100+)
Show source-provided references
1. Complexity Optimal Air Traffic Assignment for Multi-Layer Transport Network in Urban Air Mobility Operations10.1016/j.trc.2022.103776 ↗
2. Schuchardt, B.I., Geister, D., Lüken, T., Knabe, F., Metz, I.C., Peinecke, N., and Schweiger, K. (2023). Air Traffic Management as a Vital Part of Urban Air Mobility—A Review of DLR’s Research Work from 1995 to 2022. Aerospace, 10.10.3390/aerospace10010081 ↗
3. Air taxi service for urban mobility: A critical review of recent developments, future challenges, and opportunities10.1016/j.tre.2020.102090 ↗
4. Flight trajectory prediction enabled by time-frequency wavelet transform10.1038/s41467-023-40903-9 ↗
5. Corbetta, M., Banerjee, P., Okolo, W., Gorospe, G., and Luchinsky, D.G. (2019, January 17–21). Real-Time UAV Trajectory Prediction for Safety Monitoring in Low-Altitude Airspace. Proceedings of the AIAA Aviation 2019 Forum, Dallas, TX, USA.10.2514/6.2019-3514 ↗
6. Weitz, P. (2013, January 23–25). Determination and visualization of uncertainties in 4D-trajectory prediction. Proceedings of the 2013 Integrated Communications, Navigation and Surveillance Conference (ICNS), Herndon, VA, USA.10.1109/ICNSurv.2013.6548525 ↗
7. Rohani, A.S., Puranik, T.G., and Kalyanam, K.M. (2023, January 18–22). Machine Learning Approach for Aircraft Performance Model Parameter Estimation for Trajectory Prediction Applications. Proceedings of the 2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC), Barcelona, Spain.10.1109/DASC58513.2023.10311271 ↗
8. Wild, G., Baxter, G., Srisaeng, P., and Richardson, S. (July, January 27). Machine learning for air transport planning and management. Proceedings of the AIAA Aviation 2022 Forum, Chicago, IL, USA.10.2514/6.2022-3706 ↗
9. Real-time road traffic state prediction based on ARIMA and Kalman filter10.1631/FITEE.1500381 ↗
10. Prevost, C.G., Desbiens, A., and Gagnon, E. (2007, January 9–13). Extended Kalman Filter for State Estimation and Trajectory Prediction of a Moving Object Detected by an Unmanned Aerial Vehicle. Proceedings of the 2007 American Control Conference, New York, NY, USA.10.1109/ACC.2007.4282823 ↗
11. Wang, Y., Pang, Y., Liu, Y., Dutta, P., and Yang, B.-J. (2019, January 17–21). Aircraft Trajectory Prediction and Risk Assessment Using Bayesian Updating. Proceedings of the AIAA Aviation Forum 2019, Dallas, TX, USA. AIAA 2019-2936.10.2514/6.2019-2936 ↗
12. Federal Aviation Administration (FAA) (2025, August 29). Air Traffic by the Numbers 2022, Available online: https://www.faa.gov.
13. Schaefer, M., Strohmeier, M., Lenders, V., Martinovic, I., and Wilhelm, M. (2014, January 15–17). Bringing up OpenSky: A large-scale ADS-B sensor network for research. Proceedings of the 13th IEEE/ACM International Symposium on Information Processing in Sensor Networks (IPSN), Berlin, Germany.10.1109/IPSN.2014.6846743 ↗
14. Hashemi, S.M., Botez, R.M., and Ghazi, G. (2024). Bidirectional Long Short-Term Memory Development for Aircraft Trajectory Prediction Applications to the UAS-S4 Ehécatl. Aerospace, 11.10.3390/aerospace11080625 ↗
15. Silvestre, J., Mielgo, P., Bregon, A., Martínez-Prieto, M.A., and Álvarez-Esteban, P.C. (2024, January 8–12). Towards aircraft trajectory prediction using LSTM networks. Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing (SAC ‘24), New York, NY, USA.10.1145/3605098.3636195 ↗
16. Zhang, Y., Jia, Z., Dong, C., Liu, Y., Zhang, L., and Wu, Q. (2022, January 4–8). Recurrent LSTM-based UAV Trajectory Prediction with ADS-B Information. Proceedings of the GLOBECOM 2022-2022 IEEE Global Communications Conference, Rio de Janeiro, Brazil.10.1109/GLOBECOM48099.2022.10000919 ↗
17. 4D Flight Trajectory Prediction Using a Hybrid Deep Learning Prediction Method Based on ADS-B Technology: A Case Study of Hartsfield Jackson Atlanta International Airport10.1016/j.trc.2022.103878 ↗
18. Hao, Q., Zhang, J., Jing, T., and Wang, W. (2024). Flight Trajectory Prediction Using an Enhanced CNN-LSTM Network. arXiv.
19. Li, F., Xu, X., Wang, R., Ma, M., and Dong, Z. (2025). Flight Trajectory Prediction Based on Automatic Dependent Surveillance-Broadcast Data Fusion with Interacting Multiple Model and Informer Framework. Sensors, 25.10.3390/s25082531 ↗
20. Dong, X., Tian, Y., Dai, L., Li, J., and Wan, L. (2024). A New Accurate Aircraft Trajectory Prediction in Terminal Airspace Based on Spatio Temporal Attention Mechanism. Aerospace, 11.10.3390/aerospace11090718 ↗
21. Youyou, Y., Fang, Y., and Long, T. (2025). Noise Robust Autoregressive Transformer for Aircraft Trajectory Prediction. Sci. Rep., 15.
22. Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., and Zhang, W. (2020). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. arXiv.10.1609/aaai.v35i12.17325 ↗
23. Du, D., Su, B., and Wei, Z. (2022). Preformer: Predictive Transformer with Multi-Scale Segment-Wise Correlations for Long-Term Time Series Forecasting. arXiv.10.1109/ICASSP49357.2023.10096881 ↗
24. Beltagy, I., Peters, M.E., and Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv.
25. Sun, Y., Zhou, X., Yang, Z., Wang, W., and Shi, Q. (2023, January 21–23). Flight Trajectory Prediction Method Based on Attentional Graph Convolutional Network. Proceedings of the 2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS), Chengdu, China.10.1109/ISCTIS58954.2023.10213104 ↗
26. Sun, Y., Jing, T., Wang, J., and Wang, W. (2024). Fighter flight trajectory prediction based on spatio-temporal graphical attention network. arXiv.
27. Pang, Y., and Liu, Y. (2020, January 15–19). Conditional Generative Adversarial Networks (CGAN) for Aircraft Trajectory Prediction considering weather effects. Proceedings of the AIAA Aviation Forum 2020, Virtual Event. AIAA 2020-1853.10.2514/6.2020-1853 ↗
28. Four-Dimensional Aircraft Trajectory Prediction Based on Generative Deep Learning
29. Long-term 4D trajectory prediction using generative adversarial networks10.1016/j.trc.2022.103554 ↗
30. Applications of Artificial Intelligence in Air Operations: A Systematic Review
31. Henttu, A., Chatterjee, K., and Majumdar, A. (2022). A Survey on Artificial Intelligence (AI) and eXplainable AI in Air Traffic Management: Current Trends and Development with Future Research Trajectory. Appl. Sci., 12.10.3390/app12031295 ↗
32. Abdelmaboud, A., Khafaga, D.S., Abuarqoub, A., and Barkaoui, K. (2024). A Survey on Artificial-Intelligence-Based Internet of Vehicles Utilizing Unmanned Aerial Vehicles. Drones, 8.10.3390/drones8080353 ↗
33. Tian, Y., Huang, J., Wang, B., and Ren, X. (2022). Aircraft 4D Trajectory Prediction in Civil Aviation: A Review. Aerospace, 9.10.3390/aerospace9020091 ↗
34. A Deep Learning Approach for Aircraft Trajectory Prediction in Terminal Airspace10.1109/ACCESS.2020.3016289 ↗
35. Xu, Z., Zeng, W., Chu, X., and Cao, P. (2021). Multi-Aircraft Trajectory Collaborative Prediction Based on Social Long Short-Term Memory Netw. Aerospace, 8.10.3390/aerospace8040115 ↗
36. Wu, J. (2024, January 20–21). Aircraft Trajectory Prediction Based on Long and Short-Term Memory Structural Models. Proceedings of the 2024 International Conference on Distributed Computing and Optimization Techniques (ICDCOT), Bengaluru, India.10.1109/ICDCOT61034.2024.10516095 ↗
37. 4-D Flight Trajectory Prediction With Constrained LSTM Network10.1109/TITS.2020.3004807 ↗
38. Wang, B., Zhai, Z., Xiong, R., and Gao, B. (2021, January 24–26). Flight Trajectory Prediction of General Aviation Aircraft Based on LSTM Model. Proceedings of the 2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE), Dalian, China.10.1109/ICISCAE52414.2021.9590656 ↗
39. Yang, Z., Kang, X., Gong, Y., and Wang, J. (2023). Aircraft trajectory prediction and aviation safety in ADS-B failure conditions based on neural network. Sci. Rep., 13.10.1038/s41598-023-46914-2 ↗
40. Long-Term Trajectory Prediction Model Based on Transformer10.1109/ACCESS.2023.3343800 ↗
41. An improved transformer-based model for long-term 4D trajectory prediction in civil aviation
42. Jia, P., Chen, H., Zhang, L., and Han, D. (2022). Attention-LSTM based prediction model for aircraft 4-D trajectory. Sci. Rep., 12.10.1038/s41598-022-19794-1 ↗
43. Luo, S., Zhao, M., Zhao, Z., Li, L., Zhang, S., and Zhang, X. (2023, January 24–26). FT-TF: A 4D Long-Term Flight Trajectory Prediction Method Based on Transformer. Proceedings of the 2023 42nd Chinese Control Conference (CCC), Tianjin, China.10.23919/CCC58697.2023.10239944 ↗
44. Hao, H., Si, X., Li, M., and Liang, J. (2024, January 14–19). Flight Trajectory Change Prediction Via Patched Spatial-Temporal Transformer. Proceedings of the IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece.10.1109/IGARSS53475.2024.10641236 ↗
45. Guo, D., Zhang, Z., Yan, Z., Zhang, J., and Lin, Y. (2024, January 20–22). FlightBERT++: A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual Event.10.1609/aaai.v38i1.27763 ↗
46. Lu, G., Long, L., Zhang, Y., and Zheng, Y. (2025). An Inverted Transformer Framework for Aviation Trajectory Prediction with Multi-Flight Mode Fusion. Aerospace, 12.10.3390/aerospace12040319 ↗
47. Sun, Y., Wang, D., Wang, W., Xiong, L., and Yang, X. (2020, January 18–20). Confrontational flight trajectory prediction based on attention mechanism. Proceedings of the 2020 International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Bangkok, Thailand.10.1109/ICBASE51474.2020.00052 ↗
48. Multi-Route Aircraft Trajectory Prediction Using Temporal Fusion Transformers10.1109/ACCESS.2024.3415419 ↗
49. Hu, Q., Huang, G., Shi, H., Lin, Y., and Guo, D. (2022, January 27–30). A Short-term Aircraft Trajectory Prediction Framework Using Conditional Generative Adversarial Network. Proceedings of the 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China.10.1109/ICCASIT55263.2022.9986799 ↗
50. Yin, Y., Zhang, S., Zhang, Y., Zhang, Y., and Xiang, S. (2023, January 24–28). Context-aware Aircraft Trajectory Prediction with Diffusion Models. Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain.10.1109/ITSC57777.2023.10422124 ↗
51. GooDFlight: Goal-Oriented Diffusion Model for Flight Trajectory Prediction10.1109/TAES.2025.3536436 ↗
52. Global and Local Interattribute Relationships-Based Graph Convolutional Network for Flight Trajectory Prediction10.1109/TAES.2024.3357668 ↗
53. Kuang, Y., Wang, Z., Zhang, J., Shi, Z., and Zhang, Y. (2025). DA-STGCN: 4D Trajectory Prediction Based on Spatiotemporal Graph Convolution. arXiv.
54. A Hybrid CNN-LSTM Model for Aircraft 4D Trajectory Prediction10.1109/ACCESS.2020.3010963 ↗
55. Zhang, K., and Chen, B. (2022). Phased flight trajectory prediction with deep learning. arXiv.
56. Zhang, L., Chen, H., Jia, P., Tian, Z., and Du, X. (June, January 30). WGAN-GP and LSTM based Prediction Model for Aircraft 4-D Trajectory. Proceedings of the 2022 International Wireless Communications and Mobile Computing (IWCMC), Dubrovnik, Croatia.10.1109/IWCMC55113.2022.9824928 ↗
57. SATF: A flight trajectory prediction method incorporating spatial awareness and time frequency transformation
58. Ma, L., Meng, X., and Wu, Z. (2024). Data-Driven 4D Trajectory Prediction Model Using Attention-TCN-GRU. Aerospace, 11.10.3390/aerospace11040313 ↗
59. Fang, J., Liu, Y., Xu, T., Wang, Y., and Li, J. (2025, January 28–30). GCTrajectory: A CNN-Transformer Adversarial Learning Framework for Flight Trajectory Prediction. Proceedings of the 2025 8th International Conference on Advanced Algorithms and Control Engineering (ICAACE), Shanghai, China.10.1109/ICAACE65325.2025.11020282 ↗
60. Ding, W., Huang, J., Shang, G., Wang, X., Li, B., Li, Y., and Liu, H. (2022). Short-Term Trajectory Prediction Based on Hyperparametric Optimisation and a Dual Attention Mechanism. Aerospace, 9.10.3390/aerospace9080464 ↗
61. Ma, T.-Y., Meng, X., and Wu, Z. (2024). A Novel Trajectory Prediction Method Based on CNN, BILSTM, and Attention Mechanism: Analysis of B1520 Flight Data. Aerospace, 11.10.3390/aerospace11100822 ↗
62. Wu, Y., Yu, H., Du, J., Liu, B., and Yu, W. (2022). An Aircraft Trajectory Prediction Method Based on Trajectory Clustering and a Spatiotemporal Feature Network. Electronics, 11.10.3390/electronics11213453 ↗
63. Aircraft Trajectory Prediction Based on Bayesian Optimised Temporal Convolutional Network–Bidirectional Gated Recurrent Unit Hybrid Neural Network10.1155/2022/2086904 ↗
64. Wu, H., Liang, Y., Zhou, B., and Sun, H. (2023, January 1–3). A Bi-LSTM and AutoEncoder Based Framework for Multi-step Flight Trajectory Prediction. Proceedings of the 2023 IEEE 5th International Conference on Computer, Communications and Robotics Engineering (ICCRE), Chongqing, China.10.1109/ICCRE57112.2023.10155614 ↗
65. Dong, Z., Fan, B., Li, F., Xu, X., Sun, H., and Cao, W. (2023). TCN-Informer-Based Flight Trajectory Prediction for Aircraft in the Approach Phase. Sustainability, 15.10.3390/su152316344 ↗
66. Aircraft Trajectory Prediction With Enriched Intent Using Encoder-Decoder Architecture10.1109/ACCESS.2022.3149231 ↗
67. Liu, B., Shi, Q., and Han, P. (2022, January 18–22). Short-Term 4D Trajectory Prediction Method Based on LSTM-IMM. Proceedings of the 2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC), Portsmouth, VA, USA.10.1109/DASC55683.2022.9925832 ↗
68. A Generalized Approach to Aircraft Trajectory Prediction via Supervised Deep Learning10.1109/ACCESS.2023.3325053 ↗
69. Aircraft Trajectory Segmentation-based Contrastive Coding: A Framework for Self-supervised Trajectory Representation10.1109/OJITS.2025.3574746 ↗
70. Liu, S., Sun, Y., Jing, T., Li, Z., and Wang, W. (2025, January 20–22). Effective and Efficient Representation Learning for Flight Trajectories. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual Event.
71. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
72. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
73. Xu, L., Skoularidou, M., Cuesta-Infante, A., and Veeramachaneni, K. (2019). Modeling tabular data using conditional GAN. arXiv.
74. Denoising diffusion probabilistic models
75. The graph neural network model10.1109/TNN.2008.2005605 ↗
76. Kipf, T.N., and Welling, M. (2017). Semi-supervised classification with graph convolutional networks. arXiv.
77. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2018). Graph attention networks. arXiv.
78. Performance evaluation of China’s air routes based on network data envelopment analysis approach10.1016/j.jairtraman.2016.01.006 ↗
79. Improved training of Wasserstein GANs
80. Doersch, C., Gupta, A., and Efros, A.A. (2015, January 11–18). Unsupervised visual representation learning by context prediction. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.167 ↗
81. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13–18). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning (ICML), Virtual Event.
82. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance10.3354/cr030079 ↗
83. Makridakis, S., Wheelwright, S.C., and McGee, V.E. (1983). Forecasting: Methods and Applications, Wiley. [2nd ed.].
84. Dynamic programming algorithm optimization for spoken word recognition10.1109/TASSP.1978.1163055 ↗
85. Binary codes capable of correcting deletions, insertions, and reversals
86. Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., and Savarese, S. (2016, January 27–30). Social LSTM: Human trajectory prediction in crowded spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.110 ↗
87. Mercat, J., Zoghby, N.E., Sandou, G., Beauvois, D., and Pita Gil, G. (2019). Kinematic single vehicle trajectory prediction baselines and applications with the NGSIM dataset. arXiv.
88. Strictly Proper Scoring Rules, Prediction, and Estimation10.1198/016214506000001437 ↗
89. A systematic analysis of performance measures for classification tasks10.1016/j.ipm.2009.03.002 ↗
90. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
91. Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy10.1023/A:1022859003006 ↗
92. EUROCONTROL (2018). Challenges of Growth 2018: European Air Traffic in 2040, EUROCONTROL. Available online: https://www.eurocontrol.int.
93. Civil Aviation Administration of China (CAAC) (2025, August 29). Annual Report of China Civil Aviation Flight Statistics 2021, Available online: http://www.caac.gov.cn.
94. NATS (2022). Annual Report and Accounts 2022, NATS Holdings. Available online: https://www.nats.aero.
95. Flightradar24 (2025, August 29). Flightradar24: Live Flight Tracker. Available online: https://www.flightradar24.com.
96. FlightAware (2025, August 29). FlightAware Live Flight Tracking. Available online: https://www.flightaware.com.
97. ADS-B Exchange (2025, August 29). The World’s Largest Source of Unfiltered Flight Data. Available online: https://www.adsbexchange.com.
98. Eagle Dynamics (2025, August 29). Digital Combat Simulator (DCS) World, Available online: https://www.digitalcombatsimulator.com.
99. Raia Software (2025, August 29). TacView Flight Data Visualization Tool, Available online: https://www.tacview.net.
100. Air Combat Center (2025, August 29). Air Combat Simulation Platform. Available online: https://aircombatcentre.com.au/.