Predicting flight delay propagation in the Brazilian aviation network with Heterogeneous Graph Neural Networks
Resumo
This work takes advantage of a Graph Neural Network (GNN) model to predict flight delay propagation within the Brazilian aviation network. We propose SUBAERO, a method with an architecture that comprises a diverse data ingestion pipeline, integrating weather, airport, flight, and aircraft data via APIs. These datasets are structured in a graph-oriented database (Neo4j) to map complex spatial-temporal dependencies. A Heterogeneous Graph Neural Network (HGT) approach was employed, achieving a Mean Absolute Error (MAE) of 6.7 minutes in delay predictions. This study applies advanced Data Science techniques to optimize urban and regional mobility, providing a timely decision-support tool to mitigate operational bottlenecks and enhance transport infrastructure for social good.
Palavras-chave:
Aviation network, GNN, HGT, urban mobility, flight delay propagation
Referências
Aprigliano Fernandes, V., Pacheco, R. R., Fernandes, E., Cabo, M., Ventura, R. V., and Caixeta, R. (2021).
Air transportation, economy and causality: Remote towns in brazil’s amazon region. Sustainability, 13(2). DOI: 10.3390/su13020627.
Barabási, A.-L. and Albert, R. (1999). Emergence of scaling in random networks. Science, 286(5439):509–512.
Cai, K., Li, Y., Fang, Y.-P., and Zhu, Y. (2022). A deep learning approach for flight delay prediction through time-evolving graphs. IEEE Transactions on Intelligent Transportation Systems, 23(8):11397–11407. DOI: 10.1109/TITS.2021.3103502.
Diestel, R. (2017). Graph Theory. Springer Berlin Heidelberg. DOI: 10.1007/978-3-662-53622-3.
Gui, G., Liu, F., Sun, J., Yang, J., Zhou, Z., and Zhao, D. (2020). Flight delay prediction based on aviation big data and machine learning. IEEE Transactions on Vehicular Technology, 69(1):140–150. DOI: 10.1109/TVT.2019.2954094.
Hatıpoğlu, I. and Tosun, Ö. (2024). Predictive modeling of flight delays at an airport using machine learning methods. Applied Sciences, 14(13):5472. DOI: 10.3390/app14135472.
Hu, Z., Dong, Y., Wang, K., and Sun, Y. (2020). Heterogeneous graph transformer. In Proceedings of The Web Conference 2020, WWW ’20, page 2704–2710, New York, NY, USA. Association for Computing Machinery. DOI: 10.1145/3366423.3380027.
IATA (2025). IATA Launches 2024 World Air Transport Statistics Report — iata.org. URL: [link] [Accessed 23-05-2026].
ICAO (2024). Annual Report 2024 - The World of Air Transport in 2024 - icao.int. URL: [link] [Accessed 23-05-2026].
Kipf, T. N. and Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
Rebollo, J. J. and Balakrishnan, H. (2014). Characterization and prediction of air traffic delays. Transportation Research Part C: Emerging Technologies, 44:231–241. DOI: 10.1016/j.trc.2014.04.007.
Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., and Bronstein, M. M. (2020). Temporal graph networks for deep learning on dynamic graphs. CoRR, abs/2006.10637. URL: [link].
Sun, Y. and Han, J. (2013). Mining heterogeneous information networks: a structural analysis approach. SIGKDD Explor. Newsl., 14(2):20–28. DOI: 10.1145/2481244.2481248.
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2018). Graph attention networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. URL: [link].
Wu, Y., Yang, H., Lin, Y., and Liu, H. (2024). Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction. IEEE Transactions on Knowledge & Data Engineering, 36(01):386–400. DOI: 10.1109/TKDE.2023.3286690.
Zanin, M. and Lillo, F. (2013). Modelling the air transport with complex networks: A short review. The European Physical Journal Special Topics, 215(1):5–21. DOI: 10.1140/epjst/e2013-01711-9.
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., and Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1:57–81. DOI: 10.1016/j.aiopen.2021.01.001.
Air transportation, economy and causality: Remote towns in brazil’s amazon region. Sustainability, 13(2). DOI: 10.3390/su13020627.
Barabási, A.-L. and Albert, R. (1999). Emergence of scaling in random networks. Science, 286(5439):509–512.
Cai, K., Li, Y., Fang, Y.-P., and Zhu, Y. (2022). A deep learning approach for flight delay prediction through time-evolving graphs. IEEE Transactions on Intelligent Transportation Systems, 23(8):11397–11407. DOI: 10.1109/TITS.2021.3103502.
Diestel, R. (2017). Graph Theory. Springer Berlin Heidelberg. DOI: 10.1007/978-3-662-53622-3.
Gui, G., Liu, F., Sun, J., Yang, J., Zhou, Z., and Zhao, D. (2020). Flight delay prediction based on aviation big data and machine learning. IEEE Transactions on Vehicular Technology, 69(1):140–150. DOI: 10.1109/TVT.2019.2954094.
Hatıpoğlu, I. and Tosun, Ö. (2024). Predictive modeling of flight delays at an airport using machine learning methods. Applied Sciences, 14(13):5472. DOI: 10.3390/app14135472.
Hu, Z., Dong, Y., Wang, K., and Sun, Y. (2020). Heterogeneous graph transformer. In Proceedings of The Web Conference 2020, WWW ’20, page 2704–2710, New York, NY, USA. Association for Computing Machinery. DOI: 10.1145/3366423.3380027.
IATA (2025). IATA Launches 2024 World Air Transport Statistics Report — iata.org. URL: [link] [Accessed 23-05-2026].
ICAO (2024). Annual Report 2024 - The World of Air Transport in 2024 - icao.int. URL: [link] [Accessed 23-05-2026].
Kipf, T. N. and Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
Rebollo, J. J. and Balakrishnan, H. (2014). Characterization and prediction of air traffic delays. Transportation Research Part C: Emerging Technologies, 44:231–241. DOI: 10.1016/j.trc.2014.04.007.
Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., and Bronstein, M. M. (2020). Temporal graph networks for deep learning on dynamic graphs. CoRR, abs/2006.10637. URL: [link].
Sun, Y. and Han, J. (2013). Mining heterogeneous information networks: a structural analysis approach. SIGKDD Explor. Newsl., 14(2):20–28. DOI: 10.1145/2481244.2481248.
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2018). Graph attention networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. URL: [link].
Wu, Y., Yang, H., Lin, Y., and Liu, H. (2024). Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction. IEEE Transactions on Knowledge & Data Engineering, 36(01):386–400. DOI: 10.1109/TKDE.2023.3286690.
Zanin, M. and Lillo, F. (2013). Modelling the air transport with complex networks: A short review. The European Physical Journal Special Topics, 215(1):5–21. DOI: 10.1140/epjst/e2013-01711-9.
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., and Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1:57–81. DOI: 10.1016/j.aiopen.2021.01.001.
Publicado
08/09/2026
Como Citar
WITTMANN, Eduardo Zantut; CAZZOLATO, Mirela Teixeira.
Predicting flight delay propagation in the Brazilian aviation network with Heterogeneous Graph Neural Networks. In: DATA SCIENCE FOR SOCIAL GOOD BRAZILIAN WORKSHOP (DS4SG) - SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 405-414.
DOI: https://doi.org/10.5753/sbbd_estendido.2026.249492.
