Abstract
The low-altitude economy promises new options for urban transport and logistics but is constrained by gust-induced, highly unsteady aerodynamics that threaten flight safety. We present a Graph Transformer framework that fuses a surface-pressure graph with temporal attention to predict gust-induced unsteady aerodynamic loads. Sparse pressure taps are encoded as a full-link graph aligned with the airframe topology. Comparative studies show the necessity of a full-link graph, compared to streamwise or crosswise links, for precise gust modeling and highlight the complex gust flow patterns that include crosswise flows. The attention mechanism learns gust-onset-based attention patterns, enabling the model to identify and prioritize critical temporal phases of gust events. By correlating the complex spatiotemporal scales, the unified framework demonstrates robust performance on various challenging gust scenarios, delivering consistent and accurate multi-output predictions. Our framework provides a practical path for robust gust modeling, contributing to flight safety, thereby advancing the low-altitude economy.
Similar content being viewed by others
Data availability
The two-dimensional simulation dataset generated for the study is publicly available at https://doi.org/10.17605/OSF.IO/DE9CP. The three-dimensional experimental datasets form part of ongoing research and are available under restricted access; requests for access should be directed to the corresponding author.
Code availability
The code implementing the Graph Transformer framework for gust-load prediction is available at https://github.com/liangaomng/gust_ce. The repository includes model definitions, training scripts, and simulation datasets for reproducing key results in this paper.
References
Udugama, B. et al. Diagnosing COVID-19: the disease and tools for detection. ACS Nano 14, 3822–3835 (2020).
Chamola, V., Hassija, V., Gupta, V. & Guizani, M. A comprehensive review of the COVID-19 pandemic and the role of IoT, drones, AI, blockchain, and 5G in managing its impact. IEEE Access 8, 90225–90265 (2020).
Zheng, C., Yan, Y. & Liu, Y. Prospects of eVTOL and modular flying cars in China urban settings. J. Intell. Connect. Veh. 6, 187–189 (2023).
Floreano, D. & Wood, R. J. Science, technology and the future of small autonomous drones. Nature 521, 460–466 (2015).
Gao, M. et al. Weather constraints on global drone flyability. Sci. Rep. 11, 12092 (2021).
Jones, A. R., Cetiner, O. & Smith, M. J. Physics and modeling of large flow disturbances: discrete gust encounters for modern air vehicles. Annu. Rev. Fluid Mech. 54, 469–493 (2022).
Sun, X., Liu, H., Su, N. & Wu, Y. Investigation on wind tunnel tests of the kilometer skyscraper. Eng. Struct. 148, 340–356 (2017).
Rajagopalan, P., Lim, K. C. & Jamei, E. Urban heat island and wind flow characteristics of a tropical city. Sol. Energy 107, 159–170 (2014).
Gharbia, Y., Derakhshandeh, J. F., Alam, M. M. & Amer, A. M. Developments in wingtip vorticity mitigation techniques: a comprehensive review. Aerospace 11, 36 (2023).
Andrews, W. H. Exploratory Flight Investigation of Aircraft Response to the Wing Vortex Wake Generated by Jet Transport Aircraft. Tech. Rep. NASA TN D-6655 (National Aeronautics and Space Administration, 1972).
Chen, D. et al. Sparse pressure-based machine learning approach for aerodynamic loads estimation during gust encounters. AIAA J. 62, 275–290 (2024).
Fukami, K. & Taira, K. Grasping extreme aerodynamics on a low-dimensional manifold. Nat. Commun. 14, 6480 (2023).
Nakata, T. et al. Aerodynamic imaging by mosquitoes inspires a surface detector for autonomous flying vehicles. Science 368, 634–637 (2020).
Gong, Z. et al. Morphological intelligence mechanisms in biological and biomimetic flow sensing. Adv. Intell. Syst. 5, 2300154 (2023).
Jiang, Y. et al. Underwater source localization using an artificial lateral line system with pressure and flow velocity sensor fusion. IEEE/ASME Trans. Mechatron. 27, 245–255 (2021).
Dai, H. et al. Biomimetic hydrodynamic sensor with whisker array architecture and multidirectional perception ability. Adv. Sci. 11, 2405276 (2024).
Sedky, G., Biler, H. & Jones, A. R. Experimental comparison of a sinusoidal and trapezoidal transverse gust. AIAA J. 60, 3347–3351 (2022).
Corkery, S., Babinsky, H. & Harvey, J. On the development and early observations from a towing tank-based transverse wing–gust encounter test rig. Exp. Fluids 59, 1–16 (2018).
Jones, A. R. & Cetiner, O. Overview of unsteady aerodynamic response of rigid wings in gust encounters. AIAA J. 59, 731–736 (2021).
Fernandez, F., Cleaver, D. & Gursul, I. Unsteady aerodynamics of a wing in a novel small-amplitude transverse gust generator. Exp. Fluids 62, 1–20 (2021).
He, X., Williams, D. R. & Dawson, S. T. Transverse gust generation in a wind tunnel: a suction-driven approach. Exp. Fluids 63, 125 (2022).
Stutz, C. M., Hrynuk, J. T. & Bohl, D. G. Dimensional analysis of a transverse gust encounter. Aerosp. Sci. Technol. 137, 108285 (2023).
Silva, W. & Raveh, D. Development of unsteady aerodynamic state-space models from CFD-based pulse responses. In 19th AIAA Applied Aerodynamics Conference, 1213 (2001).
Greenwell, D., Khrabrov, A., Goman, M. & Abramov, N. Two-step linear regression method for identification of high incidence unsteady aerodynamic model. In AIAA Atmospheric Flight Mechanics Conference and Exhibit, 4080 (2001).
Brunton, S. L., Dawson, S. T. & Rowley, C. W. State-space model identification and feedback control of unsteady aerodynamic forces. J. Fluids Struct. 50, 253–270 (2014).
Goman, M. & Khrabrov, A. State-space representation of aerodynamic characteristics of an aircraft at high angles of attack. J. Aircr. 31, 1109–1115 (1994).
Sedky, G., Lagor, F. D. & Jones, A. Unsteady aerodynamics of lift regulation during a transverse gust encounter. Phys. Rev. Fluids 5, 074701 (2020).
Ayancik, F. & Mulleners, K. All you need is time to generalise the Goman–Khrabrov dynamic stall model. J. Fluid Mech. 942, R8 (2022).
Brunton, S. L., Noack, B. R. & Koumoutsakos, P. Machine learning for fluid mechanics. Annu. Rev. Fluid Mech. 52, 477–508 (2020).
Kou, J. & Zhang, W. Data-driven modeling for unsteady aerodynamics and aeroelasticity. Prog. Aerosp. Sci. 125, 100725 (2021).
Le Clainche, S. et al. Improving aircraft performance using machine learning: a review. Aerosp. Sci. Technol. 138, 108354 (2023).
Reed, S. Development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks. Aeronaut. J. 111, 209–230 (2007).
Kou, J. & Xiao, T. Artificial intelligence and machine learning in aerodynamics. Metascience Aerosp. 1, 190–218 (2024).
Burelle, L. A., Yang, W., Kaiser, F. & Rival, D. E. Exploring the signature of distributed pressure measurements on non-slender delta wings during axial and vertical gusts. Phys. Fluids 32, 115110 (2020).
Fukami, K. & Taira, K. Data-driven modeling, sensing, and control of extreme vortex-airfoil interactions. In AIAA Aviation Forum and ASCEND 2024, 4531 (2024).
Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533–536 (1986).
Zhong, Y., Fukami, K., An, B. & Taira, K. Sparse sensor reconstruction of vortex-impinged airfoil wake with machine learning. Theor. Comput. Fluid Dyn. 37, 269–287 (2023).
Fukami, K., Fukagata, K. & Taira, K. Assessment of supervised machine learning methods for fluid flows. Theor. Comput. Fluid Dyn. 34, 497–519 (2020).
Mangalam, S. M. Phenomena-based real-time aerodynamic measurement system (PRAMS). In 2003 IEEE Aerospace Conference Proceedings (Cat. No. 03TH8652), Vol. 7, 3347–3356 (IEEE, 2003).
Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997).
Zhang, Y., Wang, S., Sun, G. & Mao, J. Aerodynamic surrogate model based on deep long short-term memory network: an application on high-lift device control. Proc. Inst. Mech. Eng., Part G: J. Aerosp. Eng. 236, 1081–1097 (2022).
Zheng, T., Cai, W., Chen, K., Xu, X. & Gu, J. An LSTM-based aerodynamic parameter recognition method for skip gliding targets. In Seventh Asia Pacific Conference on Optics Manufacture and 2021 International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM 2021), Vol. 12166, 899–906 (SPIE, 2022).
Hoblit, F. M. Gust Loads on Aircraft: Concepts and Applications (AIAA, 1988).
Kaiser, F., Iacobello, G. & Rival, D. E. Cluster-based bayesian approach for noisy and sparse data: application to flow-state estimation. Proc. R. Soc. A 480, 20230608 (2024).
Iacobello, G., Kaiser, F. & Rival, D. E. Load estimation in unsteady flows from sparse pressure measurements: application of transition networks to experimental data. Phys. Fluids 34, 025105 (2022).
Scarselli, F., Gori, M., Tsoi, A. C. V., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61–80 (2008).
Wu, Z. et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 4–24 (2020).
Chen, J., Hachem, E. & Viquerat, J. Graph neural networks for laminar flow prediction around random two-dimensional shapes. Phys. Fluids 33, 123607 (2021).
Li, K., Kou, J. & Zhang, W. Deep learning for multifidelity aerodynamic distribution modeling from experimental and simulation data. AIAA J. 60, 4413–4427 (2022).
Hines, D. & Bekemeyer, P. Graph neural networks for the prediction of aircraft surface pressure distributions. Aerosp. Sci. Technol. 137, 108268 (2023).
Li, T., Zou, S., Chang, X., Zhang, L. & Deng, X. Predicting unsteady incompressible fluid dynamics with finite volume informed neural network. Phys. Fluids 36, 043601 (2024).
Jabón, J., Corbera, S., Álvarez, R. & Barea, R. Aerodynamic shape optimization using graph variational autoencoders and genetic algorithms. Struct. Multidiscip. Optim. 67, 32 (2024).
Chen, T., Cai, L., Zeng, J., Zhang, W. & Wang, S. Aerodynamic performance prediction for wide-incidence turbines using graph neural network models driven by small-scale experimental data. J. Turbomachinery 147, 021008 (2025).
Vaswani, A. Attention is all you need. Advances in Neural Information Processing Systems (2017).
Bucker, A. et al. Latte: Language trajectory transformer. In 2023 IEEE International Conference on Robotics and Automation (ICRA), 7287–7294 (IEEE, 2023).
Mu, Z. et al. Generalizing morphologies in dam break simulations using transformer model. Phys. Fluids 37, 016612 (2025).
Jiang, J., Li, G., Jiang, Y., Zhang, L. & Deng, X. TransCFD: A transformer-based decoder for flow field prediction. Eng. Appl. Artif. Intell. 123, 106340 (2023).
Zuo, K., Ye, Z., Zhang, W., Yuan, X. & Zhu, L. Fast aerodynamics prediction of laminar airfoils based on deep attention network. Phys. Fluids 35, 037127 (2023).
Weymouth, G. D. & Font, B. WaterLily. jl: A differentiable and backend-agnostic Julia solver for incompressible viscous flow around dynamic bodies. Comput. Phys. Commun. 315, 109748 (2025).
Marzanek, M. F. & Rival, D. E. Separation mechanics of non-slender delta wings during streamwise gusts. J. Fluids Struct. 90, 286–296 (2019).
Longobardi, P. & Skaloud, J. Aerodynamic modeling of a delta-wing UAV for model-based navigation. CEAS Aeronaut. J. 15, 283–301 (2024).
Kumar, N., Saderla, S. & Kim, Y. Aerodynamic characterisation of delta wing unmanned aerial vehicle using non-gradient-based estimator. Aeronaut. J. 127, 1435–1451 (2023).
Kumar, N., Saderla, S. & Kim, Y. System identification of cropped delta UAVs from flight test methods using particle Swarm-Optimisation-based estimation. Aeronaut. J. 127, 76–96 (2023).
Stutz, C., Hrynuk, J. & Bohl, D. Investigation of static wings interacting with vertical gusts of indefinite length at low Reynolds numbers. Exp. Fluids 63, 82 (2022).
Biewald, L. Experiment tracking with weights and biases. https://www.wandb.com/ (2020).
Liu, Y., Li, K., Zhang, J., Wang, H. & Liu, L. Numerical bifurcation analysis of static stall of airfoil and dynamic stall under unsteady perturbation. Commun. Nonlinear Sci. Numer. Simul. 17, 3427–3434 (2012).
Kurtulus, D. F. On the unsteady behavior of the flow around NACA 0012 airfoil with steady external conditions at Re = 1000. Int. J. Micro Air Veh. 7, 301–326 (2015).
Du, J., Zhang, S., Wu, G., Moura, J. M. & Kar, S. Topology adaptive graph convolutional networks. Preprint at https://arxiv.org/abs/1710.10370 (2017).
He, M., Wei, Z. & Wen, J.-R. Convolutional Neural Networks on graphs with Chebyshev approximation, revisited. Adv. Neural Inf. Process. Syst. 35, 7264–7276 (2022).
Acknowledgements
A.L. acknowledges the support from the Westlake University Education Foundation. D.F. acknowledges support from the National Natural Science Foundation of China under Grant No. 12302365.
Author information
Authors and Affiliations
Contributions
D.C. contributed to the conception of the study, conducted experiments, developed artificial intelligence models, handled the visualization and coding aspects, and was responsible for writing the manuscript. A.L. was involved in developing artificial intelligence models and coding. B.S. contributed to both the coding and the conception of the study. D.E.R. and D.F. provided supervision and secured funding for this paper.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Communications Engineering thanks the anonymous reviewers for their contribution to the peer review of this work. Primary Handling Editors: [Philip Coatsworth]. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Chen, D., Liang, A., Sun, B. et al. Bridging spatial and temporal surface pressure dynamics for gust aerodynamic modeling. Commun Eng (2026). https://doi.org/10.1038/s44172-026-00612-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s44172-026-00612-9
