Volume 19 Issue 1
Mar.  2026
Turn off MathJax
Article Contents
Article Navigation >  Water Science and Engineering  > 2026  >  19(1): 35-46
Ngoc Thi Huynh, Anh Thu Thi Phan, Tan Tai Trieu, Ho Hong Duy Nguyen, Thanh Nhan Nguyen. 2026: Prediction of turbulent flow over a single square cylinder using generative artificial intelligence. Water Science and Engineering, 19(1): 35-46. doi: 10.1016/j.wse.2025.12.004
Citation: Ngoc Thi Huynh, Anh Thu Thi Phan, Tan Tai Trieu, Ho Hong Duy Nguyen, Thanh Nhan Nguyen. 2026: Prediction of turbulent flow over a single square cylinder using generative artificial intelligence. Water Science and Engineering, 19(1): 35-46. doi: 10.1016/j.wse.2025.12.004
shu

Prediction of turbulent flow over a single square cylinder using generative artificial intelligence

doi: 10.1016/j.wse.2025.12.004

  • a. Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT), 268 Ly Thuong Kiet Street, Dien Hong Ward, Ho Chi Minh City 70000, Viet Nam;

  • b. Vietnam National University Ho Chi Minh City (VNU-HCM), Linh Xuan Ward, Ho Chi Minh City 70000, Viet Nam;

  • c. Ocean Engineering Department, Pukyong National University, Busan 48513, South Korea

  • Received Date: 2025-02-20
  • Accepted Date: 2025-12-09
    • Available Online: 2026-03-28
    Abstract
  • Turbulent flow around bluff bodies like square cylinders involves complex vortex shedding and flow separation, challenging traditional computational methods. This study developed a novel approach using a generative artificial intelligence (GenAI) model to predict turbulent flow over a single square cylinder. The GenAI model was trained using high-fidelity simulation data generated from an advanced differentiable physics framework (PhiFlow), which can efficiently capture the nonlinear dynamics of turbulent flow. Flow predictions from the GenAI model were validated against numerical results, demonstrating high accuracy in capturing key flow characteristics, including vortex shedding frequency. Stability and spatial—temporal frequency analyses revealed strong agreement between the diffusion model and numerical simulations. This study highlights the potential of GenAI models to significantly enhance the prediction and analysis of turbulent flow, offering a powerful tool for fluid dynamics research and engineering applications.

     

    • FullText(HTML)
  • loading
    • References(58)
  • [1]
    Bai, W., Mingham, C.G., Causon, D.M., Qian, L., 2016. Detached eddy simulation of turbulent flow around square and circular cylinders on Cartesian cut cells. Ocean Engineering 117, 1-14. https://doi.org/10.1016/j.oceaneng.2016.03.009.
    [2]
    Brahmachary, S., Thuerey, N., 2023. Unsteady cylinder wakes from arbitrary bodies with differentiable physics-assisted neural network. Physical Review E 109(5), 055304. https://doi.org/10.1103/PhysRevE.109.055304.
    [3]
    Brandstetter, J., Worrall, D.E., Welling, M., 2022. Message passing neural PDE solvers. arXiv preprint arXiv:2202.03376. https://doi.org/10.48550/arXiv.2202.03376.
    [4]
    Dezfouli, M., Haghighi Poshtiri, A., 2024. Numerical study flow-induced vibration of four two-degree-of-freedom circular cylinders in lozenge configuration using random vortex-boundary element scheme. Ocean Engineering 301, 117419. https://doi.org/10.1016/j.oceaneng.2024.117419.
    [5]
    Dimiduk, D.M., Holm, E.A., Niezgoda, S.R., 2018. Perspectives on the impact of machine learning, deep learning, and artificial intelligence on materials, processes, and structures engineering. Integrating Materials and Manufacturing Innovation 7(3), 157-172. https://doi.org/10.1007/S40192-018-0117-8.
    [6]
    Do, T.H., Pham, M.V., Huynh, N.T., Phan, T.A.T., Dinh, Q.T., Le, H.L., Nguyen, T.N., Nguyen, H.H.D., 2025. Interpretable ensemble learning approaches for predicting unconfined compressive strength of expansive soils. Transportation Infrastructure Geotechnology 12(5), 152. https://doi.org/10.1007/S40515-025-00609-5.
    [7]
    Dresdner, G., Kochkov, D., Norgaard, P., Zepeda-Nunez, L., Smith, J.A., Brenner, M.P., Hoyer, S., 2022. Learning to correct spectral methods for simulating turbulent flows. arXiv preprint arXiv:2207.00556. https://arxiv.org/abs/2207.00556v2.
    [8]
    Dryden, H.L., 1943. A review of the statistical theory of turbulence. Quarterly of Applied Mathematics 1(1), 7-42. https://doi.org/10.1090/QAM/8209.
    [9]
    Duarte, C.A.R., Duarte, L.E.R., de Lima, B.S., de Souza, F.J., 2020. Performance of an optimized k−ε turbulence model for flows around bluff bodies. Mechanics Research Communications 105, 103518. https://doi.org/10.1016/j.mechrescom.2020.103518.
    [10]
    Feng, Z.G., Michaelides, E.E., 2009. Heat transfer in particulate flows with Direct Numerical Simulation (DNS). International Journal of Heat and Mass Transfer 52(3-4), 777-786. https://doi.org/10.1016/j.ijheatmasstransfer.2008.07.023.
    [11]
    Fonias, E.N., Grigoriadis, D.G.E., 2018. Large eddy simulation of near-bed pipelines in oscillatory flow. Coastal Engineering 133, 76-91. https://doi.org/10.1016/j.coastaleng.2017.12.005.
    [12]
    Fukami, K., Fukagata, K., Taira, K., 2019. Super-resolution reconstruction of turbulent flows with machine learning. Journal of Fluid Mechanics 870, 106-120. https://doi.org/10.1017/JFM.2019.238.
    [13]
    Fukami, K., Fukagata, K., Taira, K., 2021. Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows. Journal of Fluid Mechanics 909, A9. https://doi.org/10.1017/JFM.2020.948.
    [14]
    Girimaji, S.S., 2023. Turbulence closure modeling with machine learning approaches: A perspective. arXiv preprint arXiv:2312.14902. https://arxiv.org/abs/2312.14902v1.
    [15]
    Ha, Y.S., Nguyen, H.H.D., Nguyen, T.N., Pham, M.V., 2025. UAV imagery-based landslide detection in challenging environment using pixel segmentation and generative AI approach. Modeling Earth Systems and Environment 11(5), 342. https://doi.org/10.1007/S40808-025-02537-2.
    [16]
    Ho, J., Jain, A., Abbeel, P., 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33, 6840-6851.
    [17]
    Holl, P., Koltun, V., Thuerey, N., 2020. Learning to control PDEs with differentiable physics. arXiv preprint arXiv:2001.07457. https://doi.org/10.48550/arXiv.2001.07457.
    [18]
    Hu, T., Liao, S., 2020. On the risks of using double precision in numerical simulations of spatio-temporal chaos. Journal of Computational Physics 418, 109629. https://doi.org/10.1016/j.jcp.2020.109629.
    [19]
    Huynh, N.T., Nguyen, H.H.D., Phan, A.T.T., Trieu, T.T., Nguyen, T.N., 2025a. Effect of pile spacing on scour depth in array configurations under steady flow conditions. Marine Georesources & Geotechnology 1-21. https://doi.org/10.1080/1064119X.2025.2500072.
    [20]
    Huynh, N.T., Phan, A.T.T., Huynh, Q.D., Nguyen, H.H.D., Nguyen, T.N., 2025b. Machine learning-based prediction of scour depth around complex bridge piers with model interpretability. Ocean Engineering 340, 122479. https://doi.org/10.1016/j.oceaneng.2025.122479.
    [21]
    Huynh, N.T., Phan, A.T.T., Trieu, T.T., Nguyen, H.H.D., Nguyen, T.N., 2025c. A CNN deep learning approach to scour depth estimation around complex bridge piers in steady flow environments. Advances in Bridge Engineering 6(1), 1-29. https://doi.org/10.1186/S43251-025-00170-8.
    [22]
    Ikani, N., Pu. J.H., Hanmaiahgari, P.R., Kumar, B., Al-Qadami, E.H.H., Razi, M.A.M., Zang, S., 2025. Computational and experimental analysis of flow velocity and complex vortex formation around a group of bridge piers. Water Science and Engineering 18(2), 247-258.
    [23]
    Ikani, N., Pu, J.H., Zang, S., Hamid Hussein Al-Qadami, E., Razi, A., 2024. Detailed turbulent structures investigation around piers group induced flow. Experimental Thermal and Fluid Science 152, 111112. https://doi.org/10.1016/j.expthermflusci.2023.111112.
    [24]
    Jain, I., Manikandan, J., 2022. Study and evaluation of machine learning algorithms for aerospace applications. In: Proceedings of the 2022 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES). IEEE, Yogyakarta, pp. 1-6. https://doi.org/10.1109/ICARES56907.2022.9993608.
    [25]
    Kadivar, M., Tormey, D., McGranaghan, G., 2021. A review on turbulent flow over rough surfaces: Fundamentals and theories. International Journal of Thermofluids 10, 100077. https://doi.org/10.1016/j.ijft.2021.100077.
    [26]
    Kim, D., Jung, S., Na, W.B., 2021. Evaluation of turbulence models for estimating the wake region of artificial reefs using particle image velocimetry and computational fluid dynamics. Ocean Engineering 223, 108673. https://doi.org/10.1016/j.oceaneng.2021.108673.
    [27]
    Kohl, G., Um, K., Thuerey, N., 2020. Learning similarity metrics for numerical simulations. In: Proceedings of the International Conference on Machine Learning. PMLR, pp. 5349-5360.
    [28]
    Kurz, M., Offenhauser, P., Beck, A., 2022. Deep reinforcement learning for turbulence modeling in large eddy simulations. International Journal of Heat and Fluid Flow 99, 109094. https://doi.org/10.1016/j.ijheatfluidflow.2022.109094.
    [29]
    Le Clainche, S., Ferrer, E., Gibson, S., Cross, E., Parente, A., Vinuesa, R., 2023. Improving aircraft performance using machine learning: A review. Aerospace Science and Technology 138, 108354. https://doi.org/10.1016/J.AST.2023.108354.
    [30]
    Li, R., Song, B., Chen, Y., Jin, X., Zhou, D., Han, Z., Chen, W.L., Cao, Y., 2024. Deep learning reconstruction of high-Reynolds-number turbulent flow field around a cylinder based on limited sensors. Ocean Engineering 304, 117857. https://doi.org/10.1016/j.oceaneng.2024.117857.
    [31]
    Liang, D., Jia, H., Xiao, Y., Yuan, S., 2022. Experimental investigation of turbulent flows around high-rise structure foundations and implications on scour. Water Science and Engineering 15(1), 47-56. https://doi.org/10.1016/j.wse.2021.12.002.
    [32]
    List, B., Chen, L.-W., Thuerey, N., 2022. Learned turbulence modelling with differentiable fluid solvers: Physics-based loss-functions and optimisation horizons. Journal of Fluid Mechanics 949, A25. https://doi.org/10.1017/jfm.2022.738.
    [33]
    Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S., 2022. A ConvNet for the 2020s. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp. 11976-11986.
    [34]
    Lysenko, D.A., Donskov, M., Ertesvag, I.S., 2023. Large-eddy simulations of the flow past a bluff-body with active flow control based on trapped vortex cells at Re = 50000. Ocean Engineering 280, 114496. https://doi.org/10.1016/j.oceaneng.2023.114496.
    [35]
    Maulik, R., Mohan, A., Lusch, B., Madireddy, S., Balaprakash, P., Livescu, D., 2020. Time-series learning of latent-space dynamics for reduced-order model closure. Physica D: Nonlinear Phenomena 405, 132368. https://doi.org/10.1016/j.physd.2020.132368.
    [36]
    Mazaheri, K., Abtahi Mehrjardi, S.A., 2024. Usage of high-fidelity large eddy simulation to improve the turbulence modeling of Reynolds averaged Navier Stokes simulation in film cooling applications via a neural network. International Journal of Thermofluids 23, 100718. https://doi.org/10.1016/j.ijft.2024.100718.
    [37]
    Moin, P., Mahesh, K., 1998. Direct numerical simulation: A tool in turbulence research. Annual Review of Fluid Mechanics 30, 539-578. https://doi.org/10.1146/annurev.fluid.30.1.539.
    [38]
    Mondal, R., Alam, M.M., 2023. Blockage effect on wakes of various bluff bodies: A review of confined flow. Ocean Engineering 286, 115592. https://doi.org/10.1016/j.oceaneng.2023.115592.
    [39]
    Nguyen, H.H.D., Pradhan, A.M.S., Song, C.H., Lee, J.S., Kim, Y.T., 2024a. A hybrid approach combining physics-based model with extreme value analysis for temporal probability of rainfall-triggered landslide. Landslides 22(1), 149-168. https://doi.org/10.1007/S10346-024-02366-X.
    [40]
    Nguyen, H.H.D., Nguyen, T.N., Phan, T.A.T., Huynh, N.T., Huynh, Q.D., Trieu, T.T., 2025a. Explainable artificial intelligence model for the prediction of undrained shear strength. Theoretical and Applied Mechanics Letters 15(3), 100578. https://doi.org/10.1016/j.taml.2025.100578.
    [41]
    Nguyen, H.H.D., Nguyen, T.N., Phan, T.A.T., Nguyen, G.P., Pham, T.K.H., Huynh, N.T., 2025b. Uncertainty effect of saturated depth on large scale assessment of landslide: Case study at Saka Town, Hiroshima Prefecture, Japan. Earth Science Informatics 18(2), 208. https://doi.org/10.1007/S12145-025-01714-2.
    [42]
    Nguyen, T.N., Yun, D.H., Kim, Y.T., 2024b. Development of an empirical equation that predicts local scour around a single cube-type artificial reef under a steady current. Ocean Engineering 308, 118332. https://doi.org/10.1016/j.oceaneng.2024.118332.
    [43]
    Nguyen, T.N., Yun, D.H., Kim, Y.T., 2024c. Measurement and prediction of scour volume around a cubic artificial reef under steady flow conditions using stereo vision. Ocean Engineering 313, 119635. https://doi.org/10.1016/j.oceaneng.2024.119635.
    [44]
    Pandey, S., Schumacher, J., Sreenivasan, K.R., 2020. A perspective on machine learning in turbulent flows. Journal of Turbulence 21(9-10), 567-584. https://doi.org/10.1080/14685248.2020.1757685.
    [45]
    Pham, M.V., Song, C.H., Nguyen, T.N., Lee, J.S., Kim, Y.T., 2023. Real-time debris flow detection using deep convolutional neural network and Jetson Nano. In: Proceedings of E3S Web of Conferences. EDP Sciences, 415, 03021. https://doi.org/10.1051/e3sconf/202341503021.
    [46]
    Pham, M.V., Ha, Y.S., Nguyen, T.N., Kim, Y.T., 2025. Segmental retaining wall displacement monitoring using RGB-D image and generative AI approach. Measurement 254, 117932. https://doi.org/10.1016/j.measurement.2025.117932.
    [47]
    Regenwetter, L., Nobari, A.H., Ahmed, F., 2022. Deep generative models in engineering design: A review. Journal of Mechanical Design 144(7), 071704. https://doi.org/10.1115/1.4053859.
    [48]
    Ronneberger, O., Fischer, P., Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, pp. 234-241.
    [49]
    Sagaut, P., 2006. Boundary conditions. In: Large Eddy Simulation for Incompressible Flows. Scientific Computation. Springer, Berlin, Heidelberg, pp. 323-367. https://doi.org/10.1007/3-540-26403-5_10.
    [50]
    Shen, H., Zhang, J., Xiong, B., Hu, R., Chen, S., Wan, Z., Wang, X., Zhang, Y., Gong, Z., Bao, G., et al., 2025. Efficient diffusion models: A survey. arXiv preprint arXiv:2502.06805. https://doi.org/10.48550/arXiv.2502.06805.
    [51]
    Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H., 2021. Efficient attention: Attention with linear complexities. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 3530-3538.
    [52]
    Tretola, G., Vogiatzaki, K., Navarro-Martinez, S., 2021. Effect of the density ratio variation on the dynamics of a liquid jet injected into a gaseous cross-flow. Physics of Fluids 33(9), 092120. https://doi.org/10.1063/5.0064149.
    [53]
    Truong-Hong, L., Nguyen, N., Lindenbergh, R., Fisk, P., Huynh, T., 2021. Towards a digital twin of a storage tank using laser scan data. The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences 46, 119-124. https://doi.org/10.5194/isprs-archives-XLVI-4-W4-2021-119-2021.
    [54]
    Vaswani, A., Brain, G., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I., 2017. Attention is all you need. In: Advances in Neural Information Processing Systems 30. NeurIPS.
    [55]
    Vinuesa, R., 2024. Perspectives on predicting and controlling turbulent flows through deep learning. Physics of Fluids 36(3), 31401. https://doi.org/10.1063/5.0190452/3268677.
    [56]
    Yaghoubi, E., Yaghoubi, E., Khamees, A., Vakili, A. H., 2024. A systematic review and meta-analysis of artificial neural network, machine learning, deep learning, and ensemble learning approaches in field of geotechnical engineering. Neural Computing and Applications 36(21), 12655-12699. https://doi.org/10.1007/S00521-024-09893-7.
    [57]
    Yang, B., Liang, B., Zhang, Q., Zhao, M., Qu, M., 2024. Numerical investigation of flow around the sagging pipeline above an equilibrium scoured bed. Ocean Engineering 311, 118785. https://doi.org/10.1016/j.oceaneng.2024.118785.
    [58]
    Zhu, C., Xiao, D., Fu, J., Feng, Y., Fu, R., Wang, J., 2024. A data-driven computational framework for non-intrusive reduced-order modelling of turbulent flows passing around bridge piers. Ocean Engineering 308, 118308. https://doi.org/10.1016/j.oceaneng.2024.118308.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(1)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (16) PDF downloads(0) Cited by()
    Proportional views
    Related

    Copyright © 2009 Editorial office of Water Science and Engineering 苏ICP备12023610号-1

    Supported by: Beijing Renhe Information Technology Co. Ltd   support: info@rhhz.net

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return