Application of machine learning methods to predict aerodynamic pressure coefficients on rectangular buildings and structures

Introduction. Wind effects are one of the key factors in the design of buildings and structures. Normative calculations, physical and numerical modelling, as well as in-situ measurements have a number of limitations in application. The use of machine learning (ML) technologies opens up new opportunities for rapid and accurate prediction of wind loads. The application of ML models to assess the distribution of aerodynamic pressure coefficients on rectangular buildings is considered, which allows not only to calculate integral characteristics (forces, moments), but also to analyze in detail the distribution of loads on facades.

Materials and methods. For model training, the Tokyo Polytechnic University database was used, which presents the results of wind tunnel tests on building models of various heights and widths. Data augmentation was performed, which increased the original example size and increased the ability of ML models to generalize various geometric configurations. During feature processing, different angles of wind attack were taken into account, and the correlation of features was analyzed in order to eliminate multicollinearity. Linear regression, decision tree and gradient boosting (CatBoost) were the main prediction methods.

Results. The calculations showed that the best balance between the accuracy of predictions and maintaining physical interpretability was provided by gradient boosting over the decision tree (CatBoost), reducing the average weighted error to 16–18 %. In addition, a comparison was made with the results of aerodynamic tests, which confirmed the adequacy of the proposed approach.

Conclusions. The application of machine learning methods, in particular gradient boosting, makes it possible to reliably predict aerodynamic pressure coefficients on various dimensional shapes of buildings at a wide range of wind attack angles. The obtained results demonstrate the promising use of ML models to accelerate and reduce the cost of wind impact assessment stages.

1. Stathopoulos T., Alrawashdeh H. Wind loads on buildings: A code of practice perspective. Journal of Wind Engineering and Industrial Aerodynamics. 2020; 206:104338. DOI: 10.1016/j.jweia.2020.104338

2. Satanov A.A., Vasin A.D. Experimental study of wind pressure distribution on a unique shape high-rise building. Privolzhsky Scientific Journal. 2021; 3(59):38-46. EDN AANDEZ. (rus.).

3. Khazov P.A., Shilov S.S. Geometric optimization of the aerodynamics of a high-rise building with a built-in wind generator. Bulletin of SUSU. Series: Construction Engineering and Architecture. 2024; 24(3):73-82. DOI: 10.14529/build240307. EDN VJYQQC. (rus.).

4. Yan B., Li Y., Li X., Zhou X., Wei M., Yang Q. et al. Wind tunnel investigation of twisted wind effect on a typical super-tall building. Buildings. 2022; 12(12):2260. DOI: 10.3390/buildings12122260

5. Sari D.P., Cho K.P. Performance Comparison of Different Building Shapes Using a Wind Tunnel and a Computational Model. Buildings. 2022; 12(2):144. DOI: 10.3390/buildings12020144

6. Potsis T., Tominaga Y., Stathopoulos T. Computational wind engineering: 30 years of research progress in building structures and environment. Journal of Wind Engineering and Industrial Aerodynamics. 2023; 234:105346. DOI: 10.1016/j.jweia.2023.105346

7. Saiyan S.G., Vasiliev A.V. Numerical Simulation of the Dynamic Response of the “Evolution” Tower under Wind Action Considering Surrounding Buildings and Turbulence Resolution. Vestnik MGSU [Monthly Journal on Construction and Architecture]. 2025; 20(2):246-279. DOI: 10.22227/1997-0935.2025.2.246-279 (rus.).

8. Wijesooriya K., Mohotti D., Lee C.K., Mendis P. A technical review of computational fluid dynamics (CFD) applications on wind design of tall buildings and structures: Past, present and future. Journal of Building Engineering. 2023; 74:106828. DOI: 10.1016/j.jobe.2023.106828

9. Saiyan S.G., Efimova A.M. Computational aerodynamic studies of the MIBC “Moscow-city” complex during sequential construction of buildings. Vestnik MGSU [Monthly Journal on Construction and Architecture]. 2024; 19(6):906-941. DOI: 10.22227/1997-0935.2024.6.906-941. EDN OKQQFI. (rus.).

10. Wang X., Zhang G., Li Y., Kong H., Liu L., Zhang C. Field Measurements of Wind-Induced Responses of the Shanghai World Financial Center during Super Typhoon Lekima. Sensors. 2023; 23(14):6519. DOI: 10.3390/s23146519

11. Cheng X.X., Zhao L., Ge Y.J., Dong J., Peng Y. Full-Scale/Model Test Comparisons to Validate the Traditional Atmospheric Boundary Layer Wind Tunnel Tests : Literature Review and Personal Perspectives. Applied Sciences. 2024; 14(2):782. DOI: 10.3390/app14020782

12. Yi J., Li Q.S. Wind tunnel and full-scale study of wind effects on a super-tall building. Journal of Fluids and Structures. 2015; 58:236-253. DOI: 10.1016/j.jfluidstructs.2015.08.005

13. Charisi S., Thiis T.K., Aurlien T. Full-scale measurements of wind-pressure coefficients in twin medium-rise buildings. Buildings. 2019; 9(3):63. DOI: 10.3390/buildings9030063

14. Wu T., Snaiki R. Applications of machine learning to wind engineering. Frontiers in Built Environment. 2022; 8. DOI: 10.3389/fbuil.2022.811460

15. Alanani M., Elshaer A. ANN-based optimization framework for the design of wind load resisting system of tall buildings. Engineering Structures. 2023; 285:116032. DOI: 10.1016/j.engstruct.2023.116032

16. Nikose T.J., Sonparote R.S. Dynamic along wind response of tall buildings using Artificial Neural Network. Cluster Computing. 2019; 22(S2):3231-3246. DOI: 10.1007/s10586-018-2027-0

17. Ding Y., Ye X.W., Guo Y. Wind load assessment with the JPDF of wind speed and direction based on SHM data. Structures. 2023; 47:2074-2080. DOI: 10.1016/j.istruc.2022.12.028

18. Oh B.K., Glisic B., Kim Y., Park H.S. Convolutional neural network-based wind-induced response estimation model for tall buildings. Computer-Aided Civil and Infrastructure Engineering. 2019; 34(10):843-858. DOI: 10.1111/mice.12476

19. Yetkin S., Abuhanieh S., Yigit S. Investigation on the abilities of different artificial intelligence methods to predict the aerodynamic coefficients. Expert Systems with Applications. 2024; 237:121324. DOI: 10.1016/j.eswa.2023.121324

20. Zakharov F., Qian J., Xu Yi. Forecasting wind loads on high-rise buildings using the ensemble method of combining results. Universum. 2024; 11-4(128):66-75. DOI: 10.32743/UniTech.2024.128.11.18607. EDN UKMYTR. (rus.).

21. Saiyan S.G., Shelepina V.B. Prediction of aerodynamic coefficients for twisting shapes of buildings and structures based on machine learning and CFD-modelling. Vestnik MGSU [Monthly Journal on Construction and Architecture]. 2024; 19(5):713-728. DOI: 10.22227/1997-0935.2024.5.713-728. EDN HUZBDU. (rus.).

22. Melbourne W.H. Comparison of measurements on the CAARC standard tall building model in simulated model wind flows. Journal of Wind Engineering and Industrial Aerodynamics. 1980; 6(1-2):73-88. DOI: 10.1016/0167-6105(80)90023-9