Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis

Reha Avşar; Tuğba Tetik

doi:10.30518/jav.1886935

Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis

Abstract

Reliably forecasting airfoil-generated aerodynamic noise is a prerequisite for designing quieter aircraft and wind turbines. Although machine learning (ML) models deliver strong predictive performance in aeroacoustics tasks, their opaque, "black-box" nature frequently impedes adoption in engineering design processes that demand transparent reasoning. In this work, three ML paradigms—Linear Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGB)—are systematically evaluated for airfoil self-noise prediction on the NASA benchmark dataset. Generalization is quantified through 10-fold cross-validation using the coefficient of determination (𝑅²), root mean squared error (RMSE), and mean absolute error (MAE). To overcome the interpretability barrier, SHapley Additive exPlanations (SHAP) is applied, providing both global feature-importance rankings and instance-level explanations of model outputs. XGB attains the highest accuracy, with a cross-validated R² of 0.9498 ± 0.0138, a test R² of 0.9577, and an RMSE of 1.4553 dB. SHAP reveals that frequency, suction-side displacement thickness, and chord length exert the strongest influence on predicted sound pressure levels, whereas angle of attack ranks lowest—an initially surprising result that is nonetheless consistent with the limited angular range covered in the original NASA experiments. These findings illustrate that pairing gradient boosting with explainable AI yields a credible and interpretable prediction framework for aeroacoustic engineering.

Keywords

Ethical Statement

Not applicable.

Thanks

We thank the editor and reviewers in advance for their time and feedback.

References

Amirsalari, B., & Rocha, J. (2023). Recent advances in airfoil self-noise passive reduction. Aerospace, 10(9), 791.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Brooks, T. F., Pope, D. S., & Marcolini, M. A. (1989). Airfoil self-noise and prediction (No. L-16528).
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794).
Choudhary, R., Kumar, A., C, P., Naik, M. M., Choudhury, M., & Khan, N. A. (2025). Predicting water quality index using stacked ensemble regression and SHAP based explainable artificial intelligence. Scientific Reports, 15(1), 31139.
Dikshit, A., & Pradhan, B. (2021). Interpretable and explainable AI (XAI) model for spatial drought prediction. Science of the Total Environment, 801, 149797.
Dua, D., & Graff, C. (2019). UCI Machine Learning Repository. University of California, School of Information and Computer Sciences. http://archive.ics.uci.edu/ml
Williams, J. E. F., & Hall, L. H. (1970). Aerodynamic sound generation by turbulent flow in the vicinity of a scattering half plane. Journal of Fluid Mechanics, 40(4), 657–670.

Givisis, I., Kalatzis, D., Christakis, C., & Kiouvrekis, Y. (2025). Comparing explainable AI models: SHAP, LIME, and their role in electric field strength prediction over urban areas. Electronics, 14(23), 4766.
Hosseini, Z. S., & Mohseni, A. (2025). Identification of airfoil stall using airborne acoustic signature under room conditions by machine learning. Results in Engineering, 28, 107561.
Isbilen, F., Bektas, O., Avsar, R., & Konar, M. (2025). Improved machine learning models with a similarity-based approach for remaining useful life prediction. The Aeronautical Journal, 129(1332), 485–505.
Kocak, E., & Ayli, E. (2024). Prediction of noise generated by rod-airfoil configuration: An investigation based on experiments and machine learning. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 238(14), 1440–1453.
Krishnan, N. S. R., & Uppu, S. P. (2023). A novel approach for noise prediction using Neural network trained with an efficient optimization technique. International Journal for Simulation and Multidisciplinary Design Optimization, 14, 3.
Li, S., & Lee, S. (2020). A machine learning-based fast prediction of rotorcraft broadband noise. In AIAA Aviation 2020 Forum (p. 2588).
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (Vol. 30, pp. 4765–4774).
Nadkarni, S. B., Vijay, G. S., & Kamath, R. C. (2023). Comparative study of random forest and gradient boosting algorithms to predict airfoil self-noise. Engineering Proceedings, 59(1), 24.
Pal, P., Datta, R., Rajbansi, D., & Segev, A. (2019). A neural net based prediction of sound pressure level for the design of the aerofoil. In International Conference on Swarm, Evolutionary and Memetic Computing (pp. 105– 112). Springer.
Pandey, H., Pandey, P., & Gupta, D. (2024). Airfoil self noise prediction using machine learning and explainable AI. In 2024 IEEE Recent Advances in Intelligent Computational Systems (pp. 1–6). IEEE.
Qayyum, F., Khan, M. A., Kim, D. H., Ko, H., & Ryu, G. A. (2023). Explainable AI for material property prediction based on energy cloud: A Shapley-driven approach. Materials, 16(23), 7322.
Saetta, E., Tognaccini, R. & Iaccarino, G. (2022). Machine learning to predict aerodynamic stall. International Journal of Computational Fluid Dynamics, 36(7), 641–654.
Tahmassebi, A., Motamedi, M., Alavi, A. H., & Gandomi, A. H. (2022). An explainable prediction framework for engineering problems: Case studies in reinforced concrete members modeling. Engineering Computations, 39(2), 609–626.
Tetik, T. (2026). Feature engineering and explainable artificial intelligence for state of health estimation of Lithium-ion batteries. Journal of Energy Storage, 144, 119873.
Tetik, T., & Cihan, P. (2026). Non-parametric ground motion duration and energy-based intensity measure models: A novel stacking ensemble model using regional seismic data. Soil Dynamics and Earthquake Engineering, 203, 110135.
Uluocak, I. (2025). A comparative evaluation of multivariate hybrid deep learning methods for airfoil noise forecasting. Signal, Image and Video Processing, 19(16), 1340.
Wang, Q., Zhang, H., Wang, X., & Ni, Y. (2025). Wind turbine airfoil noise prediction method based on generalized airfoil database and Residul Neural Network. Applied Sciences, 15(9), 5123.
Yang, H., Yuan, W., Zhu, W., Sun, Z., Zhang, Y., & Zhou, Y. (2024). Wind turbine airfoil noise prediction using dedicated airfoil database and deep learning technology. Applied Energy, 364, 123165.
Zhu, L., Zhang, W., Kou, J., & Liu, Y. (2019). Machine learning methods for turbulence modeling in subsonic flows around airfoils. Physics of Fluids, 31(1), 015105.

Details

Primary Language

English

Subjects

Aerospace Engineering (Other)

Journal Section

Research Article

Authors

Reha Avşar ^*
0000-0001-9450-5728
Türkiye

Tuğba Tetik
0000-0002-0044-706X
Türkiye

Early Pub Date

June 6, 2026

Publication Date

June 27, 2026

Submission Date

February 12, 2026

Acceptance Date

April 8, 2026

Published in Issue

Year 2026 Volume: 10 Number: 2

DOI

https://doi.org/10.30518/jav.1886935

IZ

https://izlik.org/JA52SU24WL

Cite

RIS / Bibtex

APA

Avşar, R., & Tetik, T. (2026). Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis. Journal of Aviation, 10(2), 291-300. https://doi.org/10.30518/jav.1886935

AMA

1.Avşar R, Tetik T. Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis. JAV. 2026;10(2):291-300. doi:10.30518/jav.1886935

Chicago

Avşar, Reha, and Tuğba Tetik. 2026. “Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study With SHAP Analysis”. Journal of Aviation 10 (2): 291-300. https://doi.org/10.30518/jav.1886935.

EndNote

Avşar R, Tetik T (June 1, 2026) Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis. Journal of Aviation 10 2 291–300.

IEEE

[1]R. Avşar and T. Tetik, “Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis”, JAV, vol. 10, no. 2, pp. 291–300, June 2026, doi: 10.30518/jav.1886935.

ISNAD

Avşar, Reha - Tetik, Tuğba. “Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study With SHAP Analysis”. Journal of Aviation 10/2 (June 1, 2026): 291-300. https://doi.org/10.30518/jav.1886935.

JAMA

1.Avşar R, Tetik T. Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis. JAV. 2026;10:291–300.

MLA

Avşar, Reha, and Tuğba Tetik. “Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study With SHAP Analysis”. Journal of Aviation, vol. 10, no. 2, June 2026, pp. 291-00, doi:10.30518/jav.1886935.

Vancouver

1.Reha Avşar, Tuğba Tetik. Explainable Machine Learning for Airfoil Self-Noise Prediction: A Comparative Study with SHAP Analysis. JAV. 2026 Jun. 1;10(2):291-300. doi:10.30518/jav.1886935