Tuning Machine Learning Outcomes for Airfoil Aerodynamics Seed Sensitivity in Predictive Performance
Diana-Andreea STERPU, Daniel MĂRIUȚA, Grigore CICAN, Ciprian-Marius LARCO, Lucian-Teodor GRIGORIE
Abstract. Accurate aerodynamic performance prediction remains critical in preliminary design and optimization workflows. This study proposes a hybrid deep learning framework that combines convolutional neural networks (CNNs), operating directly on raw airfoil geometries, with two fully connected branches that process engineered shape descriptors and flow parameters such as angle of attack and Reynolds number. This model is trained on a high-resolution dataset generated via XFOIL simulations, covering 91 NACA 4-digit airfoils across 200 aerodynamic conditions each, spanning Reynolds numbers from 500,000 up to 5,000,000 and angles of attack between -5˚ and 14˚. A key novelty introduced in this work is the investigation of how random seed initialization influences predictive accuracy. In machine learning, a random seed is a fixed numerical input that initializes the pseudo-random number generator responsible for operations such as weight-initialization and data shuffling. While typically treated as a background setting, the seed plays a critical role in defining the starting conditions of model training and can directly influence final performance outcomes. Results show that models with identical architecture and data can differ in performance by up to 250% depending solely on the seed used during training. To mitigate this variability, ensemble strategies based on seed diversity were also explored, leading to greater consistency and generalization. The top-performing single-seed model tested (seed 0) achieved a mean absolute percentage error (MAPE) of 1.1% for lift coefficient and 0.57% for drag coefficient, with R2 values of 0.9998 and 0.9954, respectively. The best ensemble built from three diverse seeds (C2) achieved slightly higher generalization: 1.43% MAPE CL, 1.19% MAPE CD, with R2 values of 0.9999 and 0.9968. All models tested, spanning ten seeds and five ensembles, achieved R2 scores exceeding 0.97. The results emphasize that treating seed selection as a fixed default can overlook significant variability, and that ensemble calibration can serve as a robust strategy to improve prediction reliability.
Keywords
Aerodynamic Prediction, Machine Learning, Random Seed Initialization, Ensemble Modelling, Airfoil Performance, Seed Sensitivity, Model Reproducibility, Pseudo-Random Number Generator
Published online 7/20/2026, 4 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Diana-Andreea STERPU, Daniel MĂRIUȚA, Grigore CICAN, Ciprian-Marius LARCO, Lucian-Teodor GRIGORIE, Tuning Machine Learning Outcomes for Airfoil Aerodynamics Seed Sensitivity in Predictive Performance, Materials Research Proceedings, Vol. 69, pp 84-87, 2026
DOI: https://doi.org/10.21741/9781644904251-15
The article was published as article 15 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Andrés-Pérez, E.; Paulete-Periáñez, C. On the Application of Surrogate Regression Models for Aerodynamic Coefficient Prediction. Complex Intell. Syst. 2021, 7, 1991–2021. https://doi.org/10.1007/s40747-021-00307-y
[2] Zuo, K.; Bu, S.; Zhang, W.; Hu, J.; Ye, Z.; Yuan, X. Fast Sparse Flow Field Prediction around Airfoils via Multi-Head Perceptron Based Deep Learning Architecture. Aerospace Sci. Technol. 2022, 130, 107942.
[3] Bakar, A.; Li, K.; Liu, H.; Xu, Z.; Alessandrini, M.; Wen, D. Multi-Objective Optimization of Low Reynolds Number Airfoil Using Convolutional Neural Network and Non-Dominated Sorting Genetic Algorithm. Aerospace 2022, 9, 35. https://doi.org/10.3390/aerospace9010035
[4] Galeazzo, F.C.C.; Garcia-Gasulla, M.; Boella, E.; Pocurull, J.; Lesnik, S.; Rusche, H.; Bnà, S.; Cerminara, M.; Brogi, F.; Marchetti, F.; et al. Performance Comparison of CFD Microbenchmarks on Diverse HPC Architectures. Computers 2024, 13, 115. https://doi.org/10.3390/computers13050115
[5] Cooper-Baldock, Z.; Vara Almirall, B.; Inthavong, K. Speed, Power and Cost Implications for GPU Acceleration of Computational Fluid Dynamics on HPC Systems. arXiv 2024, Preprint arXiv:2404.02482.
[6] Sterpu, D.-A.; Măriuța, D.; Grigorie, L.-T. A UDF-Based Approach for the Dynamic Stall Evaluation of Airfoils for Micro-Air Vehicles. Biomimetics 2024, 9, 339. https://doi.org/10.3390/biomimetics9060339
[7] Sterpu, D.-A.; Măriuța, D.; Cican, G.; Larco, C.-M.; Grigorie, L.-T. Machine Learning Prediction of Airfoil Aerodynamic Performance Using Neural Network Ensembles. Appl. Sci. 2025, 15, 7720. https://doi.org/10.3390/app15147720
