Multi-fidelity aerodynamic data fusion by autoencoder transfer learning

2025-12-15

AI Summary

To address the scarcity and high computational cost of high-fidelity data in high-accuracy aerodynamic prediction, this paper proposes a multi-fidelity deep learning framework that synergistically integrates abundant low-fidelity data with a minimal number of high-fidelity samples. We introduce a novel Multi-Segment Conformal Prediction (MSCP) strategy, coupled with a frozen autoencoder-based transfer learning approach, enabling physics-consistent knowledge reuse in the latent space and uncertainty-aware fusion. Evaluated on NACA airfoils (2D) and transonic wings (3D), the method achieves significant correction of low-fidelity bias using only a few high-fidelity samples: pressure prediction errors are substantially reduced, and pointwise uncertainty coverage remains stably above 95%. This work establishes a new paradigm for reliable aerodynamic modeling under extreme data scarcity.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate aerodynamic prediction often relies on high-fidelity simulations; however, their prohibitive computational costs severely limit their applicability in data-driven modeling. This limitation motivates the development of multi-fidelity strategies that leverage inexpensive low-fidelity information without compromising accuracy. Addressing this challenge, this work presents a multi-fidelity deep learning framework that combines autoencoder-based transfer learning with a newly developed Multi-Split Conformal Prediction (MSCP) strategy to achieve uncertainty-aware aerodynamic data fusion under extreme data scarcity. The methodology leverages abundant Low-Fidelity (LF) data to learn a compact latent physics representation, which acts as a frozen knowledge base for a decoder that is subsequently fine-tuned using scarce HF samples. Tested on surface-pressure distributions for NACA airfoils (2D) and a transonic wing (3D) databases, the model successfully corrects LF deviations and achieves high-accuracy pressure predictions using minimal HF training data. Furthermore, the MSCP framework produces robust, actionable uncertainty bands with pointwise coverage exceeding 95%. By combining extreme data efficiency with uncertainty quantification, this work offers a scalable and reliable solution for aerodynamic regression in data-scarce environments.

Problem

• Fuses multi-fidelity aerodynamic data under extreme scarcity
• Corrects low-fidelity deviations for high-accuracy pressure predictions
• Provides uncertainty quantification with robust prediction intervals

Innovation

• Autoencoder transfer learning for multi-fidelity data fusion
• Multi-Split Conformal Prediction for uncertainty quantification
• Latent physics representation from low-fidelity data fine-tuned