Multifidelity Aerodynamic Data Fusion by Autoencoder Transfer Learning

Accurate aerodynamic prediction often relies on high-fidelity (HF) simulations; however, their prohibitive computational costs severely limit their applicability in data-driven modeling. This limitation motivates the development of multifidelity strategies that leverage inexpensive low-fidelity (LF) information without compromising accuracy. Addressing this challenge, this work presents a multifidelity deep learning framework that combines autoencoder-based transfer learning with a newly developed multisplit conformal prediction (MSCP) strategy to achieve uncertainty-aware aerodynamic data fusion under extreme data scarcity. The methodology leverages abundant 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 (two-dimensional) and a transonic wing (three-dimensional) 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.