Aerodynamic Shape Design Space Exploration with Deep Latent Diffusion Model

Abstract

We propose DiffGeo, a latent space diffusion-based generative framework for aerodynamic design space exploration under extreme data scarcity. DiffGeo combines a learned latent space model for automatic shape parameterization with a diffusion sampler to directly generate novel, geometry-valid, and controllable designs. We validate the approach on a series of case studies: i) a 2D airfoil generation benchmark, where DiffGeo’s latent diffusion model is compared against GAN- and VAE-based baselines in terms of sample quality, diversity, and constraint adherence under limited data; ii) integration into a surrogate-based optimization pipeline, where DiffGeo’s conditional sampling produces task-informed airfoil data that improve both surrogate modeling and optimization performance; and iii) extension to 3D turbomachinery blade prototyping, where DiffGeo generates realistic and high-performance blade geometries from a small set of reference designs. Throughout these investigations, DiffGeo achieves high-quality and diverse shape generation with at least an order of magnitude less data than alternatives, decouples geometry representation from design targets for flexible reuse, and seamlessly incorporates complex design constraints via energy-based conditioning. These capabilities demonstrate DiffGeo’s potential to enhance early-stage design by automating design space exploration—improving efficiency, expanding design diversity, and embedding engineering knowledge through controllable guidance.