Denoising diffusion and latent diffusion models for physics field simulations
Aerospace Science and Technology · 2026-09 · 176 · 112571
DOI: 10.1016/j.ast.2026.112571 ↗Kurz gefasst
Fachartikel in der Zeitschrift Aerospace Science and Technology, 2026-09. Verfasst von Yuan Jia und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Technische Universität München, Research Grants Council, University Grants Committee.
Abstract (Originalsprache)
Accurate prediction of physical fields is critical in various engineering applications, including thermal management in electronic systems, airfoil shape optimization in aerospace, and flow field control in hypersonic vehicles. This study employs the Denoising Diffusion Probabilistic Models (DDPMs) for predicting the temperature field caused by the thermal diffusion, and the flow fields spanning from incompressible to hypersonic regimes. A conditional DDPM framework is first validated with a steady-state thermal diffusion problem by predicting the temperature distribution around a plate with holes. Strong agreement with ground truth data is shown with an average error of approximately 0.013 for plates with a central circular hole. The model also delivers high accuracy in critical regions, such as near the inner circular or square holes. Its performance is further evaluated on incompressible flow around an airfoil and hypersonic flow over a compression ramp, confirming robust predictive capability across diverse flow conditions. Additionally, a latent-space implementation of DDPM is introduced, which employs an Autoencoder (AE) for dimensionality reduction and reconstruction of the physical data. The resulting Latent Diffusion Model (LDM) maintains reconstruction quality comparable to the standard DDPM while substantially reducing the computational cost of the diffusion training process. When applied to hypersonic flow over a compression ramp in the original parameter space, LDM predictions align well with ground truth, achieving a deviation of only 4.28% in separation length estimation. This work confirms the high predictive accuracy of the DDPM framework and highlights the efficiency gains from performing diffusion in a learned latent space. The findings establish an efficient framework for high fidelity generative modeling of complex thermal/flow fields.
Förderung
- Technische Universität München
- Research Grants Council, University Grants Committee
Zitieren
APA
Jia, Y., Zhang, C., Ma, H., Zhang, Q., Liu, K., & Wen, C. (2026). Denoising diffusion and latent diffusion models for physics field simulations. Aerospace Science and Technology, 176, 112571. https://doi.org/10.1016/j.ast.2026.112571
Vancouver
Jia Y, Zhang C, Ma H, Zhang Q, Liu K, Wen C. Denoising diffusion and latent diffusion models for physics field simulations. Aerospace Science and Technology. 2026;176:112571. doi:10.1016/j.ast.2026.112571
BibTeX
@article{Jia2026,
author = {Jia, Yuan and Zhang, Chi and Ma, Hao and Zhang, Qiao and Liu, Kai and Wen, Chih-Yung},
title = {Denoising diffusion and latent diffusion models for physics field simulations},
journal = {Aerospace Science and Technology},
year = {2026},
volume = {176},
pages = {112571},
doi = {10.1016/j.ast.2026.112571}
}
EUVIMED