Physically Interpretable Representation Learning with Gaussian Mixture Variational AutoEncoder (GM-VAE)
Fan, Tiffany, Cutforth, Murray, D'Elia, Marta, Cortiella, Alexandre, Doostan, Alireza, Darve, Eric
–arXiv.org Artificial Intelligence
Extracting compact, physically interpretable representations from high-dimensional scientific data is a persistent challenge due to the complex, nonlinear structures inherent in physical systems. We propose a Gaussian Mixture Variational Autoencoder (GM-VAE) framework designed to address this by integrating an Expectation-Maximization (EM)-inspired training scheme with a novel spectral interpretability metric. Unlike conventional VAEs that jointly optimize reconstruction and clustering (often leading to training instability), our method utilizes a block-coordinate descent strategy, alternating between expectation and maximization steps. This approach stabilizes training and naturally aligns latent clusters with distinct physical regimes. To objectively evaluate the learned representations, we introduce a quantitative metric based on graph-Laplacian smoothness, which measures the coherence of physical quantities across the latent manifold. We demonstrate the efficacy of this framework on datasets of increasing complexity: surface reaction ODEs, Navier-Stokes wake flows, and experimental laser-induced combustion Schlieren images. The results show that our GM-VAE yields smooth, physically consistent manifolds and accurate regime clustering, offering a robust data-driven tool for interpreting turbulent and reactive flow systems.
arXiv.org Artificial Intelligence
Dec-1-2025
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.14)
- North America > United States
- California > Santa Clara County
- Palo Alto (0.04)
- Colorado > Boulder County
- Boulder (0.04)
- Rhode Island > Providence County
- Providence (0.04)
- California > Santa Clara County
- Europe > United Kingdom
- Genre:
- Research Report > New Finding (0.66)
- Industry:
- Energy (1.00)
- Government > Regional Government (0.46)
- Technology: