Conditional Denoising Model as a Physical Surrogate Model
This addresses the problem of ensuring strict physical adherence in surrogate models for researchers in computational physics, offering a novel approach that implicitly regularizes for physical constraints without explicit training on governing equations.
The paper tackled the trade-off between accuracy and physical consistency in surrogate modeling for complex physical systems by introducing the Conditional Denoising Model (CDM), which learns the geometry of the physical manifold through a denoising objective, achieving higher parameter and data efficiency than physics-consistent baselines on a low-temperature plasma benchmark.
Surrogate modeling for complex physical systems typically faces a trade-off between data-fitting accuracy and physical consistency. Physics-consistent approaches typically treat physical laws as soft constraints within the loss function, a strategy that frequently fails to guarantee strict adherence to the governing equations, or rely on post-processing corrections that do not intrinsically learn the underlying solution geometry. To address these limitations, we introduce the {Conditional Denoising Model (CDM)}, a generative model designed to learn the geometry of the physical manifold itself. By training the network to restore clean states from noisy ones, the model learns a vector field that points continuously towards the valid solution subspace. We introduce a time-independent formulation that transforms inference into a deterministic fixed-point iteration, effectively projecting noisy approximations onto the equilibrium manifold. Validated on a low-temperature plasma physics and chemistry benchmark, the CDM achieves higher parameter and data efficiency than physics-consistent baselines. Crucially, we demonstrate that the denoising objective acts as a powerful implicit regularizer: despite never seeing the governing equations during training, the model adheres to physical constraints more strictly than baselines trained with explicit physics losses.