Conditional Denoising Model as a Physical Surrogate Model

TL;DR

This paper introduces the Conditional Denoising Model, a generative approach that learns the physical solution manifold for complex systems, achieving high efficiency and strict physical adherence without explicit physics constraints.

Contribution

The paper presents a novel generative model that learns the physical manifold via denoising, enabling strict physical adherence and improved efficiency over traditional physics-based methods.

Findings

Higher parameter and data efficiency than physics-consistent baselines

Denoising objective acts as an implicit regularizer

Model adheres to physical constraints more strictly without explicit physics losses

Abstract

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.