Conditional Denoising Model as a Physical Surrogate Model

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Afonso, José, Viegas, Pedro, Ventura, Rodrigo, Guerra, Vasco
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917230410727424
author Afonso, José
Viegas, Pedro
Ventura, Rodrigo
Guerra, Vasco
author_facet Afonso, José
Viegas, Pedro
Ventura, Rodrigo
Guerra, Vasco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21021
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conditional Denoising Model as a Physical Surrogate Model
Afonso, José
Viegas, Pedro
Ventura, Rodrigo
Guerra, Vasco
Machine Learning
Artificial Intelligence
Plasma Physics
68T07
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.
title Conditional Denoising Model as a Physical Surrogate Model
topic Machine Learning
Artificial Intelligence
Plasma Physics
68T07
url https://arxiv.org/abs/2601.21021