PhysFormer: A Physics-Embedded Generative Model for Physically Self-Consistent Spectral Synthesis

TL;DR

PhysFormer is a novel generative model that ensures physical consistency in spectral synthesis by embedding physical laws directly into its architecture, improving stability and fidelity in complex, high-dimensional systems.

Contribution

It introduces a physics-embedded generative framework that learns physical quantities directly from data without known physical fields, enhancing spectral synthesis and inversion stability.

Findings

Improves spectral fidelity in high-dimensional tasks

Enhances inversion stability under noisy conditions

Ensures physical consistency through embedded physical processes

Abstract

In scientific and engineering domains, modeling high-dimensional complex systems governed by partial differential equations (PDEs) remains challenging in terms of physical consistency and numerical stability. However, existing approaches, such as physics-informed neural networks (PINNs), typically rely on known physical fields or coefficients and enforce physical constraints via external loss functions, which can lead to training instability and make it difficult to handle high-dimensional or unobservable scenarios. To this end, we propose PhysFormer, a generative modeling framework that is self-consistent at both the data and physical levels. PhysFormer leverages a low-dimensional, physically interpretable latent space to learn key physical quantities directly from data without requiring known high-dimensional physical field parameters, and embeds the physical process of radiative flux generation within the network to ensure the physical consistency of the generated spectra. In high-dimensional, degenerate inversion tasks, PhysFormer constrains generation within physical limits and enhances spectral fidelity and inversion stability under varying signal-to-noise ratios (SNRs). More broadly, this approach shifts the physical processes from external loss functions into the generative mechanism itself, providing a physically consistent generative modeling paradigm for complex systems involving unknown or unobservable physical quantities.