Towards a Foundation Model for Partial Differential Equations Across Physics Domains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Soares, Eduardo, Brazil, Emilio Vital, Shirasuna, Victor, de Carvalho, Breno W. S. R., Malossi, Cristiano
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915640293457920
author Soares, Eduardo
Brazil, Emilio Vital
Shirasuna, Victor
de Carvalho, Breno W. S. R.
Malossi, Cristiano
author_facet Soares, Eduardo
Brazil, Emilio Vital
Shirasuna, Victor
de Carvalho, Breno W. S. R.
Malossi, Cristiano
contents We present PDE-FM, a modular foundation model for physics-informed machine learning that unifies spatial, spectral, and temporal reasoning across heterogeneous partial differential equation (PDE) systems. PDE-FM combines spatial-spectral tokenization, physics-aware conditioning, and a Mamba-based state-space backbone with an operator-theoretic decoder, enabling scalable and data-efficient modeling of complex physical dynamics. In contrast to task-specific neural operators, PDE-FM is pretrained once on diverse PDE datasets and can be transferred to new physical regimes without architectural or data-specific modifications. Evaluated on twelve 2D and 3D datasets from The Well benchmark - spanning hydrodynamic, radiative, elastic, and astrophysical phenomena - PDE-FM achieves state-of-the-art accuracy in six domains, reducing mean VRMSE by 46% relative to prior operator-learning baselines. The model demonstrates robust cross-physics generalization, excelling in turbulent and radiative systems while maintaining strong performance in linear and steady-state regimes. These results suggest that large-scale pretraining across diverse physical processes can yield transferable representations of dynamics, marking a step toward unified, foundation-level surrogates for multi-physics simulation and scientific discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards a Foundation Model for Partial Differential Equations Across Physics Domains
Soares, Eduardo
Brazil, Emilio Vital
Shirasuna, Victor
de Carvalho, Breno W. S. R.
Malossi, Cristiano
Machine Learning
Artificial Intelligence
We present PDE-FM, a modular foundation model for physics-informed machine learning that unifies spatial, spectral, and temporal reasoning across heterogeneous partial differential equation (PDE) systems. PDE-FM combines spatial-spectral tokenization, physics-aware conditioning, and a Mamba-based state-space backbone with an operator-theoretic decoder, enabling scalable and data-efficient modeling of complex physical dynamics. In contrast to task-specific neural operators, PDE-FM is pretrained once on diverse PDE datasets and can be transferred to new physical regimes without architectural or data-specific modifications. Evaluated on twelve 2D and 3D datasets from The Well benchmark - spanning hydrodynamic, radiative, elastic, and astrophysical phenomena - PDE-FM achieves state-of-the-art accuracy in six domains, reducing mean VRMSE by 46% relative to prior operator-learning baselines. The model demonstrates robust cross-physics generalization, excelling in turbulent and radiative systems while maintaining strong performance in linear and steady-state regimes. These results suggest that large-scale pretraining across diverse physical processes can yield transferable representations of dynamics, marking a step toward unified, foundation-level surrogates for multi-physics simulation and scientific discovery.
title Towards a Foundation Model for Partial Differential Equations Across Physics Domains
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.21861