# CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs

DevFeed: [CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs](<https://devfeed.tech/articles/coupledflow-one-step-neural-operators-for-coupled-multi-physics-pdes-125282.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10945>)

Author: Trong Khiem Tran, Minh Long Bui, Phi Le Nguyen, Mrinal Sen, Sanjay Srinivasan, Trong Nghia Hoang, Jana Doppa

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Deep neural networks](<https://devfeed.tech/topics/deep-neural-networks.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [also](<https://devfeed.tech/tags/also.md>), [art](<https://devfeed.tech/tags/art.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [capture](<https://devfeed.tech/tags/capture.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [develop](<https://devfeed.tech/tags/develop.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [neural](<https://devfeed.tech/tags/neural.md>), [one](<https://devfeed.tech/tags/one.md>), [operators](<https://devfeed.tech/tags/operators.md>), [physics](<https://devfeed.tech/tags/physics.md>)

## AI overview

COUPLED FLOW targets coupled multi-physics PDEs with one-step predictions by learning process-specific mean velocity fields conditioned on the full system state. Its structure-constrained flow matching uses a mean-flow consistency identity to define the training loss and posterior multi-output Gaussian processes to sample correlated conditional interpolants, which capture richer cross-process correlations than endpoint-conditioned linear interpolants. The paper also bounds the Wasserstein-2 distance between predicted and oracle solution distributions using the matching loss and learned-flow smoothness. The abstract reports that experiments on diverse coupled PDE benchmarks outperform existing neural operators and generative PDE solvers; it provides no benchmark-specific results in this excerpt.

## Source excerpt

arXiv:2611.10945v1 Announce Type: new Abstract: This paper introduces COUPLED FLOW, a new neural operator learning framework for multi-physics PDE systems that captures the co-evolution of multiple physical processes by modeling their cross-process interactions. Unlike existing neural operator methods that primarily target single-physics settings, COUPLED FLOW employs a novel structure-constrained flow matching algorithm to learn process- specific mean velocity fields conditioned on the full multi-physics state. This enables fast and accurate one-step prediction of coupled PDE systems that would otherwise require expensive numerical simulations. A key challenge in training COUPLED FLOW however lies in sampling structure-constrained conditional flow interpolants that capture cross-process correlations and serve as training examples for flow matching. To address this challenge, we derive a multi-physics mean-flow consistency identity that characterizes cross-process interactions and defines the structure-constrained mean-flow matching loss. To provide informative training samples for flow matching with this loss, we develop a principled method for sampling correlated conditional interpolants based on posterior multi-output Gaus- sian processes, which capture richer cross-process correlations than the commonly used endpoint-conditioned linear interpolants. We also establish a theoretical re- sult showing that the Wasserstein-2 distance between the predicted and oracle PDE solution distributions is upper-bounded in terms of the structure-constrained flow matching loss and the smoothness of the learned flow. Experiments across diverse coupled PDE benchmarks demonstrate that COUPLED FLOW consistently outperforms existing state-of-the-art neural operators and generative PDE solvers.