XRePIT: A deep learning-computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations

TL;DR

XRePIT is an automated hybrid framework combining neural surrogates and OpenFOAM for efficient, stable, and scalable 3D unsteady fluid simulations, outperforming standalone models in speed and accuracy.

Contribution

It introduces an open-source, residual-guided coupling framework that automates the transition between neural surrogates and traditional solvers, enhancing stability and scalability.

Findings

Achieves up to 2.91x faster simulations compared to traditional methods.

Maintains relative L2 errors within 1E-03 during long-term simulations.

Demonstrates architecture-agnostic stabilizing effect of residual guardrail.

Abstract

Autoregressive neural surrogates offer computational acceleration for fluid dynamics but inherently suffer from error accumulation and non-physical drift during long-term rollouts. Although hybrid strategies combining surrogate models and physics-based solvers have been proposed, they are limited to manual implementations for low-dimensional benchmarks. In this study, we propose an OpenFOAM-based hybrid framework, XRePIT (eXtensible Residual-based Physics-nformed Transfer learning), characterized by its fastness, robustness, and scalability. Unlike prior manual implementations (e.g., RePIT), XRePIT integrates a fully automated open-source workflow that manages the state transition between a neural surrogate and a traditional numerical solver (OpenFOAM) based on a monitored residual threshold. Using 3D buoyancy-driven flow as a testbed, we demonstrate that this residual-guided coupling enables stable long-term simulation-ell beyond the stability horizon of standalone surrogates. Our results indicate that the hybrid loop achieves up to 2.91x wall-clock acceleration while maintaining relative L2 errors within O(1E-03) Furthermore, we benchmark the framework's extensibility by introducing a finite-volume-based Fourier neural operator (FVFNO), confirming that the stabilizing effect of the residual guardrail is agnostic to the underlying neural architecture. This study provides a deployable methodology for fast, robust, and automated hybrid simulation in 3D unsteady flow.