Regime-Aware Coupled Orchestration of Neural Operator Specialists for Multiphysics Dynamics
Abstract
Real-world physics often unfolds over a variety of characteristic lengths and time scales. These non-uniformities are among the main reasons numerical simulations remain expensive when used predictively on practical systems: the same computational domain can contain smooth transport, vortical structures, thin interfaces, reaction fronts, and rapidly relaxing regions. Neural operators are attractive surrogates for such problems. However, a single architecture is still expected to represent all these local behaviours with a single set of weights and a single inductive bias. In this work, we introduce the regime-aware coupled neural orchestrator (RCNO), a framework that learns to distribute and connect a library of local operator specialists in space and time. For every patch, an orchestrator builds a causal query from the current fields, neighbouring halo values, local regime features, patch identity, activity level, and case parameters. The nine expert embeddings exchange two rounds of query-conditioned message passing before an edge-biased cross-attention stage produces a dispatch distribution that can be evaluated sparsely. Local predictions are assembled into a global field and projected onto system-specific physical constraints. A seam-aware extension additionally learns residual corrections across internal patch interfaces. We apply the same orchestration architecture to two qualitatively different systems: reacting flow and Cahn-Hilliard-Navier-Stokes (CHNS) dynamics. The results show that useful operator specialisation exists across local regimes, that the advantage of conditional composition increases as the spatial decomposition becomes finer, and, on reacting flow, that explicitly treating patch interfaces improves continuity, PDE consistency, and rollout accuracy.
Related
- A multiphysics-coupled DeepONet framework for predicting sodium dendrite growth in wide-temperature sodium-ion capacitors
- Temperature-Dependent Multiphysics Modeling of Additive Friction Stir Deposition Using Multi-Task Coupled Physics-Informed Neural Networks
- Comprehensive Acoustic Characterization of a Broadband Lateral MEMS Ultrasonic Transducer by Near-Field Acoustic Holography and Coupled Multiphysics Simulation
- A projection operator approach for ultracold bosons coupled to a cavity
- An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling
BibTeX
@misc{guida2026regimeaware,
title = {{Regime-Aware Coupled Orchestration of Neural Operator Specialists for Multiphysics Dynamics}},
author = {Paolo Guida and Vijayamanikandan Vijayarangan and Hong G. Im and William L. Roberts},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.22378},
eprint = {2610.22378},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.22378},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Regime-Aware Coupled Orchestration of Neural Operator Specialists for Multiphysics Dynamics
AU - Paolo Guida
AU - Vijayamanikandan Vijayarangan
AU - Hong G. Im
AU - William L. Roberts
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.22378
UR - https://arxiv.org/abs/2610.22378
AB - Real-world physics often unfolds over a variety of characteristic lengths and time scales. These non-uniformities are among the main reasons numerical simulations remain expensive when used predictively on practical systems: the same computational domain can contain smooth transport, vortical structures, thin interfaces, reaction fronts, and rapidly relaxing regions. Neural operators are attractive surrogates for such problems. However, a single architecture is still expected to represent all these local behaviours with a single set of weights and a single inductive bias. In this work, we introduce the regime-aware coupled neural orchestrator (RCNO), a framework that learns to distribute and connect a library of local operator specialists in space and time. For every patch, an orchestrator builds a causal query from the current fields, neighbouring halo values, local regime features, patch identity, activity level, and case parameters. The nine expert embeddings exchange two rounds of query-conditioned message passing before an edge-biased cross-attention stage produces a dispatch distribution that can be evaluated sparsely. Local predictions are assembled into a global field and projected onto system-specific physical constraints. A seam-aware extension additionally learns residual corrections across internal patch interfaces. We apply the same orchestration architecture to two qualitatively different systems: reacting flow and Cahn-Hilliard-Navier-Stokes (CHNS) dynamics. The results show that useful operator specialisation exists across local regimes, that the advantage of conditional composition increases as the spatial decomposition becomes finer, and, on reacting flow, that explicitly treating patch interfaces improves continuity, PDE consistency, and rollout accuracy.
ER -