Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields

arXiv:2607.20321 · physics.flu-dyn, cs.LG · Submitted 2026-07-22 · Read on arXiv

physics.flu-dyn, cs.LG

Submitted: 2026-07-22

Updated: 2026-10-26

Terminology

• Neural Surrogates — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Computational Fluid Dynamics (CFD) — 1× in this paper · explained in 2 episodes

Related papers

• Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
• A neural operator framework for data-driven discovery of stability and receptivity in physical systems
• Physics Foundation Models for Efficient Control of Fluid Flows
• Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
• Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
• A mass invariant in a compressible turbulent medium