Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators

2026-10-05

AI Summary

This study addresses the challenge of inferring the complete physical state and identifying unknown parameters of coupled systems from incomplete observations of a single physical field. To this end, it proposes a physics-informed machine learning framework that employs a cross-attention encoder to propagate sparse observations onto regular grids, combined with a Fourier Neural Operator (FNO) decoder to capture global dependencies. The network weights and physical parameters are jointly optimized through a physics-constrained loss function. Evaluated on benchmark problems including two- and three-dimensional lid-driven cavity flows, flow past a cylinder, and non-ideal magnetohydrodynamics, the proposed approach achieves simultaneous multi-physics field reconstruction and accurate joint inversion of unknown parameters.

Abstract

Given incomplete measurements of a single physical field in a coupled system with unknown parameters, can we infer its full physical state and identify the underlying parameters? This problem is challenging because multiple coupled fields must be reconstructed simultaneously from limited observations of only one, while the system parameters are unknown. In this work, we propose a machine learning framework for full-field reconstruction and parameter identification of unknown physical systems from sparse observations of a single physical field. Specifically, the cross-attention encoder propagates sparse sensor observations onto a regular grid to construct a sensor-conditioned latent representation, while a Fourier neural operator (FNO) decoder captures global spatial dependencies to reconstruct all coupled physical fields. The network parameters and unknown physical parameters are jointly optimized by minimizing observation losses, governing equation residuals, and boundary/initial condition constraints. The proposed approach is validated on two- and three-dimensional lid-driven cavity flows, a two-dimensional cylinder wake, and a two-dimensional non-ideal magnetohydrodynamics problem, demonstrating the recovery performance of unobserved fields and physical parameters from incomplete observations.

Problem

• coupled systems
• incomplete observations
• full-field reconstruction
• parameter identification
• physics-constrained

Innovation

• Physics-constrained neural operators
• Cross-attention encoder
• Fourier neural operator
• Parameter identification
• Full-field reconstruction