Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
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.
Related
- A Two-Stage Hybrid Framework for Inferring Air Trips from Mobile Location-based Service (LBS) Data under Incomplete Airport Sightings
- Bounding the Risk Difference Bias Given Incomplete Parameters for Externally Adjusting Uncontrolled Confounding
- P-stationary structural equation modeling: Causal effect identification under temporally incomplete observations
- UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations
- Maximum likelihood, neural networks and posterior mean for inferring fractional Brownian motion parameters
BibTeX
@misc{wei2026inferring,
title = {{Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators}},
author = {Shilun Wei and Xiaoqiang Sun and Wei Li and Kejun Tang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05723},
eprint = {2610.05723},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05723},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
AU - Shilun Wei
AU - Xiaoqiang Sun
AU - Wei Li
AU - Kejun Tang
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.05723
UR - https://arxiv.org/abs/2610.05723
AB - 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.
ER -