analiza aiqbench
This research introduces a physics-constrained neural operator framework capable of reconstructing full-field states and identifying unknown parameters in coupled systems using only sparse observations of a single field. By integrating cross-attention encoders with Fourier neural operators, the method effectively handles global spatial dependencies while jointly optimizing network weights against governing equation residuals. The approach demonstrates robust performance across diverse fluid dynamics and magnetohydrodynamics benchmarks, offering a promising pathway for data-efficient modeling in complex physical systems.
Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
arXiv:2610.05723v1 Announce Type: new 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.
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.
Machine Learning (cs.LG); Numerical Analysis (math.NA)
arXiv:2610.05723 [cs.LG]
(or arXiv:2610.05723v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.05723 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 266 cuvinte
Subiecte conexe
Researchers Learn Quantum System with Single Qubit Readout
Quantum Zeitgeist · 2 oct. 2026
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · 8 oct. 2026
New Protocol Shares Parameters Hidden in Strong Coupling
Quantum Zeitgeist · 14 aug. 2026
Virtual Sensing to Enable Real-Time Monitoring of Inaccessible Locations & Unmeasurable Parameters
arXiv · 16 iun. 2026