3D Magnetic Field Reconstruction and Mapping with Physics-Informed Neural Networks
It provides a high-precision, physically consistent method for magnetic field mapping in inaccessible regions, addressing a key limitation of traditional spherical harmonic expansion for physics experiments.
This study proposes a Physics-Informed Neural Network (PINN) framework for 3D magnetic field reconstruction that integrates Maxwell's equations into the loss function, achieving a tenfold improvement in accuracy over existing PINN benchmarks (10^{-4} on simulated data) and sub-percent relative accuracy (10^{-3}) in experimental validation.
Accurate reconstruction of magnetic fields in inaccessible regions is vital for many high-precision experiments in physics. Traditional methods, such as spherical harmonic expansion, often suffer from truncation errors that limit their precision. This study proposes an advanced Physics-Informed Neural Network (PINN) framework for high-precision 3D magnetic field mapping. Unlike conventional data-driven models, the proposed PINN integrates Maxwell's equations directly into the loss function, enforcing divergence-free and curl-free conditions across the entire domain. A key innovation is the inclusion of explicit physics-residual losses at measurement locations, ensuring rigorous physical consistency beyond random collocation sampling. Validation using simulated data achieves a reconstruction accuracy of $10^{-4}$, a tenfold improvement over existing PINN benchmarks. Furthermore, experimental validation using a custom coil assembly demonstrates robust reconstruction with sub-percent relative accuracy, reaching the $10^{-3}$ level under ambient conditions. This AI-driven methodology provides a robust, high-precision solution for field monitoring and measurement in complex experimental environments where direct sensor placement is restricted.