Physics Aware Neural Networks: Denoising for Magnetic Navigation

• URL: http://arxiv.org/abs/2602.13690v1
• Date: Sat, 14 Feb 2026 09:23:57 GMT
• Title: Physics Aware Neural Networks: Denoising for Magnetic Navigation
• Authors: Aritra Das, Yashas Shende, Muskaan Chugh, Reva Laxmi Chauhan, Arghya Pathak, Debayan Gupta,
• Abstract summary: Airborne systems face a key challenge in extracting geomagnetic field data: the aircraft itself induces magnetic noise.<n>We propose a framework based on two physics-based constraints: divergence-free vector field and E(3)equivariance.<n>Experiments show that embedding these constraints significantly improves predictive accuracy and physical plausibility, outperforming classical deep learning approaches.
• Score: 3.624059602945058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Magnetic-anomaly navigation, leveraging small-scale variations in the Earth's magnetic field, is a promising alternative when GPS is unavailable or compromised. Airborne systems face a key challenge in extracting geomagnetic field data: the aircraft itself induces magnetic noise. Although the classical Tolles-Lawson model addresses this, it inadequately handles stochastically corrupted magnetic data required for navigation. To address stochastic noise, we propose a framework based on two physics-based constraints: divergence-free vector field and E(3)-equivariance. These ensure the learned magnetic field obeys Maxwell's equations and that outputs transform correctly with sensor position/orientation. The divergence-free constraint is implemented by training a neural network to output a vector potential $A$, with the magnetic field defined as its curl. For E(3)-equivariance, we use tensor products of geometric tensors representable via spherical harmonics with known rotational transformations. Enforcing physical consistency and restricting the admissible function space acts as an implicit regularizer that improves spatio-temporal performance. We present ablation studies evaluating each constraint alone and jointly across CNNs, MLPs, Liquid Time Constant models, and Contiformers. Continuous-time dynamics and long-term memory are critical for modelling magnetic time series; the Contiformer architecture, which provides both, outperforms state-of-the-art methods. To mitigate data scarcity, we generate synthetic datasets using the World Magnetic Model (WMM) with time-series conditional GANs, producing realistic, temporally consistent magnetic sequences across varied trajectories and environments. Experiments show that embedding these constraints significantly improves predictive accuracy and physical plausibility, outperforming classical and unconstrained deep learning approaches.

Related papers

• Gradient Networks for Universal Magnetic Modeling of Synchronous Machines [39.146761527401424]
  This paper presents a physics-informed neural network approach for dynamic modeling of saturable synchronous machines.<n>We introduce an architecture that incorporates gradient networks directly into the fundamental machine equations.<n>We validate the proposed approach using measured and finite-element method (FEM) datasets from a 5.6-kW permanent-magnet synchronous machine.
  arXiv  Detail & Related papers  (2026-02-16T17:28:42Z)
• PhyG-MoE: A Physics-Guided Mixture-of-Experts Framework for Energy-Efficient GNSS Interference Recognition [49.955269674859004]
  This paper introduces PhyG-MoE (Physics-Guided Mixture-of-Experts), a framework designed to align model capacity with signal complexity.<n>Unlike static architectures, the proposed system employs a spectrum-based gating mechanism that routes signals based on their spectral feature entanglement.<n>A high-capacity TransNeXt expert is activated on-demand to disentangle complex features in saturated scenarios, while lightweight experts handle fundamental signals to minimize latency.
  arXiv  Detail & Related papers  (2026-01-19T07:57:52Z)
• Optimal and efficient inference tools for field tracking with precessing spins [35.18016233072556]
  Spin-precession magnetometer (SPM) observes electron, nucleus, color center, or muon spins as they precess in response to their local magnetic field.<n>We show that it is sufficient to accurately track fluctuating and unknown transient signals.<n>Our methods can be easily adapted to other types of sensors undergoing nonlinear dissipative dynamics.
  arXiv  Detail & Related papers  (2025-10-13T19:44:33Z)
• Physics-informed Attention-enhanced Fourier Neural Operator for Solar Magnetic Field Extrapolations [24.60472525182772]
  We propose Physics-informed Attention-enhanced Neural Operator (PIANO) to solve the Force-Free Field (NLFFF) problem in solar physics.<n>Unlike conventional approaches that rely on iterative numerical methods, our proposed PIANO directly learns the 3D magnetic field structure from 2D boundary conditions.<n> Experimental results on the ISEE NLFFF dataset show that our PIANO not only outperforms state-of-the-art neural operators in terms of accuracy but also shows strong consistency with the physical characteristics of NLFFF data.
  arXiv  Detail & Related papers  (2025-10-06T20:24:22Z)
• Global-local Fourier Neural Operator for Accelerating Coronal Magnetic Field Model [17.256941005824576]
  We propose a global-local Fourier Neural Operator (GL-FNO) that contains two branches of FNO. The performance of the GLFNO is compared with state-of-the-art deep learning methods, including FNO, U-NO, U-FNO, Vision Transformer, CNN-RNN, and CNN-LSTM. The results demonstrate that GL-FNO not only accelerates the MHD simulation (a few seconds for prediction, more than times 20,000 speed up) but also provides reliable prediction capabilities, thus greatly contributing to the understanding of space weather dynamics.
  arXiv  Detail & Related papers  (2024-05-21T13:04:53Z)
• Equivariant Graph Neural Operator for Modeling 3D Dynamics [148.98826858078556]
  We propose Equivariant Graph Neural Operator (EGNO) to directly models dynamics as trajectories instead of just next-step prediction. EGNO explicitly learns the temporal evolution of 3D dynamics where we formulate the dynamics as a function over time and learn neural operators to approximate it. Comprehensive experiments in multiple domains, including particle simulations, human motion capture, and molecular dynamics, demonstrate the significantly superior performance of EGNO against existing methods.
  arXiv  Detail & Related papers  (2024-01-19T21:50:32Z)
• Self-Supervised Knowledge-Driven Deep Learning for 3D Magnetic Inversion [6.001304967469112]
  The proposed self-supervised knowledge-driven 3D magnetic inversion method learns on the target field data by a closed loop of the inversion and forward models. There is a knowledge-driven module in the proposed inversion model, which makes the deep learning method more explicable. The experimental results demonstrate that the proposed method is a reliable magnetic inversion method with outstanding performance.
  arXiv  Detail & Related papers  (2023-08-23T15:31:38Z)
• Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere [53.63505583883769]
  We introduce Spherical FNOs (SFNOs) for learning operators on spherical geometries. SFNOs have important implications for machine learning-based simulation of climate dynamics.
  arXiv  Detail & Related papers  (2023-06-06T16:27:17Z)
• Rotating Majorana Zero Modes in a disk geometry [75.34254292381189]
  We study the manipulation of Majorana zero modes in a thin disk made from a $p$-wave superconductor. We analyze the second-order topological corner modes that arise when an in-plane magnetic field is applied. We show that oscillations persist even in the adiabatic phase because of a frequency independent coupling between zero modes and excited states.
  arXiv  Detail & Related papers  (2021-09-08T11:18:50Z)
• Simultaneous boundary shape estimation and velocity field de-noising in Magnetic Resonance Velocimetry using Physics-informed Neural Networks [70.7321040534471]
  Magnetic resonance velocimetry (MRV) is a non-invasive technique widely used in medicine and engineering to measure the velocity field of a fluid. Previous studies have required the shape of the boundary (for example, a blood vessel) to be known a priori. We present a physics-informed neural network that instead uses the noisy MRV data alone to infer the most likely boundary shape and de-noised velocity field.
  arXiv  Detail & Related papers  (2021-07-16T12:56:09Z)
• Noisy atomic magnetometry in real time [0.0]
  Continuously monitored atomic spin-ensembles allow, in principle, for real-time sensing of external magnetic fields. We study how conclusions based on Kalman filtering methods change when inevitable imperfections are taken into account. We prove that even an infinitesimal amount of noise disallows the error to be arbitrarily diminished.
  arXiv  Detail & Related papers  (2021-03-22T17:28:40Z)
• Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations [79.71184760864507]
  This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA) In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field. We show that the new method class has characteristics not found in previous alignment methods.
  arXiv  Detail & Related papers  (2020-09-28T15:05:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.