Machine learning for improved current-density reconstruction from two-dimensional vector magnetic images
Authors:
- Niko R. ReedNRNiko R. Reed
- Danyal BhuttoDBDanyal Bhutto
- Declan M. DalyDDDeclan M. Daly
- Sean M. OliverSOSean M. Oliver
- Jiashen TangJTJiashen Tang
- Kevin S. OlssonKOKevin S. Olsson
- Nicholas LangellierNLNicholas Langellier
- Mark J.H. KuMKMark J.H. Ku
- Matthew S. RosenMRMatthew S. Rosen
- Ronald L. WalsworthRWRonald L. Walsworth
Open Access
- 17 March 2025
- journal article
- Published by American Physical Society (APS) in Physical Review Applied
- Vol. 23 (3)
Abstract
The reconstruction of electrical current densities from magnetic field measurements is an important technique with applications in materials science, circuit design, quality control, plasma physics, and biology. Analytic reconstruction methods exist for planar currents, but break down in the presence of high-spatial-frequency noise or large standoff distance, restricting the types of systems that can be studied. Here, we demonstrate the use of a deep convolutional neural network for current density reconstruction from two-dimensional images of vector magnetic fields acquired by a quantum diamond microscope . Trained network performance significantly exceeds analytic reconstruction for data with high noise or large standoff distances. This machine learning technique can perform quality inversions on lower-signal-to-noise-ratio data, significantly reducing the data collection time and permitting reconstructions of weaker and three-dimensional current sources.Keywords
All Related Versions
Funding Information
- National Science Foundation (DGE 2236417, DGE 1840990, H9823022C0029)
- Air Force Office of Scientific Research (FA9550-22-1-0312)
- University of Maryland
- Intelligence Community Postdoctoral Research Fellowship Program
- Oak Ridge Institute for Science and Education
- U.S. Department of Energy
- Office of the Director of National Intelligence
- Army Research Laboratory
- IC Postdoctoral Fellowship (STEMWD00851)
This publication has 55 references indexed in Scilit:
- Helical Luttinger Liquid on the Edge of a Two-Dimensional Topological AntiferromagnetNano Letters, 2022
- Current Mapping of Amorphous LaAlO3/SrTiO3 near the Metal–Insulator TransitionACS Applied Electronic Materials, 2022
- Non-invasive current density imaging of lithium-ion batteriesJournal of Power Sources, 2022
- Direct measurement of current distribution in lithium-ion cells by magnetic field imagingJournal of Power Sources, 2021
- Evaluation of the Quality of Solder Joints within Silicon Solar Modules Using Magnetic Field ImagingPhysica Status Solidi (a), 2020
- Image reconstruction by domain-transform manifold learningNature, 2018
- Nitrogen-Vacancy centers in diamond for current imaging at the redistributive layer level of Integrated CircuitsMicroelectronics Reliability, 2015
- Image Quality Assessment Using the SSIM and the Just Noticeable Difference Paradigm2013
- Magnetic microscopy for 3D devices: Defect localization with high resolution and long working distance on complex system in packageMicroelectronics Reliability, 2009
- Noninvasive biomagnetic imaging in coronary artery disease based on individual current density maps of the heartInternational Journal of Cardiology, 1998