Machine learning for improved current-density reconstruction from two-dimensional vector magnetic images
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.
Authors
- Ronald L. Walsworth (ORCID: https://orcid.org/0000-0003-0311-4751)
- Danyal Bhutto (ORCID: https://orcid.org/0000-0002-7388-1852)
- Kevin Olsson (ORCID: https://orcid.org/0000-0002-4437-7067)
- Sean M. Oliver (ORCID: https://orcid.org/0000-0003-3848-5632)
- Nicholas Langellier (ORCID: https://orcid.org/0000-0003-2107-3308)
- Mark Ku (ORCID: https://orcid.org/0000-0003-3144-3069)
- Nicholas N. Reed
- Jiashen Tang (ORCID: https://orcid.org/0000-0002-2763-6194)
- Matthew J. Turner
- Matthew S. Rosen (ORCID: https://orcid.org/0000-0002-7194-002X)
- D. Daly
Institutions
- Boston University (US)
- Harvard University (US)
- Lemuel Shattuck Hospital (US)
- Harvard University Press (US)
- Massachusetts General Hospital (US)
- Athinoula A. Martinos Center for Biomedical Imaging (US)
- Joint Quantum Institute (US)
- Mitre (United States) (US)
- University of Maryland, College Park (US)
- University of Delaware (US)
Publication Details
- Journal
- Physical Review Applied
- Published
- 2025-03-17
- DOI
- https://doi.org/10.1103/physrevapplied.23.034035
- Citations
- 6
- Primary Topic
- Electrical and Bioimpedance Tomography
- Type
- article
- Field-Weighted Citation Impact
- 4.38
Funders
- National Science Foundation
- U.S. Department of Energy
- University of Maryland
- Office of the Director of National Intelligence
- Oak Ridge Institute for Science and Education
- U.S. Air Force
- Intelligence Community Postdoctoral Research Fellowship Program
- Air Force Office of Scientific Research
- Army Research Laboratory