Machine learning based localization and classification with atomic magnetometers

TL;DR

This paper demonstrates how machine learning enhances atomic magnetometer imaging by accurately localizing and classifying objects, surpassing traditional resolution limits and achieving high classification accuracy, with broad applications in biomedicine and security.

Contribution

It introduces a machine learning approach that extracts hidden information from atomic magnetometer images, improving localization and classification without solving inverse problems.

Findings

Localization 2.6 times better than system resolution

Classification accuracy up to 97%

Extension to diffusive low-frequency electrodynamics

Abstract

We demonstrate identification of position, material, orientation and shape of objects imaged by an $^{85}$Rb atomic magnetometer performing electromagnetic induction imaging supported by machine learning. Machine learning maximizes the information extracted from the images created by the magnetometer, demonstrating the use of hidden data. Localization 2.6 times better than the spatial resolution of the imaging system and successful classification up to 97$\%$ are obtained. This circumvents the need of solving the inverse problem, and demonstrates the extension of machine learning to diffusive systems such as low-frequency electrodynamics in media. Automated collection of task-relevant information from quantum-based electromagnetic imaging will have a relevant impact from biomedicine to security.