Physics-Embedded Machine Learning for Electromagnetic Data Imaging: Examining three types of data-driven imaging methods

Electromagnetic (EM) imaging is widely applied in sensing for security, biomedicine, geophysics, and various industries. It is an ill-posed inverse problem whose solution is usually computationally expensive. Machine learning (ML) techniques and especially deep learning (DL) show potential in fast and accurate imaging. However, the high performance of purely data-driven approaches relies on constructing a training set that is statistically consistent with practical scenarios, which is often not possible in EM-imaging tasks. Consequently, generalizability becomes a major concern. On the other hand, physical principles underlie EM phenomena and provide baselines for current imaging techniques. To benefit from prior knowledge in big data and the theoretical constraint of physical laws, physics-embedded ML methods for EM imaging have become the focus of a large body of recent work.

Automated summary

Electromagnetic (EM) imaging is widely used in various fields, but it is an ill-posed inverse problem. Machine learning techniques, particularly deep learning, have shown potential in fast and accurate imaging. However, the challenge lies in constructing a training set that accurately represents practical scenarios. To overcome this, recent research has focused on physics-embedded ML methods for EM imaging, which combine the benefits of big data and the theoretical constraints of physical laws.