Deep learning estimation of complex reverberant wave fields by a programmable metasurface

TL;DR

This paper presents a deep learning method combined with a programmable metasurface to shape and control electromagnetic wave fields in complex, reverberant environments, enabling wavefront reconstruction even without direct line of sight.

Contribution

It introduces a novel approach integrating deep learning with programmable metasurfaces for wave control in complex environments, especially where traditional methods struggle.

Findings

Accurately reconstructed wavefronts in chaotic microwave cavities.

Determined metasurface configurations for desired wave properties.

Effective control with metasurfaces covering only 1.5% of the cavity surface.

Abstract

Electromagnetic environments are becoming increasingly complex and congested, creating a growing challenge for systems that rely on electromagnetic waves for communication, sensing, or imaging, particularly in reverberating environments. The use of programmable metasurfaces provides a potential means of directing waves to optimize wireless channels on-demand, ensuring reliable operation and protecting sensitive electronic components. Here we introduce a technique that combines a deep learning network with a binary programmable metasurface to shape waves in complex reverberant electromagnetic environments, in particular ones where there is no direct line of sight. We applied this technique for wavefront reconstruction and control, and accurately determined metasurface configurations based on measured system scattering responses in a chaotic microwave cavity. The state of the metasurface that realizes desired electromagnetic wave field distribution properties was successfully determined even in cases previously unseen by the deep learning algorithm. Our technique is enabled by the reverberant nature of the cavity, and is effective with a metasurface that covers only $\sim$1.5\% of the total cavity surface area.