Scattered elastic waves provide non-invasive diagnostics and dynamic characterization of metamaterials, but extracting information from small-size samples is challenging. Here, convolutional neural networks are used to interpret diffracted waves, revealing how sample-edge scattering provides the most significant information on macroscopic metamaterial properties.
- Yuxin Zhai
- Hyung-Suk Kwon
- Bogdan-Ioan Popa
