How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning

Metamaterials are composite materials with engineered geometrical micro- and meso-structures that can lead to uncommon physical properties, like negative Poisson's ratio or ultra-low shear resistance. Periodic metamaterials are composed of repeating unit-cells, and geometrical patterns within these unit-cells influence the propagation of elastic or acoustic waves and control dispersion. In this work, we develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials that reveal their dynamic properties. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates. Machine learning models built using these feature classes can accurately predict dynamic material properties. These feature representations (particularly the unit-cell templates) have a useful property: they can operate on designs of higher resolutions. By learning key coarse scale patterns that can be reliably transferred to finer resolution design space via the shape-frequency features or unit-cell templates, we can almost freely design the fine resolution features of the unit-cell without changing coarse scale physics. Through this multi-resolution approach, we are able to design materials that possess target frequency ranges in which waves are allowed or disallowed to propagate (frequency bandgaps). Our approach yields major benefits: (1) unlike typical machine learning approaches to materials science, our models are interpretable, (2) our approaches leverage multi-resolution properties, and (3) our approach provides design flexibility.