How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
This work addresses the need for interpretable and data-efficient machine learning in metamaterials design, offering a domain-specific solution that is incremental in its approach.
The authors tackled the problem of opaque and data-hungry machine learning models in metamaterials design by developing interpretable approaches, resulting in methods that discover 2D metamaterials with user-specified frequency band gaps and provide logical rule-based conditions for design flexibility.
Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems. However, past work has usually relied on black box deep neural networks, whose reasoning processes are opaque and require enormous datasets that are expensive to obtain. In this work, we develop two novel machine learning approaches to metamaterials discovery that have neither of these disadvantages. These approaches, called shape-frequency features and unit-cell templates, can discover 2D metamaterials with user-specified frequency band gaps. Our approaches provide logical rule-based conditions on metamaterial unit-cells that allow for interpretable reasoning processes, and generalize well across design spaces of different resolutions. The templates also provide design flexibility where users can almost freely design the fine resolution features of a unit-cell without affecting the user's desired band gap.