FAIR Data and Interpretable AI Framework for Architectured Metamaterials
Brinson, L. Catherine, Rudin, Cynthia · 2026
Read FAIR Data and Interpretable AI Framework for Architectured Metamaterials by Brinson, L. Catherine, Rudin, Cynthia (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/doe-osti-3029848-fair-data-and-interpretable-ai-framework.txt.
Description
Chiara Daraio of the California Institute of Technology led this joint project with L. Catherine Brinson and Cynthia Rudin of Duke University, under awards DE-SC0021253 and DE-SC0021358. The subject is architectured metamaterials, solids whose inner pattern, not just their chemistry, sets how they act. The team built open benchmark datasets that meet the FAIR tests: findable, accessible, interoperable, and reusable. They also built a learning system meant to be read, not just run.
That system, Learning Refined Compositional Rules, pulls plain rules that link a pattern shape to bulk sound behavior across size scales. Such rules replace hunches and black-box searches that were hard to reuse. Tests with real samples checked the rules, which now guide tuning of wave spread and vibration control in acoustic devices.
Catalog record
| CREATOR | Brinson, L. Catherine, Rudin, Cynthia |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 17 KB |
| LICENSE | Public Domain |
| RIGHTS | PUBLIC DOMAIN |
| SOURCE | DOE OSTI |