Interpretable Machine Learning of Nanoparticle Stability through Topological Layer Embeddings
Felipe Hawthorne, Leandro Seixas, James M. Almeida, Cristiano F. Woellner, Raphael M. Tromer · 2026
Read Interpretable Machine Learning of Nanoparticle Stability through Topological Layer Embeddings by Felipe Hawthorne, Leandro Seixas, James M. Almeida, Cristiano F. Woellner, Raphael M. Tromer (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/PMC13359354.txt.
Description
Felipe Hawthorne and co-authors teach computers to find stable nanoparticles in a 2026 study. A nanoparticle's atoms can be arranged in a vast number of ways, and the most stable arrangement is the prize. Testing each by full physics is slow. The team built a description that splits each particle into surface, middle, and core layers using shape math.
Joined with boosted decision trees and a ranking method, the system picked out the most stable arrangements using only a few hundred full calculations for training. Because the layers have clear physical meaning, users can see why the model favors a design. Faster, clearer searches could speed work on catalysts and new materials.
Catalog record
| CREATOR | Felipe Hawthorne, Leandro Seixas, James M. Almeida, Cristiano F. Woellner, Raphael M. Tromer |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69978 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |