Hybrid machine learning guides experimental discovery of multicomponent metallic glasses
Hybrid classification and regression models with physically motivated descriptors, trained on about 5,000 metallic-glass compositions, guided exploration of multicomponent alloy compositions. Researchers synthesized 23 selected compositions: 12 predicted glass-formers produced glass in bulk, ribbon or both, while 11 predicted negative comparisons did not form glass under the tested preparation conditions. Six of the positive designs formed bulk glass; six formed glassy ribbons only. These selected experiments are not an unbiased estimate of global predictive accuracy. Some authors disclosed inventorship on a filed patent related to the new bulk compositions; composition-level prior art and independent replication remain open.
Technology: Hybrid classification/regression models including adaptive boosting, SVM, KNN and rational-quadratic Gaussian-process regression
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: direct test
- Tested: The study reports synthesis and diffraction/thermal characterization of selected predicted positive and negative compositions.
- Still unknown: Selected validation set, not unbiased global accuracy; patent inventorship disclosed and composition-level novelty/replication remain open.
- AI role: Hybrid models trained on prior metallic-glass data prioritized compositions for synthesis and measurement.
Evidence sources: https://www.nature.com/articles/s41524-021-00607-4 · https://scholars.cityu.edu.hk/ws/portalfiles/portal/86074146/82269007.pdf
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 16 Nov 2026. Review scope: Primary publisher full indexed article and institutional full-text copy, methods, results, date, affiliation and patent disclosure..
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.