A transferable machine-learning framework linking interstice distribution and plastic heterogeneity in metallic glasses
Understanding plastic deformation in metallic glasses is challenging due to their heterogeneous atomic environments. Here the authors propose a machine learning approach generalizable across compositions to predict the structural features from which plastic deformation is initiated in a metallic gla...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2019
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/444c69cac40f4b0eabb51d733ddb8f58 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Understanding plastic deformation in metallic glasses is challenging due to their heterogeneous atomic environments. Here the authors propose a machine learning approach generalizable across compositions to predict the structural features from which plastic deformation is initiated in a metallic glass. |
|---|