Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials
Understanding local dynamical processes in materials is challenging due to the complexity of the local atomic environments. Here the authors propose a graph dynamical networks approach that is shown to learn the atomic scale dynamics in arbitrary phases and environments from molecular dynamics simul...
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2019
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/e95ce383366d4ae098b08194f9e7596d |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Understanding local dynamical processes in materials is challenging due to the complexity of the local atomic environments. Here the authors propose a graph dynamical networks approach that is shown to learn the atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. |
|---|