Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials
© 2019, The Author(s). Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2021
|
| Online Access: | https://hdl.handle.net/1721.1/134825 |
| _version_ | 1826210957002539008 |
|---|---|
| author | Xie, Tian France-Lanord, Arthur Wang, Yanming Shao-Horn, Yang Grossman, Jeffrey C |
| author_facet | Xie, Tian France-Lanord, Arthur Wang, Yanming Shao-Horn, Yang Grossman, Jeffrey C |
| author_sort | Xie, Tian |
| collection | MIT |
| description | © 2019, The Author(s). Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. In this work, we develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information, which would be difficult to obtain otherwise, can be learned for various multi-component amorphous material systems. With the large amounts of molecular dynamics data generated every day in nearly every aspect of materials design, this approach provides a broadly applicable, automated tool to understand atomic scale dynamics in material systems. |
| first_indexed | 2024-09-23T14:58:28Z |
| format | Article |
| id | mit-1721.1/134825 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:58:28Z |
| publishDate | 2021 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1348252022-04-01T17:13:08Z Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials Xie, Tian France-Lanord, Arthur Wang, Yanming Shao-Horn, Yang Grossman, Jeffrey C © 2019, The Author(s). Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. In this work, we develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information, which would be difficult to obtain otherwise, can be learned for various multi-component amorphous material systems. With the large amounts of molecular dynamics data generated every day in nearly every aspect of materials design, this approach provides a broadly applicable, automated tool to understand atomic scale dynamics in material systems. 2021-10-27T20:09:21Z 2021-10-27T20:09:21Z 2019 2019-09-19T14:37:28Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/134825 en 10.1038/s41467-019-10663-6 Nature Communications Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Nature |
| spellingShingle | Xie, Tian France-Lanord, Arthur Wang, Yanming Shao-Horn, Yang Grossman, Jeffrey C Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| title | Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| title_full | Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| title_fullStr | Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| title_full_unstemmed | Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| title_short | Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| title_sort | graph dynamical networks for unsupervised learning of atomic scale dynamics in materials |
| url | https://hdl.handle.net/1721.1/134825 |
| work_keys_str_mv | AT xietian graphdynamicalnetworksforunsupervisedlearningofatomicscaledynamicsinmaterials AT francelanordarthur graphdynamicalnetworksforunsupervisedlearningofatomicscaledynamicsinmaterials AT wangyanming graphdynamicalnetworksforunsupervisedlearningofatomicscaledynamicsinmaterials AT shaohornyang graphdynamicalnetworksforunsupervisedlearningofatomicscaledynamicsinmaterials AT grossmanjeffreyc graphdynamicalnetworksforunsupervisedlearningofatomicscaledynamicsinmaterials |