Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties
Polymer electrolytes are promising candidates for the next generation lithium-ion battery technology. Large scale screening of polymer electrolytes is hindered by the significant cost of molecular dynamics (MD) simulation in amorphous systems: the amorphous structure of polymers requires multiple, r...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2024
|
| Online Access: | https://hdl.handle.net/1721.1/154301 |
| _version_ | 1824458300812427264 |
|---|---|
| author | Xie, Tian France-Lanord, Arthur Wang, Yanming Lopez, Jeffrey Stolberg, Michael A. Hill, Megan Leverick, Graham Michael Gomez-Bombarelli, Rafael Johnson, Jeremiah A. Shao-Horn, Yang Grossman, Jeffrey C. |
| author2 | Massachusetts Institute of Technology. Department of Materials Science and Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Materials Science and Engineering Xie, Tian France-Lanord, Arthur Wang, Yanming Lopez, Jeffrey Stolberg, Michael A. Hill, Megan Leverick, Graham Michael Gomez-Bombarelli, Rafael Johnson, Jeremiah A. Shao-Horn, Yang Grossman, Jeffrey C. |
| author_sort | Xie, Tian |
| collection | MIT |
| description | Polymer electrolytes are promising candidates for the next generation lithium-ion battery technology. Large scale screening of polymer electrolytes is hindered by the significant cost of molecular dynamics (MD) simulation in amorphous systems: the amorphous structure of polymers requires multiple, repeated sampling to reduce noise and the slow relaxation requires long simulation time for convergence. Here, we accelerate the screening with a multi-task graph neural network that learns from a large amount of noisy, unconverged, short MD data and a small number of converged, long MD data. We achieve accurate predictions of 4 different converged properties and screen a space of 6247 polymers that is orders of magnitude larger than previous computational studies. Further, we extract several design principles for polymer electrolytes and provide an open dataset for the community. Our approach could be applicable to a broad class of material discovery problems that involve the simulation of complex, amorphous materials. |
| first_indexed | 2024-09-23T14:21:30Z |
| format | Article |
| id | mit-1721.1/154301 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:23:42Z |
| publishDate | 2024 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1543012025-01-07T04:29:16Z Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties Xie, Tian France-Lanord, Arthur Wang, Yanming Lopez, Jeffrey Stolberg, Michael A. Hill, Megan Leverick, Graham Michael Gomez-Bombarelli, Rafael Johnson, Jeremiah A. Shao-Horn, Yang Grossman, Jeffrey C. Massachusetts Institute of Technology. Department of Materials Science and Engineering Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Research Laboratory of Electronics Massachusetts Institute of Technology. Department of Chemistry Massachusetts Institute of Technology. Department of Mechanical Engineering Polymer electrolytes are promising candidates for the next generation lithium-ion battery technology. Large scale screening of polymer electrolytes is hindered by the significant cost of molecular dynamics (MD) simulation in amorphous systems: the amorphous structure of polymers requires multiple, repeated sampling to reduce noise and the slow relaxation requires long simulation time for convergence. Here, we accelerate the screening with a multi-task graph neural network that learns from a large amount of noisy, unconverged, short MD data and a small number of converged, long MD data. We achieve accurate predictions of 4 different converged properties and screen a space of 6247 polymers that is orders of magnitude larger than previous computational studies. Further, we extract several design principles for polymer electrolytes and provide an open dataset for the community. Our approach could be applicable to a broad class of material discovery problems that involve the simulation of complex, amorphous materials. 2024-04-26T19:19:27Z 2024-04-26T19:19:27Z 2022-06-14 2024-04-26T19:11:32Z Article http://purl.org/eprint/type/JournalArticle 2041-1723 https://hdl.handle.net/1721.1/154301 Xie, T., France-Lanord, A., Wang, Y. et al. Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties. Nat Commun 13, 3415 (2022). en 10.1038/s41467-022-30994-1 Nature Communications Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Springer Science and Business Media LLC |
| spellingShingle | Xie, Tian France-Lanord, Arthur Wang, Yanming Lopez, Jeffrey Stolberg, Michael A. Hill, Megan Leverick, Graham Michael Gomez-Bombarelli, Rafael Johnson, Jeremiah A. Shao-Horn, Yang Grossman, Jeffrey C. Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| title | Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| title_full | Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| title_fullStr | Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| title_full_unstemmed | Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| title_short | Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| title_sort | accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties |
| url | https://hdl.handle.net/1721.1/154301 |
| work_keys_str_mv | AT xietian acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT francelanordarthur acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT wangyanming acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT lopezjeffrey acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT stolbergmichaela acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT hillmegan acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT leverickgrahammichael acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT gomezbombarellirafael acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT johnsonjeremiaha acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT shaohornyang acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties AT grossmanjeffreyc acceleratingamorphouspolymerelectrolytescreeningbylearningtoreduceerrorsinmoleculardynamicssimulatedproperties |