A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer
Abstract This work presents a framework governing the development of an efficient, accurate, and transferable coarse-grained (CG) model of a polyether material. The framework combines bottom-up and top-down approaches of coarse-grained model parameters by integrating machine learning (ML) with optim...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-022-00914-4 |
| _version_ | 1797452114456215552 |
|---|---|
| author | Zakiya Shireen Hansani Weeratunge Adrian Menzel Andrew W. Phillips Ronald G. Larson Kate Smith-Miles Elnaz Hajizadeh |
| author_facet | Zakiya Shireen Hansani Weeratunge Adrian Menzel Andrew W. Phillips Ronald G. Larson Kate Smith-Miles Elnaz Hajizadeh |
| author_sort | Zakiya Shireen |
| collection | DOAJ |
| description | Abstract This work presents a framework governing the development of an efficient, accurate, and transferable coarse-grained (CG) model of a polyether material. The framework combines bottom-up and top-down approaches of coarse-grained model parameters by integrating machine learning (ML) with optimization algorithms. In the bottom-up approach, bonded interactions of the CG model are optimized using deep neural networks (DNN), where atomistic bonded distributions are matched. In the top-down approach, optimization of nonbonded parameters is accomplished by reproducing the temperature-dependent experimental density. We demonstrate that developed framework addresses the thermodynamic consistency and transferability issues associated with the classical coarse-graining approaches. The efficiency and transferability of the CG model is demonstrated through accurate predictions of chain statistics, the limiting behavior of the glass transition temperature, diffusion, and stress relaxation, where none were included in the parametrization process. The accuracy of the predicted properties are evaluated in context of molecular theories and available experimental data. |
| first_indexed | 2024-03-09T15:03:05Z |
| format | Article |
| id | doaj.art-8728fe8a841b443e8973ef4520ffe939 |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-03-09T15:03:05Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-8728fe8a841b443e8973ef4520ffe9392023-11-26T13:47:22ZengNature Portfolionpj Computational Materials2057-39602022-11-018111110.1038/s41524-022-00914-4A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymerZakiya Shireen0Hansani Weeratunge1Adrian Menzel2Andrew W. Phillips3Ronald G. Larson4Kate Smith-Miles5Elnaz Hajizadeh6Department of Mechanical Engineering, Faculty of Engineering and Information Technology, The University of MelbourneDepartment of Mechanical Engineering, Faculty of Engineering and Information Technology, The University of MelbournePlatforms Division, Defence Science and Technology GroupPlatforms Division, Defence Science and Technology GroupDepartment of Chemical Engineering, University of MichiganSchool of Mathematics and Statistics, The University of MelbourneDepartment of Mechanical Engineering, Faculty of Engineering and Information Technology, The University of MelbourneAbstract This work presents a framework governing the development of an efficient, accurate, and transferable coarse-grained (CG) model of a polyether material. The framework combines bottom-up and top-down approaches of coarse-grained model parameters by integrating machine learning (ML) with optimization algorithms. In the bottom-up approach, bonded interactions of the CG model are optimized using deep neural networks (DNN), where atomistic bonded distributions are matched. In the top-down approach, optimization of nonbonded parameters is accomplished by reproducing the temperature-dependent experimental density. We demonstrate that developed framework addresses the thermodynamic consistency and transferability issues associated with the classical coarse-graining approaches. The efficiency and transferability of the CG model is demonstrated through accurate predictions of chain statistics, the limiting behavior of the glass transition temperature, diffusion, and stress relaxation, where none were included in the parametrization process. The accuracy of the predicted properties are evaluated in context of molecular theories and available experimental data.https://doi.org/10.1038/s41524-022-00914-4 |
| spellingShingle | Zakiya Shireen Hansani Weeratunge Adrian Menzel Andrew W. Phillips Ronald G. Larson Kate Smith-Miles Elnaz Hajizadeh A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer npj Computational Materials |
| title | A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer |
| title_full | A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer |
| title_fullStr | A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer |
| title_full_unstemmed | A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer |
| title_short | A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer |
| title_sort | machine learning enabled hybrid optimization framework for efficient coarse graining of a model polymer |
| url | https://doi.org/10.1038/s41524-022-00914-4 |
| work_keys_str_mv | AT zakiyashireen amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT hansaniweeratunge amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT adrianmenzel amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT andrewwphillips amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT ronaldglarson amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT katesmithmiles amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT elnazhajizadeh amachinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT zakiyashireen machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT hansaniweeratunge machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT adrianmenzel machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT andrewwphillips machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT ronaldglarson machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT katesmithmiles machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer AT elnazhajizadeh machinelearningenabledhybridoptimizationframeworkforefficientcoarsegrainingofamodelpolymer |