Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929299480641536 |
|---|---|
| author | Ghaffari, Kimia Bavdekar, Salil Spearot, Douglas E. Subhash, Ghatu |
| author_facet | Ghaffari, Kimia Bavdekar, Salil Spearot, Douglas E. Subhash, Ghatu |
| contents | The number of published Machine Learning Interatomic Potentials (MLIPs) has increased significantly in recent years. These new data-driven potential energy approximations often lack the physics-based foundations that inform many traditionally-developed interatomic potentials and hence require robust validation methods for their applicability, accuracy, computational efficiency, and transferability to the intended applications. This work presents a sequential, three-stage workflow for MLIP validation: (i) preliminary validation, (ii) static property prediction, and (iii) dynamic property prediction. This material-agnostic procedure is demonstrated in a tutorial approach for the development of a robust MLIP for boron carbide (B4C), a widely employed, structurally complex ceramic that undergoes a deleterious deformation mechanism called "amorphization" under high-pressure loading. It is shown that the resulting B4C MLIP offers a more accurate prediction of properties compared to the available empirical potential. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05222 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics Ghaffari, Kimia Bavdekar, Salil Spearot, Douglas E. Subhash, Ghatu Materials Science Disordered Systems and Neural Networks Mesoscale and Nanoscale Physics The number of published Machine Learning Interatomic Potentials (MLIPs) has increased significantly in recent years. These new data-driven potential energy approximations often lack the physics-based foundations that inform many traditionally-developed interatomic potentials and hence require robust validation methods for their applicability, accuracy, computational efficiency, and transferability to the intended applications. This work presents a sequential, three-stage workflow for MLIP validation: (i) preliminary validation, (ii) static property prediction, and (iii) dynamic property prediction. This material-agnostic procedure is demonstrated in a tutorial approach for the development of a robust MLIP for boron carbide (B4C), a widely employed, structurally complex ceramic that undergoes a deleterious deformation mechanism called "amorphization" under high-pressure loading. It is shown that the resulting B4C MLIP offers a more accurate prediction of properties compared to the available empirical potential. |
| title | Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics |
| topic | Materials Science Disordered Systems and Neural Networks Mesoscale and Nanoscale Physics |
| url | https://arxiv.org/abs/2402.05222 |