Electronic structure prediction of medium and high entropy alloys across composition space
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917205862514688 |
|---|---|
| author | Pathrudkar, Shashank Taylor, Stephanie Keripale, Abhishek Gangan, Abhijeet Sadashiv Thiagarajan, Ponkrshnan Agarwal, Shivang Marian, Jaime Ghosh, Susanta Banerjee, Amartya S. |
| author_facet | Pathrudkar, Shashank Taylor, Stephanie Keripale, Abhishek Gangan, Abhijeet Sadashiv Thiagarajan, Ponkrshnan Agarwal, Shivang Marian, Jaime Ghosh, Susanta Banerjee, Amartya S. |
| contents | We propose machine learning (ML) models to predict the electron density -- the fundamental unknown of a material's ground state -- across the composition space of concentrated alloys. From this, other physical properties can be inferred, enabling accelerated exploration. A significant challenge is that the number of sampled compositions and descriptors required to accurately predict fields like the electron density increases rapidly with species. To address this, we employ Bayesian Active Learning (AL), which minimizes training data requirements by leveraging uncertainty quantification capabilities of Bayesian Neural Networks. Compared to strategic tessellation of the composition space, Bayesian-AL reduces the number of training data points by a factor of 2.5 for ternary (SiGeSn) and 1.7 for quaternary (CrFeCoNi) systems. We also introduce easy-to-optimize, body-attached-frame descriptors, which respect physical symmetries and maintain approximately the same descriptor-vector size as alloy elements increase. Our ML models demonstrate high accuracy and generalizability in predicting both electron density and energy across composition space. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08294 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Electronic structure prediction of medium and high entropy alloys across composition space Pathrudkar, Shashank Taylor, Stephanie Keripale, Abhishek Gangan, Abhijeet Sadashiv Thiagarajan, Ponkrshnan Agarwal, Shivang Marian, Jaime Ghosh, Susanta Banerjee, Amartya S. Materials Science Disordered Systems and Neural Networks Computational Physics Quantum Physics We propose machine learning (ML) models to predict the electron density -- the fundamental unknown of a material's ground state -- across the composition space of concentrated alloys. From this, other physical properties can be inferred, enabling accelerated exploration. A significant challenge is that the number of sampled compositions and descriptors required to accurately predict fields like the electron density increases rapidly with species. To address this, we employ Bayesian Active Learning (AL), which minimizes training data requirements by leveraging uncertainty quantification capabilities of Bayesian Neural Networks. Compared to strategic tessellation of the composition space, Bayesian-AL reduces the number of training data points by a factor of 2.5 for ternary (SiGeSn) and 1.7 for quaternary (CrFeCoNi) systems. We also introduce easy-to-optimize, body-attached-frame descriptors, which respect physical symmetries and maintain approximately the same descriptor-vector size as alloy elements increase. Our ML models demonstrate high accuracy and generalizability in predicting both electron density and energy across composition space. |
| title | Electronic structure prediction of medium and high entropy alloys across composition space |
| topic | Materials Science Disordered Systems and Neural Networks Computational Physics Quantum Physics |
| url | https://arxiv.org/abs/2410.08294 |