Hydrogen Diffusion in Magnesium Using Machine Learning Potentials: a comparative study
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_ | 1866913779266093056 |
|---|---|
| author | Angeletti, Andrea Leoni, Luca Massa, Dario Pasquini, Luca Papanikolaou, Stefanos Franchini, Cesare |
| author_facet | Angeletti, Andrea Leoni, Luca Massa, Dario Pasquini, Luca Papanikolaou, Stefanos Franchini, Cesare |
| contents | Understanding and accurately predicting hydrogen diffusion in materials is challenging due to the complex interactions between hydrogen defects and the crystal lattice. These interactions span large length and time scales, making them difficult to address with standard ab initio techniques. This work addresses this challenge by employing accelerated machine learning (ML) molecular dynamics simulations through active learning. We conduct a comparative study of different ML-based interatomic potential schemes, including VASP, MACE, and CHGNet, utilizing various training strategies such as on-the-fly learning, pre-trained universal models, and fine-tuning.By considering different temperatures and concentration regimes, we obtain hydrogen diffusion coefficients and activation energy values which align remarkably well with experimental results, underlining the efficacy and accuracy of ML-assisted methodologies in the context of diffusive dynamics. Particularly, our procedure significantly reduces the computational effort associated with traditional transition state calculations or ad-hoc designed interatomic potentials. The results highlight the limitations of pre-trained universal solutions for defective materials and how they can be improved by fine-tuning. Specifically, fine-tuning the models on a database produced during on-the-fly training of VASP ML force-field allows the retrieving of DFT-level accuracy at a fraction of the computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21088 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hydrogen Diffusion in Magnesium Using Machine Learning Potentials: a comparative study Angeletti, Andrea Leoni, Luca Massa, Dario Pasquini, Luca Papanikolaou, Stefanos Franchini, Cesare Materials Science Other Condensed Matter Chemical Physics Computational Physics Understanding and accurately predicting hydrogen diffusion in materials is challenging due to the complex interactions between hydrogen defects and the crystal lattice. These interactions span large length and time scales, making them difficult to address with standard ab initio techniques. This work addresses this challenge by employing accelerated machine learning (ML) molecular dynamics simulations through active learning. We conduct a comparative study of different ML-based interatomic potential schemes, including VASP, MACE, and CHGNet, utilizing various training strategies such as on-the-fly learning, pre-trained universal models, and fine-tuning.By considering different temperatures and concentration regimes, we obtain hydrogen diffusion coefficients and activation energy values which align remarkably well with experimental results, underlining the efficacy and accuracy of ML-assisted methodologies in the context of diffusive dynamics. Particularly, our procedure significantly reduces the computational effort associated with traditional transition state calculations or ad-hoc designed interatomic potentials. The results highlight the limitations of pre-trained universal solutions for defective materials and how they can be improved by fine-tuning. Specifically, fine-tuning the models on a database produced during on-the-fly training of VASP ML force-field allows the retrieving of DFT-level accuracy at a fraction of the computational cost. |
| title | Hydrogen Diffusion in Magnesium Using Machine Learning Potentials: a comparative study |
| topic | Materials Science Other Condensed Matter Chemical Physics Computational Physics |
| url | https://arxiv.org/abs/2407.21088 |