SiOx-ACE-24

The training database used to fit the SiOx-ACE-24 potential in: Modelling atomic and nanoscale structure in the silicon-oxygen system through active machine-learning. The dataset comprises structures taken from the Si-GAP-18 and SiO2-GAP-22 datasets, together with new structures generated using an active-learning approach.

>>> from load_atoms import load_dataset
>>> load_dataset("SiOx-ACE-24")
SiOx-ACE-24:
    structures: 11,428
    atoms: 1,258,198
    species:
        O: 55.82%
        Si: 44.18%
    properties:
        per atom: (charge_bader, forces)
        per structure: (config_type, energy, free_energy, stress, virial)

License

This dataset is licensed under the CC BY 4.0 license.

Citation

If you use this dataset in your work, please cite the following:

@article{Erhard-24-03,
    title = {
        Modelling Atomic and Nanoscale Structure in the
        Silicon--Oxygen System through Active Machine Learning
    },
    author = {
        Erhard, Linus C. and Rohrer, Jochen
        and Albe, Karsten and Deringer, Volker L.
    },
    year = {2024},
    journal = {Nature Communications},
    volume = {15},
    number = {1},
    pages = {1927},
    doi = {10.1038/s41467-024-45840-9},
}

Properties

Per-atom:

Property	Units	Type	Description
forces	eV/Å	ndarray(N, 3)	force vectors (DFT)

Per-structure:

Property	Units	Type	Description
energy	eV	float64	total structure energy (DFT)
free_energy	eV	float64	total structure free energy (DFT)
virial	eV	ndarray(3, 3)	virial stress tensor (DFT)
stress	eV Å\({}^{-3}\)	ndarray(3, 3)	stress tensor (DFT) (- virial / cell.volume)
config_type		str	category of structure

Miscellaneous information

SiOx-ACE-24 is imported as an InMemoryAtomsDataset:

Importer script for SiOx-ACE-24

from __future__ import annotations

from pathlib import Path
from typing import Iterator

import ase.io
from ase import Atoms
from load_atoms.database.backend import BaseImporter, rename, unzip_file
from load_atoms.database.internet import FileDownload
from load_atoms.progress import Progress


class Importer(BaseImporter):
    @classmethod
    def files_to_download(cls) -> list[FileDownload]:
        return [
            FileDownload(
                url="https://zenodo.org/records/10419194/files/database.zip",
                expected_hash="42eb5808b0aa",
            )
        ]

    @classmethod
    def get_structures(
        cls, tmp_dir: Path, progress: Progress
    ) -> Iterator[Atoms]:
        contents = unzip_file(tmp_dir / "database.zip", progress)
        for structure in ase.io.iread(
            contents / "database/training.general_purpose.SiOx.xyz"
        ):
            yield rename(
                structure,
                {
                    "dft_forces": "forces",
                    "dft_energy": "energy",
                    "dft_free_energy": "free_energy",
                    "dft_stress": "stress",
                    "dft_virials": "virial",
                },
            )

DatabaseEntry for SiOx-ACE-24

name: SiOx-ACE-24
year: 2024
description: |
    The training database used to fit the `SiOx-ACE-24 potential <https://zenodo.org/records/10419194>`_ in:
    `Modelling atomic and nanoscale structure in the silicon-oxygen system through active machine-learning <https://www.nature.com/articles/s41467-024-45840-9>`_.
    The dataset comprises structures taken from the `Si-GAP-18 <https://jla-gardner.github.io/load-atoms/datasets/Si-GAP-18.html>`__
    and `SiO2-GAP-22 <https://jla-gardner.github.io/load-atoms/datasets/SiO2-GAP-22.html>`__ datasets, together
    with new structures generated using an active-learning approach.
category: Potential Fitting
minimum_load_atoms_version: 0.2
license: CC BY 4.0
citation: |
    @article{Erhard-24-03,
        title = {
            Modelling Atomic and Nanoscale Structure in the
            Silicon--Oxygen System through Active Machine Learning
        },
        author = {
            Erhard, Linus C. and Rohrer, Jochen
            and Albe, Karsten and Deringer, Volker L.
        },
        year = {2024},
        journal = {Nature Communications},
        volume = {15},
        number = {1},
        pages = {1927},
        doi = {10.1038/s41467-024-45840-9},
    }
representative_structure: 7390
per_atom_properties:
    forces:
        desc: force vectors (DFT)
        units: eV/Å
per_structure_properties:
    energy:
        desc: total structure energy (DFT)
        units: eV
    free_energy:
        desc: total structure free energy (DFT)
        units: eV
    virial:
        desc: virial stress tensor (DFT)
        units: eV
    stress:
        desc: |
            | stress tensor (DFT)
            | (:code:`- virial / cell.volume`)
        units: eV Å\ :math:`{}^{-3}`
    config_type:
        desc: category of structure


# TODO: remove after Dec 2024
# backwards compatability: unused as of 0.3.0
files:
    - url: https://zenodo.org/records/10419194/files/database.zip
      hash: 42eb5808b0aa
processing:
    - UnZip
    - SelectFile:
        file: database/training.general_purpose.SiOx.xyz
    - ReadASE
    - Rename:
        dft_forces: forces
        dft_energy: energy
        dft_free_energy: free_energy
        dft_stress: stress
        dft_virials: virial