Recommended by

Indexed by

Machine learning guided high-throughput search of non-oxide garnets

Jonathan Schmidt1, Hai-Chen Wang1, Georg Schmidt1, Miguel A. L. Marques1*

1 Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, 06120 Halle (Saale), Germany.

* Corresponding authors emails: miguel.marques@physik.uni-halle.de
DOI10.24435/materialscloud:gm-n0 [version v1]

Publication date: Aug 30, 2022

How to cite this record

Jonathan Schmidt, Hai-Chen Wang, Georg Schmidt, Miguel A. L. Marques, Machine learning guided high-throughput search of non-oxide garnets, Materials Cloud Archive 2022.107 (2022), doi: 10.24435/materialscloud:gm-n0.


Garnets, known since the early stages of human civilization, have found important applications in modern technologies including magnetorestriction, spintronics, lithium batteries, etc. The overwhelming majority of experimentally known garnets are oxides, while explorations (experimental or theoretical) for the rest of the chemical space have been limited in scope. A key issue is that the garnet structure has a large primitive unit cell, requiring an enormous amount of computational resources. To perform a comprehensive search of the complete chemical space for new garnets, we combine recent progress in graph neural networks with high-throughput calculations. We apply the machine learning model to identify the potential (meta-)stable garnet systems before systematic density-functional calculations to validate the predictions. In this way, we discover more than 600 ternary garnets with distances to the convex hull below 100~meV/atom with a variety of physical and chemical properties. This includes sulfide, nitride and halide garnets. This record includes the results of 15742 vasp calculations of the ternary garnets investigated. All calculations were performed using the PBE functional.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
37.8 MiB Json containing calculations in pymatgen's ComputedStructureEntry format


Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference
J. Schmidt, H.-C, Wang, G. Schmidt, and M.A.L. Marques (in preparation)


Garnets density-functional theory VASP

Version history:

2022.107 (version v1) [This version] Aug 30, 2022 DOI10.24435/materialscloud:gm-n0