Sensitivity benchmarks of structural representations for atomic-scale machine learning

DOI

This dataset contains three sets of CH4 geometries that are distorted along special directions, to reveal the sensitivity to atomic displacements of structural descriptors used in machine-learning applications. The structures are stored in a format that can be visualized on http://chemiscope.org, and contain also DFT-computed energies, as well as the sensitivity analysis of four different kinds of features.

Identifier
DOI https://doi.org/10.24435/materialscloud:7z-g6
Related Identifier https://chemiscope.materialscloud.io/?load=https%3A%2F%2F127.0.0.1%2Fapi%2Frecords%2Fxk012-g6s95%2Ffiles%2Fasymmetric_ch4.chemiscope.json.gz%2Fcontent%3Ffilename%3Dasymmetric_ch4.chemiscope.json.gz%26materials_cloud_doi%3D10.24435%2Fmaterialscloud%3A7z-g6
Related Identifier https://chemiscope.materialscloud.io/?load=https%3A%2F%2F127.0.0.1%2Fapi%2Frecords%2Fxk012-g6s95%2Ffiles%2Fsymmetric_ch4.chemiscope.json.gz%2Fcontent%3Ffilename%3Dsymmetric_ch4.chemiscope.json.gz%26materials_cloud_doi%3D10.24435%2Fmaterialscloud%3A7z-g6
Related Identifier https://chemiscope.materialscloud.io/?load=https%3A%2F%2F127.0.0.1%2Fapi%2Frecords%2Fxk012-g6s95%2Ffiles%2Fdegenerate_ch4.chemiscope.json.gz%2Fcontent%3Ffilename%3Ddegenerate_ch4.chemiscope.json.gz%26materials_cloud_doi%3D10.24435%2Fmaterialscloud%3A7z-g6
Related Identifier https://archive.materialscloud.org/communities/mcarchive
Related Identifier https://doi.org/10.24435/materialscloud:9z-82
Metadata Access https://archive.materialscloud.org/oai2d?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:1024
Provenance
Creator Pozdnyakov, Sergey; Ceriotti, Michele
Publisher Materials Cloud
Contributor Pozdnyakov, Sergey; Ceriotti, Michele
Publication Year 2021
Rights info:eu-repo/semantics/openAccess; Creative Commons Attribution Non Commercial 4.0 International; https://creativecommons.org/licenses/by-nc/4.0/legalcode
OpenAccess true
Contact archive(at)materialscloud.org
Representation
Language English
Resource Type info:eu-repo/semantics/other
Format application/gzip; text/plain; text/markdown
Discipline Materials Science and Engineering