Sensitivity benchmarks of structural representations for atomic-scale machine learning

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
Source https://archive.materialscloud.org/record/2021.149
Metadata Access https://archive.materialscloud.org/xml?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai:materialscloud.org:1024
Provenance
Creator Pozdnyakov, Sergey; Ceriotti, Michele
Publisher Materials Cloud
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 Dataset
Discipline Materials Science and Engineering