English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Advancing descriptor search in materials science: feature engineering and selection strategies

Hoock, B., Rigamonti, S., & Draxl, C. (2022). Advancing descriptor search in materials science: feature engineering and selection strategies. New Journal of Physics, 24(11): 113049. doi:10.1088/1367-2630/aca49c.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-000C-2250-3 Version Permalink: https://hdl.handle.net/21.11116/0000-000C-2286-6
Genre: Journal Article

Files

show Files
hide Files
:
Hoock_2022_New_J._Phys._24_113049.pdf (Publisher version), 3MB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-000C-2252-1
Name:
Hoock_2022_New_J._Phys._24_113049.pdf
Description:
-
OA-Status:
Gold
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
2022
Copyright Info:
The Author(s)
License:
https://creativecommons.org/licenses/by/4.0/

Locators

show

Creators

show
hide
 Creators:
Hoock, Benedikt1, Author           
Rigamonti, Santiago, Author
Draxl, Claudia1, Author           
Affiliations:
1NOMAD, Fritz Haber Institute, Max Planck Society, ou_3253022              

Content

show
hide
Free keywords: -
 Abstract: A main goal of data-driven materials research is to find optimal low-dimensional descriptors, allowing us to predict a physical property, and to interpret them in a human-understandable way. In this work, we advance methods to identify descriptors out of a large pool of candidate features by means of compressed sensing. To this extent, we develop schemes for engineering appropriate candidate features that are based on simple basic properties of building blocks that constitute the materials and that are able to represent a multi-component system by scalar numbers. Cross-validation based feature-selection methods are developed for identifying the most relevant features, thereby focusing on high generalizability. We apply our approaches to an ab initio dataset of ternary group-IV compounds to obtain a set of descriptors for predicting lattice constants and energies of mixing. In particular, we introduce simple complexity measures in terms of involved algebraic operations as well as the amount of utilized basic properties.

Details

show
hide
Language(s): eng - English
 Dates: 2022-06-242022-11-212022-12-01
 Publication Status: Published online
 Pages: 18
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1088/1367-2630/aca49c
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : NOMAD CoE - Novel materials for urgent energy, environmental and societal challenges
Grant ID : 951786
Funding program : Horizon 2020 (H2020)
Funding organization : European Commission (EC)
Project name : NoMaD - The Novel Materials Discovery Laboratory
Grant ID : 676580
Funding program : Horizon 2020 (H2020)
Funding organization : European Commission (EC)

Source 1

show
hide
Title: New Journal of Physics
  Abbreviation : New J. Phys.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Bristol : IOP Publishing
Pages: 18 Volume / Issue: 24 (11) Sequence Number: 113049 Start / End Page: - Identifier: ISSN: 1367-2630
CoNE: https://pure.mpg.de/cone/journals/resource/954926913666