Chemistry and Local Environment Adaptive Representation graphs as material descriptors

Swetlana, S and Singh, AK (2024) Chemistry and Local Environment Adaptive Representation graphs as material descriptors. In: Acta Materialia, 276 .

	PDF act_mat_276_2024.pdf - Published Version Restricted to Registered users only Download (5MB) | Request a copy
	PDF Act_Mat_Vol_276_Sup_2024.pdf - Published Supplemental Material Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Accelerating materials design and property prediction via supervised learning involves manually generating feature vectors or performing complicated atom coordinates transformation, which restricts the model to a limited set of crystal structures or makes it challenging to provide chemical insights. In this work, we devised a unique low-dimensional featurization technique known as "Chemistry and Local Environment Adaptive Representation" (CLEAR) graphs to automatically learn the properties of materials through the chemistry of the atom connections. CLEAR is an adaptive featurization method that integrates the chemistry of atoms with their atomic environment using Voronoi nearest neighbours (NN). In addition, integrating the CLEAR descriptors with explainable machine learning models unravels its potential to obtain numerous scientific insights. We applied this approach to study the stability of compositional and configurational diverse high entropy alloys (HEAs). The proposed framework provides a universal low-dimensional representation with chemistry-informed local environment descriptors, which outperforms the prediction of phases and formation energies in HEAs. © 2024 Acta Materialia Inc.

Item Type:	Journal Article
Publication:	Acta Materialia
Publisher:	Acta Materialia Inc
Additional Information:	The copyright for this article belongs to Acta Materialia Inc.
Keywords:	Atoms; Entropy; Graphic methods; High-entropy alloys, Adaptive representations; Descriptors; Features vector; Formation likelihood; Graph representation; High entropy alloys; Local environments; Machine-learning; Materials design; Property predictions, Machine learning
Department/Centre:	Division of Chemical Sciences > Materials Research Centre
Date Deposited:	17 Dec 2024 11:17
Last Modified:	17 Dec 2024 11:17
URI:	http://eprints.iisc.ac.in/id/eprint/85809

Actions (login required)

View Item