Compositional Representation of Polymorphic Crystalline Materials

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Namkyeong, Noh, Heewoong, Na, Gyoung S., Sun, Jimeng, Fu, Tianfan, Zitnik, Marinka, Park, Chanyoung
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913600314015744
author Lee, Namkyeong
Noh, Heewoong
Na, Gyoung S.
Sun, Jimeng
Fu, Tianfan
Zitnik, Marinka
Park, Chanyoung
author_facet Lee, Namkyeong
Noh, Heewoong
Na, Gyoung S.
Sun, Jimeng
Fu, Tianfan
Zitnik, Marinka
Park, Chanyoung
contents Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world material synthesis processes. An alternative, using compositional descriptors, offers a simpler approach by indicating the elemental ratios of compounds without detailed structural insights. However, accurately representing materials solely with compositional descriptors presents challenges due to polymorphism, where a single composition can correspond to various structural arrangements, creating ambiguities in its representation. To this end, we introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information. Extensive evaluations on sixteen datasets demonstrate the effectiveness of PCRL in learning compositional representation, and our analysis highlights its potential applicability of PCRL in material discovery. The source code for PCRL is available at https://github.com/Namkyeong/PCRL.
format Preprint
id arxiv_https___arxiv_org_abs_2312_13289
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Compositional Representation of Polymorphic Crystalline Materials
Lee, Namkyeong
Noh, Heewoong
Na, Gyoung S.
Sun, Jimeng
Fu, Tianfan
Zitnik, Marinka
Park, Chanyoung
Materials Science
Machine Learning
Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world material synthesis processes. An alternative, using compositional descriptors, offers a simpler approach by indicating the elemental ratios of compounds without detailed structural insights. However, accurately representing materials solely with compositional descriptors presents challenges due to polymorphism, where a single composition can correspond to various structural arrangements, creating ambiguities in its representation. To this end, we introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information. Extensive evaluations on sixteen datasets demonstrate the effectiveness of PCRL in learning compositional representation, and our analysis highlights its potential applicability of PCRL in material discovery. The source code for PCRL is available at https://github.com/Namkyeong/PCRL.
title Compositional Representation of Polymorphic Crystalline Materials
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2312.13289