Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds

The cluster analysis of materials categorizes them according to similarities based on the features of materials, providing insight into the relationship between the materials. Conventional cluster analyses typically use basic features derived from the chemical composition and crystal structure witho...

Full description

Saved in:
Bibliographic Details
Main Authors: Nobuya Sato, Akira Takahashi, Shin Kiyohara, Kei Terayama, Ryo Tamura, Fumiyasu Oba
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400253
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846111022754037760
author Nobuya Sato
Akira Takahashi
Shin Kiyohara
Kei Terayama
Ryo Tamura
Fumiyasu Oba
author_facet Nobuya Sato
Akira Takahashi
Shin Kiyohara
Kei Terayama
Ryo Tamura
Fumiyasu Oba
author_sort Nobuya Sato
collection DOAJ
description The cluster analysis of materials categorizes them according to similarities based on the features of materials, providing insight into the relationship between the materials. Conventional cluster analyses typically use basic features derived from the chemical composition and crystal structure without considering target material properties such as the bandgap and dielectric constant. However, such approaches do not meet demands for grading materials according to properties of interest simultaneously with chemical and structural similarities. Herein, a clustering method grouping similar materials in terms of both the target properties and basic features is proposed. The clustering is compared considering the cohesive energy with that considering the bandgap of metal oxides, showing that their categorizations are clearly different. Further, several clusters classified by the bandgap are analyzed, and coordination environments related to each range of the bandgap are revealed. The clustering for the electronic static dielectric constant identifies a cluster involving several perovskite‐type oxides and balancing with the bandgap near the Pareto front. The method enables analyses with different viewpoints from those of the conventional clustering and feature importance analyses by taking the relationship between the target property and the basic features into account.
format Article
id doaj-art-1d8aa3932f954b9c801abb752611b8af
institution Kabale University
issn 2640-4567
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj-art-1d8aa3932f954b9c801abb752611b8af2024-12-23T13:10:42ZengWileyAdvanced Intelligent Systems2640-45672024-12-01612n/an/a10.1002/aisy.202400253Target Material Property‐Dependent Cluster Analysis of Inorganic CompoundsNobuya Sato0Akira Takahashi1Shin Kiyohara2Kei Terayama3Ryo Tamura4Fumiyasu Oba5Laboratory for Materials and Structures Institute of Innovative Research Tokyo Institute of Technology R3‐7, 4259 Nagatsuta, Midori‐ku 226‐8501 JapanLaboratory for Materials and Structures Institute of Innovative Research Tokyo Institute of Technology R3‐7, 4259 Nagatsuta, Midori‐ku 226‐8501 JapanLaboratory for Materials and Structures Institute of Innovative Research Tokyo Institute of Technology R3‐7, 4259 Nagatsuta, Midori‐ku 226‐8501 JapanGraduate School of Medical Life Science Yokohama City University 1‐7‐29 Suehiro‐cho, Tsurumi‐ku 230‐0045 JapanCenter for Basic Research on Materials National Institute for Materials Science 1‐1 Namiki Tsukuba 305‐0044 JapanLaboratory for Materials and Structures Institute of Innovative Research Tokyo Institute of Technology R3‐7, 4259 Nagatsuta, Midori‐ku 226‐8501 JapanThe cluster analysis of materials categorizes them according to similarities based on the features of materials, providing insight into the relationship between the materials. Conventional cluster analyses typically use basic features derived from the chemical composition and crystal structure without considering target material properties such as the bandgap and dielectric constant. However, such approaches do not meet demands for grading materials according to properties of interest simultaneously with chemical and structural similarities. Herein, a clustering method grouping similar materials in terms of both the target properties and basic features is proposed. The clustering is compared considering the cohesive energy with that considering the bandgap of metal oxides, showing that their categorizations are clearly different. Further, several clusters classified by the bandgap are analyzed, and coordination environments related to each range of the bandgap are revealed. The clustering for the electronic static dielectric constant identifies a cluster involving several perovskite‐type oxides and balancing with the bandgap near the Pareto front. The method enables analyses with different viewpoints from those of the conventional clustering and feature importance analyses by taking the relationship between the target property and the basic features into account.https://doi.org/10.1002/aisy.202400253clusteringinorganic compoundsinterpretable artificial intelligencerandom forest
spellingShingle Nobuya Sato
Akira Takahashi
Shin Kiyohara
Kei Terayama
Ryo Tamura
Fumiyasu Oba
Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds
Advanced Intelligent Systems
clustering
inorganic compounds
interpretable artificial intelligence
random forest
title Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds
title_full Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds
title_fullStr Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds
title_full_unstemmed Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds
title_short Target Material Property‐Dependent Cluster Analysis of Inorganic Compounds
title_sort target material property dependent cluster analysis of inorganic compounds
topic clustering
inorganic compounds
interpretable artificial intelligence
random forest
url https://doi.org/10.1002/aisy.202400253
work_keys_str_mv AT nobuyasato targetmaterialpropertydependentclusteranalysisofinorganiccompounds
AT akiratakahashi targetmaterialpropertydependentclusteranalysisofinorganiccompounds
AT shinkiyohara targetmaterialpropertydependentclusteranalysisofinorganiccompounds
AT keiterayama targetmaterialpropertydependentclusteranalysisofinorganiccompounds
AT ryotamura targetmaterialpropertydependentclusteranalysisofinorganiccompounds
AT fumiyasuoba targetmaterialpropertydependentclusteranalysisofinorganiccompounds