Magnetization in iron based compounds: A machine learning model analysis
In material science domain, the data availability has made it possible to design and test machine learning models not only to strengthen our understanding of various properties of materials but also to give predictive capabilities through finding trends and patterns. Here, we report the insight into...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2023-02-01
|
Series: | AIP Advances |
Online Access: | http://dx.doi.org/10.1063/9.0000498 |
_version_ | 1811154866680102912 |
---|---|
author | Yogesh Khatri Rajesh Sharma Ashutosh Shah Arti Kashyap |
author_facet | Yogesh Khatri Rajesh Sharma Ashutosh Shah Arti Kashyap |
author_sort | Yogesh Khatri |
collection | DOAJ |
description | In material science domain, the data availability has made it possible to design and test machine learning models not only to strengthen our understanding of various properties of materials but also to give predictive capabilities through finding trends and patterns. Here, we report the insight into magnetization of Iron based compounds using the machine learning model and by doing the model interpretability analysis using SHapley Additive exPlanations. Most of the Iron based compounds are magnetic in nature and are well studied with abundant data available in different repositories. We have used data from Materials Project. |
first_indexed | 2024-04-10T04:24:22Z |
format | Article |
id | doaj.art-e1f9a3f32dfe444591d80d888af07f9a |
institution | Directory Open Access Journal |
issn | 2158-3226 |
language | English |
last_indexed | 2024-04-10T04:24:22Z |
publishDate | 2023-02-01 |
publisher | AIP Publishing LLC |
record_format | Article |
series | AIP Advances |
spelling | doaj.art-e1f9a3f32dfe444591d80d888af07f9a2023-03-10T17:26:21ZengAIP Publishing LLCAIP Advances2158-32262023-02-01132025318025318-610.1063/9.0000498Magnetization in iron based compounds: A machine learning model analysisYogesh Khatri0Rajesh Sharma1Ashutosh Shah2Arti Kashyap3Indian Institute of Technology Mandi, Kamand, Mandi, HP 175005, IndiaIndian Institute of Technology Mandi, Kamand, Mandi, HP 175005, IndiaIndian Institute of Technology Mandi, Kamand, Mandi, HP 175005, IndiaIndian Institute of Technology Mandi, Kamand, Mandi, HP 175005, IndiaIn material science domain, the data availability has made it possible to design and test machine learning models not only to strengthen our understanding of various properties of materials but also to give predictive capabilities through finding trends and patterns. Here, we report the insight into magnetization of Iron based compounds using the machine learning model and by doing the model interpretability analysis using SHapley Additive exPlanations. Most of the Iron based compounds are magnetic in nature and are well studied with abundant data available in different repositories. We have used data from Materials Project.http://dx.doi.org/10.1063/9.0000498 |
spellingShingle | Yogesh Khatri Rajesh Sharma Ashutosh Shah Arti Kashyap Magnetization in iron based compounds: A machine learning model analysis AIP Advances |
title | Magnetization in iron based compounds: A machine learning model analysis |
title_full | Magnetization in iron based compounds: A machine learning model analysis |
title_fullStr | Magnetization in iron based compounds: A machine learning model analysis |
title_full_unstemmed | Magnetization in iron based compounds: A machine learning model analysis |
title_short | Magnetization in iron based compounds: A machine learning model analysis |
title_sort | magnetization in iron based compounds a machine learning model analysis |
url | http://dx.doi.org/10.1063/9.0000498 |
work_keys_str_mv | AT yogeshkhatri magnetizationinironbasedcompoundsamachinelearningmodelanalysis AT rajeshsharma magnetizationinironbasedcompoundsamachinelearningmodelanalysis AT ashutoshshah magnetizationinironbasedcompoundsamachinelearningmodelanalysis AT artikashyap magnetizationinironbasedcompoundsamachinelearningmodelanalysis |