Zhang Yan , Gao Fei , Cui Guofeng , Kuang Yafei , Zong Shutong , Chen Fenghua , Liu Hongxia , Sun Zhigang , Shen Baogen
{"title":"Machine learning of heavy rare earth-based low-temperature magnetocaloric materials under complex classification methods","authors":"Zhang Yan , Gao Fei , Cui Guofeng , Kuang Yafei , Zong Shutong , Chen Fenghua , Liu Hongxia , Sun Zhigang , Shen Baogen","doi":"10.1016/j.jmmm.2025.173180","DOIUrl":null,"url":null,"abstract":"<div><div>Low-temperature magnetic refrigeration materials have important application value in the fields of aerospace, military defense, medical and health care, and low-temperature physics. Compared with the “stir-fry” material R&D model, machine learning can accelerate the data analysis and R&D of new materials. However, at present, the research on machine learning is limited to the simulation and prediction of a single type of material, and the research object is mainly focused on materials with high phase transition temperature. Obviously, the generalizability of this kind of research is low. In order to solve the above scientific problems, this paper uses the gradient boosted regression tree (GBRT) model to train the dataset of heavy rare earth-based alloys under different classification methods, taking the chemical composition as the characteristic attributes, and the Curie temperature and maximum magnetic entropy as the target attributes. It was found that the performance of heavy rare earth-based alloys was different under different classification methods. The prediction of Curie temperature under each classification method is very good, but the prediction effect of magnetic entropy change with non-intrinsic properties is completely different. Among them, the prediction effect of magnetic entropy change of the whole dataset is poor,and the training results of the hexagonal structure and ternary alloys dataset are excellent. The correlation coefficient (R<sup>2</sup>) of the hexagonal structure on the training set and the test set is 0.99 and 0.77, respectively. The fitting results for the ternary alloys also reached 0.97 and 0.80, respectively. However, the orthogonal structure and binary structure datasets performed extremely poor, and the R<sup>2</sup> value of the test set was only 0.31 and 0.17, respectively. For the first time, we obtained the good prediction results of magnetocaloric effect materials under complex classification methods through the GBRT machine learning model, and revealed the influence of different classification methods on the target and feature attributes of the dataset from the physical level. These results are helpful to accelerate the development of low-temperature magnetocaloric materials.</div></div>","PeriodicalId":366,"journal":{"name":"Journal of Magnetism and Magnetic Materials","volume":"628 ","pages":"Article 173180"},"PeriodicalIF":2.5000,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Magnetism and Magnetic Materials","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0304885325004123","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Low-temperature magnetic refrigeration materials have important application value in the fields of aerospace, military defense, medical and health care, and low-temperature physics. Compared with the “stir-fry” material R&D model, machine learning can accelerate the data analysis and R&D of new materials. However, at present, the research on machine learning is limited to the simulation and prediction of a single type of material, and the research object is mainly focused on materials with high phase transition temperature. Obviously, the generalizability of this kind of research is low. In order to solve the above scientific problems, this paper uses the gradient boosted regression tree (GBRT) model to train the dataset of heavy rare earth-based alloys under different classification methods, taking the chemical composition as the characteristic attributes, and the Curie temperature and maximum magnetic entropy as the target attributes. It was found that the performance of heavy rare earth-based alloys was different under different classification methods. The prediction of Curie temperature under each classification method is very good, but the prediction effect of magnetic entropy change with non-intrinsic properties is completely different. Among them, the prediction effect of magnetic entropy change of the whole dataset is poor,and the training results of the hexagonal structure and ternary alloys dataset are excellent. The correlation coefficient (R2) of the hexagonal structure on the training set and the test set is 0.99 and 0.77, respectively. The fitting results for the ternary alloys also reached 0.97 and 0.80, respectively. However, the orthogonal structure and binary structure datasets performed extremely poor, and the R2 value of the test set was only 0.31 and 0.17, respectively. For the first time, we obtained the good prediction results of magnetocaloric effect materials under complex classification methods through the GBRT machine learning model, and revealed the influence of different classification methods on the target and feature attributes of the dataset from the physical level. These results are helpful to accelerate the development of low-temperature magnetocaloric materials.
期刊介绍:
The Journal of Magnetism and Magnetic Materials provides an important forum for the disclosure and discussion of original contributions covering the whole spectrum of topics, from basic magnetism to the technology and applications of magnetic materials. The journal encourages greater interaction between the basic and applied sub-disciplines of magnetism with comprehensive review articles, in addition to full-length contributions. In addition, other categories of contributions are welcome, including Critical Focused issues, Current Perspectives and Outreach to the General Public.
Main Categories:
Full-length articles:
Technically original research documents that report results of value to the communities that comprise the journal audience. The link between chemical, structural and microstructural properties on the one hand and magnetic properties on the other hand are encouraged.
In addition to general topics covering all areas of magnetism and magnetic materials, the full-length articles also include three sub-sections, focusing on Nanomagnetism, Spintronics and Applications.
The sub-section on Nanomagnetism contains articles on magnetic nanoparticles, nanowires, thin films, 2D materials and other nanoscale magnetic materials and their applications.
The sub-section on Spintronics contains articles on magnetoresistance, magnetoimpedance, magneto-optical phenomena, Micro-Electro-Mechanical Systems (MEMS), and other topics related to spin current control and magneto-transport phenomena. The sub-section on Applications display papers that focus on applications of magnetic materials. The applications need to show a connection to magnetism.
Review articles:
Review articles organize, clarify, and summarize existing major works in the areas covered by the Journal and provide comprehensive citations to the full spectrum of relevant literature.