Query-and-Learn Machine Learning framework to model the stability mechanism of REFe12 magnets

用于模拟 REFe12 磁体稳定性机制的查询和学习机器学习框架

• 批准号: 21K14396
• 负责人: NGUYEN DuongNguyen
• 金额: $ 2.83万
• 依托单位: Japan Advanced Institute of Science and Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Early-Career Scientists
• 财政年份: 2021
• 资助国家: 日本
• 起止时间: 2021-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-21K14396/
• 关键词: materials discovery; rare-earths magnets; evidence-based theory; active learning; SmFe12; materials exploration; REFe12 magnets

The research project has been process with three main achievements:(1) develop an active learning framework in investigating the structure-stability of SmFe12 family magnets (published in MRS Bulletin Impact). (2) develop an Evidence-based similarity measure for materials science data (published in J. Appl. Phys.) (3) develop a Machine Learning-aided Genetic algorithm to investigate the stability SmFe12 based magnets (published in J. Appl. Phys.)From data contribution aspect, published articles in (1) and (3) provided systematic quantum calculation datasets for SmFe12 magnets and framework for higher efficiency data calculation. From theoretical contribution aspect, article in (2) investigated a new method bridging between Dempster theory of evidence to investigate materials science data.

该研究项目已经取得了三个主要成就：（1）在研究SMFE12家族磁铁的结构稳定性（发表在MRS Bulletin Impact中）时，开发了一个积极的学习框架。 （2）制定了针对材料科学数据的基于证据的相似性度量（J.Appl。Phys。发表）（3）开发一种机器学习辅助遗传算法，以研究基于稳定性SMFE12的磁铁（在J.Appl。Phys。发表在J.Appl。Phys。中），从数据贡献方面，在（1）和（3）提供了SMEFE12的系统量定计算量的范围范围内（1）和（3）提供了SMFE12的范围。从理论贡献方面来看，（2）中的文章调查了一种新的方法，在研究材料科学数据的证据理论之间桥接了。

项目成果

Deep attention model for extracting material structure-property relationships

用于提取材料结构-性质关系的深度注意力模型

• 发表时间: 2021
• 作者: Vu Tien-Sinh;DINH Duy Tai;NGUYEN Duong Nguyen;DAM Hieu Chi
• 通讯作者: DAM Hieu Chi

Elucidating atomic-scale phenomena with transmission electron microscopy: a study of gold nanocontact

用透射电子显微镜阐明原子尺度现象：金纳米接触的研究

• 发表时间: 2021
• 作者: Dao Duc-Anh;NGUYEN Duong Nguyen;DAM Hieu Chi
• 通讯作者: DAM Hieu Chi

Query-and-learn Based Active Learning Framework for Screening New SmFe12 Structures

基于查询和学习的主动学习框架用于筛选新的 SmFe12 结构

• 发表时间: 2023
• 作者: Duong-Nguyen NGUYEN;Hieu-Chi DAM
• 通讯作者: Hieu-Chi DAM

Explainable active learning to investigate the structure-stability of SmFe12-a-BX a Y structures X, Y = {Mo, n, Co, Cu, Ti, Al, Ga}

可解释的主动学习研究 SmFe12-a-BX a Y 结构的结构稳定性 X, Y = {Mo, n, Co, Cu, Ti, Al, Ga}

• 发表时间: 2021
• 作者: NGUYEN Duong Nguyen;DAM Hieu Chi
• 通讯作者: DAM Hieu Chi

Evidence-based data mining method to reveal similarities between materials based on physical mechanisms

基于证据的数据挖掘方法，根据物理机制揭示材料之间的相似性

• DOI: 10.1063/5.0134999
• 发表时间: 2023
• 期刊: Journal of Applied Physics
• 影响因子: 3.2
• 作者: Ha Minh-Quyet;Nguyen Duong-Nguyen;Nguyen Viet-Cuong;Kino Hiori;Ando Yasunobu;Miyake Takashi;Deneux Thierry;Huynh Van-Nam;Dam Hieu-Chi
• 通讯作者: Dam Hieu-Chi