在材料工程中使用机器学习的自动化设计-一个明确的预测

Birgir Guomundsson, Gunnar Lorna
{"title":"在材料工程中使用机器学习的自动化设计-一个明确的预测","authors":"Birgir Guomundsson, Gunnar Lorna","doi":"10.53759/832x/jcims202301006","DOIUrl":null,"url":null,"abstract":"Every discipline of physics, including materials science, has been profoundly influenced by the arrival of\nalgorithmic breakthroughs in the domain of machine learning. Many important advances have been made by combining\nmaterials data (computed and measured) with different machine learning approaches to solve difficult problems like,\ncreating effectual and extrapolative surrogate prototypes for a wide variety of material parameters, down-selecting and\nscreening novel candidate materials for particular application, and structuring novel approaches to accelerate and enhance\natomistic and molecular simulations. Although current implementations have shown some of the promise of data-enabled\npathways, it has become evident that success in this area will depend on our capacity to interpret, explain, and justify the\nresults of a machine learning approach on the basis of our professional knowledge in the field. This article reviews the\nmost important machine learning applications in materials engineering. In addition, we present a short overview of a\nnumber of methods that have proven useful in deriving physically relevant insights, design-centric knowledge, and causal\nlinks from materials engineering. Last but not least, we highlight some of the next prospects and obstacles that the\nmaterials community will encounter in this dynamic and fast developing industry.","PeriodicalId":240206,"journal":{"name":"Journal of Computational Intelligence in Materials Science","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automated Design Using Machine Learning in Materials Engineering - An Explicit Forecasts\",\"authors\":\"Birgir Guomundsson, Gunnar Lorna\",\"doi\":\"10.53759/832x/jcims202301006\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Every discipline of physics, including materials science, has been profoundly influenced by the arrival of\\nalgorithmic breakthroughs in the domain of machine learning. Many important advances have been made by combining\\nmaterials data (computed and measured) with different machine learning approaches to solve difficult problems like,\\ncreating effectual and extrapolative surrogate prototypes for a wide variety of material parameters, down-selecting and\\nscreening novel candidate materials for particular application, and structuring novel approaches to accelerate and enhance\\natomistic and molecular simulations. Although current implementations have shown some of the promise of data-enabled\\npathways, it has become evident that success in this area will depend on our capacity to interpret, explain, and justify the\\nresults of a machine learning approach on the basis of our professional knowledge in the field. This article reviews the\\nmost important machine learning applications in materials engineering. In addition, we present a short overview of a\\nnumber of methods that have proven useful in deriving physically relevant insights, design-centric knowledge, and causal\\nlinks from materials engineering. Last but not least, we highlight some of the next prospects and obstacles that the\\nmaterials community will encounter in this dynamic and fast developing industry.\",\"PeriodicalId\":240206,\"journal\":{\"name\":\"Journal of Computational Intelligence in Materials Science\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Computational Intelligence in Materials Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.53759/832x/jcims202301006\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Computational Intelligence in Materials Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.53759/832x/jcims202301006","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

物理的每一门学科,包括材料科学,都受到机器学习领域算法突破的深刻影响。通过将材料数据(计算和测量)与不同的机器学习方法相结合来解决难题,例如,为各种材料参数创建有效和外推的替代原型,为特定应用选择和筛选新的候选材料,以及构建新的方法来加速和增强原子和分子模拟,已经取得了许多重要的进展。尽管目前的实现已经显示出数据支持路径的一些前景,但很明显,这一领域的成功将取决于我们在该领域的专业知识基础上解释、解释和证明机器学习方法结果的能力。本文综述了机器学习在材料工程中最重要的应用。此外,我们还简要介绍了一些方法,这些方法已被证明可以从材料工程中获得物理相关的见解、以设计为中心的知识和因果关系。最后但并非最不重要的是,我们强调了材料界在这个充满活力和快速发展的行业中将遇到的一些下一个前景和障碍。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automated Design Using Machine Learning in Materials Engineering - An Explicit Forecasts
Every discipline of physics, including materials science, has been profoundly influenced by the arrival of algorithmic breakthroughs in the domain of machine learning. Many important advances have been made by combining materials data (computed and measured) with different machine learning approaches to solve difficult problems like, creating effectual and extrapolative surrogate prototypes for a wide variety of material parameters, down-selecting and screening novel candidate materials for particular application, and structuring novel approaches to accelerate and enhance atomistic and molecular simulations. Although current implementations have shown some of the promise of data-enabled pathways, it has become evident that success in this area will depend on our capacity to interpret, explain, and justify the results of a machine learning approach on the basis of our professional knowledge in the field. This article reviews the most important machine learning applications in materials engineering. In addition, we present a short overview of a number of methods that have proven useful in deriving physically relevant insights, design-centric knowledge, and causal links from materials engineering. Last but not least, we highlight some of the next prospects and obstacles that the materials community will encounter in this dynamic and fast developing industry.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信