{"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}
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.