清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Materials discovery and design using machine learning

材料科学 纳米技术 系统工程 建筑工程 工程类
作者
Yue Liu,Tianlu Zhao,Wangwei Ju,Siqi Shi
出处
期刊:Journal of Materiomics [Elsevier BV]
卷期号:3 (3): 159-177 被引量:1043
标识
DOI:10.1016/j.jmat.2017.08.002
摘要

The screening of novel materials with good performance and the modelling of quantitative structure-activity relationships (QSARs), among other issues, are hot topics in the field of materials science. Traditional experiments and computational modelling often consume tremendous time and resources and are limited by their experimental conditions and theoretical foundations. Thus, it is imperative to develop a new method of accelerating the discovery and design process for novel materials. Recently, materials discovery and design using machine learning have been receiving increasing attention and have achieved great improvements in both time efficiency and prediction accuracy. In this review, we first outline the typical mode of and basic procedures for applying machine learning in materials science, and we classify and compare the main algorithms. Then, the current research status is reviewed with regard to applications of machine learning in material property prediction, in new materials discovery and for other purposes. Finally, we discuss problems related to machine learning in materials science, propose possible solutions, and forecast potential directions of future research. By directly combining computational studies with experiments, we hope to provide insight into the parameters that affect the properties of materials, thereby enabling more efficient and target-oriented research on materials discovery and design. Machine learning provides a new means of screening novel materials with good performance, developing quantitative structure-activity relationships (QSARs) and other models, predicting the properties of materials, discovering new materials and performing other materials-relateds studies. • The typical mode of and basic procedures for applying machine learning in materials science are summarized and discussed. • For various points of application, the machine learning methods used for different purposes are comprehensively reviewed. • Existing problems are discussed, possible solutions are proposed and potential directions of future research are suggested.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
情怀应助雪山飞龙采纳,获得10
7秒前
雪山飞龙完成签到,获得积分10
53秒前
六一完成签到 ,获得积分10
1分钟前
失眠的香蕉完成签到 ,获得积分10
1分钟前
1分钟前
超男完成签到 ,获得积分10
1分钟前
南宫士晋完成签到 ,获得积分10
2分钟前
2分钟前
勋出色发布了新的文献求助10
2分钟前
2分钟前
猫猫发布了新的文献求助10
2分钟前
2分钟前
2分钟前
偏偏海完成签到,获得积分10
2分钟前
woxinyouyou完成签到,获得积分0
2分钟前
若眠完成签到 ,获得积分10
2分钟前
Akim应助快中文章啊采纳,获得10
3分钟前
3分钟前
发个15分的完成签到 ,获得积分10
3分钟前
Angenstern完成签到 ,获得积分10
3分钟前
科研通AI2S应助科研通管家采纳,获得10
3分钟前
3分钟前
3分钟前
3分钟前
聪明的云完成签到 ,获得积分10
4分钟前
乐乐应助天真咖啡豆采纳,获得10
4分钟前
4分钟前
4分钟前
5分钟前
秋半梦完成签到,获得积分10
5分钟前
5分钟前
nojego发布了新的文献求助10
5分钟前
fang完成签到,获得积分10
5分钟前
5分钟前
5分钟前
5分钟前
6分钟前
6分钟前
简易完成签到 ,获得积分10
6分钟前
脑洞疼应助天真咖啡豆采纳,获得10
6分钟前
高分求助中
Africanfuturism: African Imaginings of Other Times, Spaces, and Worlds 3000
Electron microscopy study of magnesium hydride (MgH2) for Hydrogen Storage 1000
Exhibiting Chinese Art in Asia: Histories, Politics and Practices 700
1:500万中国海陆及邻区磁力异常图 600
相变热-动力学 520
Elephant Welfare in Global Tourism 500
生物降解型栓塞微球市场(按产品类型、应用和最终用户)- 2030 年全球预测 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3897811
求助须知:如何正确求助?哪些是违规求助? 3441834
关于积分的说明 10823320
捐赠科研通 3166828
什么是DOI,文献DOI怎么找? 1749631
邀请新用户注册赠送积分活动 845385
科研通“疑难数据库(出版商)”最低求助积分说明 788687