|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Recent advances and applications of machine learning in solidstate materials science显示文摘One of the most exciting tools that have entered the material science toolbox in recent years is machine learning.This collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied research.At present,we are witnessing an explosion of works that develop and apply machine learning to solid-state systems.We provide a comprehensive overview and analysis of the most recent research in this topic.As a starting point,we introduce machine learning principles,algorithms,descriptors,and databases in materials science.We continue with the description of different machine learning approaches for the discovery of stable materials and the prediction of their crystal structure.Then we discuss research in numerous quantitative structure–property relationships and various approaches for the replacement of first-principle methods by machine learning.We review how active learning and surrogate-based optimization can be applied to improve the rational design process and related examples of applications.Two major questions are always the interpretability of and the physical understanding gained from machine learning models.We consider therefore the different facets of interpretability and their importance in materials science.Finally,we propose solutions and future research paths for various challenges in computational materials science. | Jonathan Schmidt Mário R.G.Marques Silvana Botti Miguel A.L.Marques | 2019 | npj Computational Materials2019，，1： | 49 |
| 2 | 数据+人工智能是材料基因工程的核心显示文摘材料基因工程的工作模式,可大致总结为实验驱动、计算驱动和数据驱动3种。以"数据+人工智能"为标志的数据驱动模式围绕数据产生与数据处理展开,代表了材料基因工程的核心理念与发展方向。材料研究由"试错法"向科学第四范式的根本转变,将更快、更准、更省地获得成分-结构-工艺-性能间的关系。在数据密集型科学时代,快速获取大量材料数据的能力成为关键,而基于高通量实验与高通量计算的"数据工厂"是满足材料基因工程数据需求的重要平台。 | 汪洪 项晓东 张澜庭 | 2018 | 科技导报2018，36，14： | 23 |
| 3 | 材料领域知识嵌入的机器学习显示文摘数据驱动的机器学习因其能够快速拟合历史数据中的潜在模式并实现材料性能的精准预测,已被广泛应用于材料性能优化和新材料设计。然而,由于缺乏描述符间关联关系、材料性能驱动机制等材料领域知识的指导,数据驱动的机器学习在实际应用中常常出现与材料基础理论认知或原理不一致的结果。本工作通过分析材料数据的特点和数据驱动的机器学习建模原理,厘清了数据驱动的机器学习应用于材料领域面临的三大矛盾:高维度与小样本数据的矛盾、模型准确性与易用性的矛盾、模型学习结果与领域专家知识的矛盾。藉此提出材料领域知识嵌入的机器学习作为上述矛盾的调和策略。进一步,面向“目标定义–数据准备–数据预处理–特征工程–模型构建–模型应用”的机器学习全流程,通过剖析相关的基础性和探索性工作,探讨了在机器学习各阶段实现材料领域知识嵌入的关键技术。最后,展望了材料领域知识嵌入机器学习的发展机遇和挑战。 | 刘悦 邹欣欣 杨正伟 施思齐 | 2022 | 硅酸盐学报2022，50，3： | 18 |
| 4 | Predicting the onset temperature(Tg) of GexSe1-x glass transition: a feature selection based two-stage support vector regression method显示文摘Despite the usage of both experimental and topological methods, realizing a rapid and accurate measurement of the onset temperature(Tg ) of GexSe1-xglass transition remains an open challenge. In this paper, a predictive model for the Tg in GexSe1-xglass system is presented by a machine learning method named feature selection based two-stage support vector regression(FSTS-SVR). Firstly, Pearson correlation coefficient(PCC) is used to select features highly correlated with Tg from the candidate features of GexSe1-x glass system. Secondly, in order to simulate the two-stage characteristic of Tg which is caused by structural variation with a turning point at x = 0.33 via the structural analysis, SVR is utilized to build predictive models for two stages separately and then the two achieved models are synthesized using a minimum error based model for Tg prediction. Compared with the topological and other methods based on SVR, the FSTS-SVR gives the highest predictive accuracy with the root mean square error(RMSE) and mean absolute percentage error(MAPE) of 10.64 K and 2.38%, respectively. This method is also expected to be more efficient for the prediction of Tg of other glass systems with the multi-stage characteristic. | Yue Liu Junming Wu Guang Yang Tianlu Zhao Siqi Shi | 2019 | Science Bulletin2019，64，16： | 12 |
| 5 | 基于高通量计算及机器学习的新材料带隙预测显示文摘在功能材料应用中,带隙往往起着重要的作用,如光电材料一般为宽带隙半导体,而热电材料为窄带隙半导体,因此对指定类别的材料体系带隙进行快速而准确的预测对于功能材料应用具有非常重要的科学意义.然而,通过基于第一性原理的高通量计算获取高精度带隙的方法耗时长,效率低,而实验上系统测量大量材料体系带隙也不现实,所以基于统计学的机器学习预测方法就成了一种有前景的可能性替代方案.本文设计了一种集成学习模型用于有效而准确地预测带隙值.在已计算过带隙值的热电材料类金刚石化合物的基础上,一方面利用单组元组分替换策略产生大批量相似化合物,并用查重技术过滤掉重复体系,得到356个相似材料体系.另一方面结合机器学习技术,构建高效的带隙预测模型,预测并验证了50个相似材料体系的带隙值.通过实验证明,该预测模型具有77.73%的准确率,且足够健壮稳定,可以广泛应用于需要进行大批量带隙预测的热电材料的研究情景中. | 徐永林 王香蒙 李鑫 席丽丽 倪剑樾 朱文浩 张武 杨炯 | 2019 | 中国科学:技术科学2019，49，1： | 10 |
| 6 | 机器学习在材料设计方面的研究进展显示文摘新材料的发现是推动现代科学发展与技术革新的源动力之一,是当前促进经济发展与解决环境问题的迫切需求.传统的材料研发基于试错法,效率低且成本高.大量实验与计算模拟产生的数据为新材料的研发提供了新契机.基于这些数据,机器学习最近在材料性能预测、新材料的发现与设计等领域取得了很大进展.譬如基于材料项目(materials project)数据库对钙钛矿材料的统计分类、结合高通量计算对双钙钛矿卤化物材料稳定性的预测,以及金属间化合物电催化剂的设计与筛选等.除了基于隐式模型的预测,机器学习也可以用来发现具有物理可解释性的显式描述符,从而加速新材料的发现. | 孙中体 李珍珠 程观剑 徐其琛 侯柱锋 尹万健 | 2019 | 科学通报2019，64，32： | 10 |
| 7 | Machine learning:Accelerating materials development for energy storage and conversion显示文摘With the development of modern society,the requirement for energy has become increasingly important on a global scale.Therefore,the exploration of novel materials for renewable energy technologies is urgently needed.Traditional methods are difficult to meet the requirements for materials science due to long experimental period and high cost.Nowadays,machine learning(ML)is rising as a new research paradigm to revolutionize materials discovery.In this review,we briefly introduce the basic procedure of ML and common algorithms in materials science,and particularly focus on latest progress in applying ML to property prediction and materials development for energyrelated fields,including catalysis,batteries,solar cells,and gas capture.Moreover,contributions of ML to experiments are involved as well.We highly expect that this review could lead the way forward in the future development of ML in materials science. | An Chen Xu Zhang Zhen Zhou | 2020 | InfoMat2020，2，3： | 9 |
| 8 | 基于卷积神经网络的钢铁材料微观组织自动辨识显示文摘基于深度学习在计算机视觉上优异的表现,采用深度学习模型对扫描电子显微镜(SEM)所获得的钢铁材料微观组织图片进行自动辨识。提出了适用于钢铁材料微观组织辨识的AlexNet、VggNet、GoogleNet、ResNet改进模型,比较了不同卷积神经网络模型在不同预处理方式下的图片辨识精度,针对从某国家重点实验室收集到的铁素体、珠光体、上贝氏体、下贝氏体、板条马氏体、片状马氏体等6类微观组织图像的数据集进行预测实验,结果表明:与现有技术或人工辨识相比,提出的卷积神经网络能成功辨识不同类型的钢材微观组织,具有较高的适应性和准确度,在测试集上的识别率精度最高可达到100%。 | 李维刚 谌竟成 范丽霞 谢璐 | 2020 | 钢铁研究学报2020，32，1： | 8 |
| 9 | High-throughput experiments facilitate materials innovation:A review显示文摘Since the Material Genome Initiative(MGI) was proposed, high-throughput based technology has been widely employed in various fields of materials science. As a theoretical guide, material informatics has been introduced based on machine learning and data mining and high-throughput computation has been employed for large scale search, narrowing down the scope of the experiment trials. High-throughput materials experiments including synthesis, processing, and characterization technologies have become valuable research tools to pin down the prediction experimentally, enabling the discovery-to-deployment of advances materials more efficiently at a fraction of cost. This review aims to summarize the recent advances of high-throughput materials experiments and introduce briefly the development of materials design based on material genome concept. By selecting representative and classic works in the past years, various high-throughput preparation methods are introduced for different types of material gradient libraries, including metallic, inorganic materials, and polymers. Furthermore, high-throughput characterization approaches are comprehensively discussed, including both their advantages and limitations. Specifically, we focus on high-throughput mass spectrometry to analyze its current status and challenges in the application of catalysts screening. | LIU Yi Hao HU ZiHeng SUO ZhiGuang HU LianZhe FENG LingYan GONG XiuQing LIU Yi ZHANG JinCang | 2019 | Science China(Technological Sciences)2019，62，4： | 7 |
| 10 | Benchmarking materials property prediction methods:the Matbench test set and Automatminer reference algorithm显示文摘We present a benchmark test suite and an automated machine learning procedure for evaluating supervised machine learning(ML)models for predicting properties of inorganic bulk materials.The test suite,Matbench,is a set of 13 ML tasks that range in size from 312 to 132k samples and contain data from 10 density functional theory-derived and experimental sources. | Alexander Dunn Qi Wang Alex Ganose Daniel Dopp Anubhav Jain | 2020 | npj Computational Materials2020，，1： | 7 |
| 11 | 数据驱动的机器学习在电化学储能材料研究中的应用显示文摘储能电池的关键是材料。继实验观测、理论研究和计算模拟之后,数据驱动的机器学习具有快速捕捉材料成分-结构-工艺-性能间复杂构效关系的优势,有望为电化学储能材料的研发提供新的范式。本文从结构化和非结构化数据驱动两方面,系统评述了机器学习在电化学储能材料研究中的最新进展。全面概括了可用于电化学储能材料机器学习的国内外材料数据库,分析了其数据的收集、共享和质量检测存在的问题;重点阐述了电化学储能材料中机器学习的工作流程和应用,包括结构化数据驱动下数据收集、特征工程和机器学习建模以及图形、表征图像和文献文本这类非结构化数据驱动下的模型构建和应用。进一步,厘清电化学储能材料领域机器学习面临的三大矛盾且给出对策,即高维度与小样本数据的矛盾与协调、模型复杂性与易用性的矛盾与统一、模型学习结果与专家经验的矛盾与融合,并提出构建“领域知识嵌入的机器学习方法”有望调和这些矛盾。本文将为机器学习在电化学储能材料设计和性能优化中的应用提供参考。 | 施思齐 涂章伟 邹欣欣 孙拾雨 杨正伟 刘悦 | 2022 | 储能科学与技术2022，11，3： | 7 |
| 12 | A living foundry for Synthetic Biological Materials:A synthetic biology roadmap to new advanced materials显示文摘Society is on the cusp of harnessing recent advances in synthetic biology to discover new bio-based products and routes to their affordable and sustainable manufacture.This is no more evident than in the discovery and manufacture of Synthetic Biological Materials,where synthetic biology has the capacity to usher in a new Materials from Biology era that will revolutionise the discovery and manufacture of innovative synthetic biological materials.These will encompass novel,smart,functionalised and hybrid materials for diverse applications whose discovery and routes to bio-production will be stimulated by the fusion of new technologies positioned across physical,digital and biological spheres.This article,which developed from an international workshop held in Manchester,United Kingdom,in 2017[1],sets out to identify opportunities in the new materials from biology era.It considers requirements,early understanding and foresight of the challenges faced in delivering a Discovery to Manufacturing Pipeline for synthetic biological materials using synthetic biology approaches.This challenge spans the complete production cycle from intelligent and predictive design,fabrication,evaluation and production of synthetic biological materials to new ways of bringing these products to market.Pathway opportunities are identified that will help foster expertise sharing and infrastructure development to accelerate the delivery of a new generation of synthetic biological materials and the leveraging of existing investments in synthetic biology and advanced materials research to achieve this goal. | Rosalind A.Le Feuvre Nigel S.Scrutton | 2018 | Synthetic and Systems Biotechnology2018，3，2： | 6 |
| 13 | 基于分层编码晶体结构(HECS)描述符的机器学习预测立方相锂-硫银锗矿电解质材料的激活能显示文摘合理设计高离子电导率和低活化能(Ea)的固态电解质(SSEs)对全固态电池至关重要.近年来,基于各种描述符的机器学习技术成功地预测了锂离子在SSEs中的传导特性.本文建立了一个通用的基于HECS描述符的机器学习预测无机SSEs材料Ea的框架,并且以立方相锂-硫银锗矿型SSEs材料作为模型体系进行实例研究,采用偏最小二乘方法(PLS)建立了高精度(训练集:R^(2),88.7%;RMSE,0.02 e V;测试集:R^(2),82.0%;RMSE,0.02 e V)预测E_(a)的模型.变量投影重要性(VIP)分析表明了全局及局域离子传导环境对E_(a)的联合作用,其中平均阴离子尺寸以及与阴离子位置无序密切相关的结构的改变对激活能值的贡献尤为突出,这一发现有助于进一步指导发现或设计新的无机固态电解质材料.同时,对该模型进行的知识提取表明,可以通过增大瓶颈尺寸、引发阴离子位置无序、激活离子协同迁移等优化和设计出具有高离子传导性能的新的无机固态电解质材料. | 赵倩 Maxim Avdeev 陈立泉 施思齐 | 2021 | Science Bulletin2021，66，14： | 5 |
| 14 | 人工智能在复合材料研究中的应用显示文摘复合材料以其轻质高强高模、可设计性强等优点成为结构轻量化的重要用材.然而,随着复合材料组分、结构以及性能需求的日益复杂化,以实验观测、理论建模和数值模拟为主体的传统研究范式,在复合材料力学性能分析、设计和制造等方面遇到了新的科学问题与技术瓶颈.其中,实验观测不足、理论模型缺乏、数值分析受限、结果验证困难等问题在一定程度上制约了先进复合材料在面向未来工程领域中应用的发展.人工智能方法以数据驱动的模型替代传统研究中的数学力学模型,直接由高维高通量数据建立变量间的复杂关系,捕捉传统力学研究方法难以发现的规律,在复杂系统的分析、预测、优化方面拥有与生俱来的优势.而通过人工智能赋能来寻求复合材料中传统研究方法所面临难题的新的解决方案,目前已成为复合材料研究领域的发展趋势.本文综述并评价了人工智能方法在复合材料性能预测、优化设计、制造检测及健康监测等方面的研究进展,并对未来发展方向进行了探讨和展望. | 张峻铭 杨伟东 李岩 | 2021 | 力学进展2021，51，4： | 5 |
| 15 | Discovering unusual structures from exception using big data and machine learning techniques显示文摘Recently, machine learning(ML) has become a widely used technique in materials science study. Most work focuses on predicting the rule and overall trend by building a machine learning model. However,new insights are often learnt from exceptions against the overall trend. In this work, we demonstrate that how unusual structures are discovered from exceptions when machine learning is used to get the relationship between atomic and electronic structures based on big data from high-throughput calculation database. For example, after training an ML model for the relationship between atomic and electronic structures of crystals, we find AgO2 F, an unusual structure with both Ag3+and O22à, from structures whose band gap deviates much from the prediction made by our model. A further investigation on this structure might shed light into the research on anionic redox in transition metal oxides of Li-ion batteries. | Jianshu Jie Zongxiang Hu Guoyu Qian Mouyi Weng Shunning Li Shucheng Li Mingyu Hu Dong Chen Weiji Xiao Jiaxin Zheng Lin-Wang Wang Feng Pan | 2019 | Science Bulletin2019，64，9： | 5 |
| 16 | JAMIP:面向材料基因工程研究的功能材料设计开源软件显示文摘材料信息学或材料基因工程作为新兴的材料研究与设计范式,通过深度结合材料大数据与人工智能机器学习算法,正在加速新材料、新功能和新原则的创新发现.如何高效产生、收集、管理、学习和挖掘大规模材料数据是开展材料信息学或材料基因工程研究的关键.JAMIP(Jilin Artificial-intelligence-aided Materials-design Integrated Package)材料设计软件为满足这方面的研究需求而设计,涵盖半导体材料、介电材料、金属材料等材料体系,为基于功能材料大数据与机器学习算法结合的新材料发现和设计提供工具支撑.软件基于Python语言开发,代码开源,既可以基于结构原型数据库高效开展大规模高通量材料计算,也可以实现对计算任务更精细的控制及新任务流程的灵活定制.软件包主体框架包含以高通量材料计算为核心的数据产生、数据收集、管理工具及数据存储、机器学习/数据挖掘等功能模块.机器学习模块集成了数据预处理、数据特征工程,以及常用机器学习算法的模型构建和性能评估子模块.软件各模块之间高度融合,能够高效产生、分析、管理和学习计算材料大数据,为开展材料信息学或材料基因工程研究、实现新材料设计提供专业化的操作软件平台. | 赵信刚 周琨 邢邦昱 赵若廷 罗树林 李天姝 孙远慧 那广仁 颉家豪 杨晓雨 王新江 王啸宇 贺欣 吕健 付钰豪 张立军 | 2021 | Science Bulletin2021，66，19： | 4 |
| 17 | Magnetic and superconducting phase diagrams and transition temperatures predicted using text mining and machine learning显示文摘Predicting the properties of materials prior to their synthesis is of great importance in materials science.Magnetic and superconducting materials exhibit a number of unique properties that make them useful in a wide variety of applications,including solid oxide fuel cells,solid-state refrigerants,photon detectors and metrology devices.In all these applications,phase transitions play an important role in determining the feasibility of the materials in question.Here,we present a pipeline for fully integrating data extracted from the scientific literature into machine-learning tools for property prediction and materials discovery.Using advanced natural language processing(NLP)and machine-learning techniques,we successfully reconstruct the phase diagrams of well-known magnetic and superconducting compounds,and demonstrate that it is possible to predict the phase-transition temperatures of compounds not present in the database.We provide the tool as an online open-source platform,forming the basis for further research into magnetic and superconducting materials discovery for potential device applications. | Callum J.Court Jacqueline M.Cole | 2020 | npj Computational Materials2020，，1： | 4 |
| 18 | Machine learning for perovskite materials design and discovery显示文摘The development of materials is one of the driving forces to accelerate modern scientific progress and technological innovation.Machine learning(ML)technology is rapidly developed in many fields and opening blueprints for the discovery and rational design of materials.In this review,we retrospected the latest applications of ML in assisting perovskites discovery.First,the development tendency of ML in perovskite materials publications in recent years was organized and analyzed.Second,the workflow of ML in perovskites discovery was introduced.Then the applications of ML in various properties of inorganic perovskites,hybrid organic–inorganic perovskites and double perovskites were briefly reviewed.In the end,we put forward suggestions on the future development prospects of ML in the field of perovskite materials. | Qiuling Tao Pengcheng Xu Minjie Li Wencong Lu | 2021 | npj Computational Materials2021，，1： | 4 |
| 19 | A new MaterialGo database and its comparison with other high-throughput electronic structure databases for their predicted energy band gaps显示文摘Recently, many high-throughput calculation materials databases have been constructed and found wide applications. However, a database is only useful if its content is reliable and sufficiently accurate. It is thus of paramount importance to gauge the reliabilities and accuracies of these databases. Although many properties have been predicted accurately in these databases,electronic band gap is well known to be underestimated by traditional density functional theory(DFT) calculations under local density approximation(LDA), which becomes a challenging problem for materials database building. Here, we introduce MaterialGo(http://gffzz077c307637e74fb9hbxk9ck56oupx6xu6.ffgz.tsg.suse.edu.cn/data-base.html), a new database calculating the band structures of crystals using both Perdew-Burke-Ernzerhof(PBE) exchange-correlation functional and Heyd-Scuseria-Ernzerhof(HSE) hybrid functional.Comparing different PBE databases, it is found that their band gaps are consistent when no U parameter is used for transition metal d-state or heavy element f-state to correct their self-interaction error, but rather different when PBE+U are used, mostly because of the different values of U used in different database. HSE calculations under standard parameters will give larger band gaps that are closer to experiment. Based on the high-throughput HSE calculations over 10000 crystal structures, we might have a better understanding of the relationship between crystal structures and electronic structures, which will help us to further explore material genome science and engineering. | JIE JianShu WENG MouYi LI ShunNing CHEN Dong LI ShuCheng XIAO WeiJi ZHENG JiaXin PAN Feng Wang LinWang | 2019 | Science China(Technological Sciences)2019，62，8： | 4 |
| 20 | An infrastructure with user-centered presentation data model for integrated management of materials data and services显示文摘With scientific research in materials science becoming more data intensive and collaborative after the announcement of the Materials Genome Initiative,the need for modern data infrastructures that facilitate the sharing of materials data and analysis tools is compelling in the materials community.In this paper,we describe the challenges of developing such infrastructure and introduce an emerging architecture with high usability.We call this architecture the Materials Genome Engineering Databases(MGED).MGED provides cloud-hosted services with features to simplify the process of collecting datasets from diverse data providers,unify data representation forms with user-centered presentation data model,and accelerate data discovery with advanced search capabilities.MGED also provides a standard service management framework to enable finding and sharing of tools for analyzing and processing data.We describe MGED’s design,current status,and how MGED supports integrated management of shared data and services. | Shilong Liu Yanjing Su Haiqing Yin Dawei Zhang Jie He Haiyou Huang Xue Jiang Xuan Wang Haiyan Gong Zhuang Li Hao Xiu Jiawang Wan Xiaotong Zhang | 2021 | npj Computational Materials2021，，1： | 4 |
您所在的机构暂未开通此部分的功能，请联系管理员