Robust activation energy predictions of solute diffusion from machine learning method
文献类型:期刊论文
作者 | He, Kang-ni1,2; Kong, Xiang-shan2,3; Liu, C. S.2 |
刊名 | COMPUTATIONAL MATERIALS SCIENCE |
出版日期 | 2020-11-01 |
卷号 | 184 |
ISSN号 | 0927-0256 |
关键词 | Diffusion Activation energy Machine learning Support vector machine |
DOI | 10.1016/j.commatsci.2020.109948 |
通讯作者 | Kong, Xiang-shan(xskong@sdu.edu.cn) ; Liu, C. S.(csliu@issp.ac.cn) |
英文摘要 | We evaluate the performance of a popular machine learning (ML) method support vector machine (SVM) for modeling and predicting the solute diffusion activation energies in fcc, bcc, and hcp metallic hosts. The diffusion activation energies of 408 host-solute systems from ab-initio calculations are made as our dataset. We obtain an optimal set of features by combining prior physics knowledge and combination ranking based on the LeaveGroup-Out (LOG) cross-validation (CV) method, including solute migration barrier, atomic volume of host, elastic modulus of host, melting point of host, unpaired d electrons of host, and the corresponding parameters of solute. We present the results of LOG/10-fold/5-fold/3-fold CV, with the corresponding root mean squared error (RMSE) of 0.128/0.106 +/- 0.014/0.107 +/- 0.004/0.110 +/- 0.005 eV. SVM gives an about 0.1 eV errors when extrapolating to new host-solute systems for main hosts. We further make predictions on the activation energies of thousands of new systems with quite small computational cost. Our work demonstrates that the ML method is a promising method to accelerate materials science researches. |
WOS关键词 | TRANSITION-METAL SOLUTES ; IMPURITY DIFFUSIVITIES ; STAINLESS-STEEL ; FCC ; 1ST-PRINCIPLES ; COEFFICIENTS ; DATABASE |
资助项目 | National Key Research and Development Program of China[2018YFE0308102] ; National Natural Science Foundation of China[11735015] ; National Natural Science Foundation of China[51771185] |
WOS研究方向 | Materials Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000566888800001 |
资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/104072] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Kong, Xiang-shan; Liu, C. S. |
作者单位 | 1.Univ Sci & Technol China, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Solid State Phys, Key Lab Mat Phys, POB 1129, Hefei 230031, Peoples R China 3.Shandong Univ, Minist Educ, Key Lab Liquid Solid Struct Evolut & Proc Mat, Jinan 250061, Shandong, Peoples R China |
推荐引用方式 GB/T 7714 | He, Kang-ni,Kong, Xiang-shan,Liu, C. S.. Robust activation energy predictions of solute diffusion from machine learning method[J]. COMPUTATIONAL MATERIALS SCIENCE,2020,184. |
APA | He, Kang-ni,Kong, Xiang-shan,&Liu, C. S..(2020).Robust activation energy predictions of solute diffusion from machine learning method.COMPUTATIONAL MATERIALS SCIENCE,184. |
MLA | He, Kang-ni,et al."Robust activation energy predictions of solute diffusion from machine learning method".COMPUTATIONAL MATERIALS SCIENCE 184(2020). |
入库方式: OAI收割
来源:合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。