Automating selective area electron diffraction phase identification using machine learning

作     者：M.Mika N.Tomczak C.Finney J.Carter A.Aitkaliyeva 

作者机构：Nuclear Engineering Program in Department of Materials ScienceUniversity of Florida100 Rhines HallGainesville32611FLUSA Department of Materials Science&EngineeringCase Western Reserve University2111 Martin Luther King Jr DrCleveland44106OHUSA 

出 版 物：《Journal of Materiomics》 (无机材料学学报（英文）)

年 卷 期：2024年第10卷第4期

页      面：896-905页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The funding for this work was provided by the U.S.Department of Energy,Office of Nuclear Energy Contract DEAC07-051D14517 The CNN work was partially supported by the National Science Foundation(award number 1552716) 

主　　题：Selective area electron diffraction Machine learning Phase identification Metallic fuels Pu alloys 

摘      要：Selective area electron diffraction(SAED)patterns can provide valuable insight into the structure of a ***,the manual identification of collected patterns can be a significant bottleneck in the overall phase classification *** this work,we utilize the recent advances in computer vision and machine learning(ML)to automate the indexing of SAED *** performance of six different ML algorithms is demonstrated using metallic plutonium-zirconium *** most successful approach trained a neural network(NN)to make a classification of the phase and zone axis,and then utilized a second NN to synthesize multiple independent predictions of different tilts in a single sample to make an overall phase *** results demonstrate that automated SAED phase identification using ML is a viable route to accelerate materials characterization.