Kusne A G, Keller D, Anderson A, Zaban A, Takeuchi I
Materials Measurement Science Division, National Institute of Standards and Technology, Gaithersburg, MD 20899, USA.
Nanotechnology. 2015 Nov 6;26(44):444002. doi: 10.1088/0957-4484/26/44/444002. Epub 2015 Oct 15.
Advances in high-throughput materials fabrication and characterization techniques have resulted in faster rates of data collection and rapidly growing volumes of experimental data. To convert this mass of information into actionable knowledge of material process-structure-property relationships requires high-throughput data analysis techniques. This work explores the use of the Graph-based endmember extraction and labeling (GRENDEL) algorithm as a high-throughput method for analyzing structural data from combinatorial libraries, specifically, to determine phase diagrams and constituent phases from both x-ray diffraction and Raman spectral data. The GRENDEL algorithm utilizes a set of physical constraints to optimize results and provides a framework by which additional physics-based constraints can be easily incorporated. GRENDEL also permits the integration of database data as shown by the use of critically evaluated data from the Inorganic Crystal Structure Database in the x-ray diffraction data analysis. Also the Sunburst radial tree map is demonstrated as a tool to visualize material structure-property relationships found through graph based analysis.
高通量材料制造和表征技术的进步使得数据收集速度加快，实验数据量迅速增长。要将大量此类信息转化为关于材料工艺-结构-性能关系的可操作知识，需要高通量数据分析技术。本工作探索使用基于图的端元提取和标记（GRENDEL）算法作为一种高通量方法，用于分析来自组合库的结构数据，具体而言，是从X射线衍射和拉曼光谱数据确定相图和组成相。GRENDEL算法利用一组物理约束来优化结果，并提供了一个框架，通过该框架可以轻松纳入其他基于物理的约束。GRENDEL还允许整合数据库数据，如在X射线衍射数据分析中使用来自无机晶体结构数据库的严格评估数据所示。此外，日晕径向树状图被证明是一种可视化通过基于图的分析发现的材料结构-性能关系的工具。
