journal article·2018-02

Inferring phase diagrams from X-ray data with background signals using graph segmentation

Shaobo Li, Zheng Xiong, Jianjun Hu

Materials Science and Technology· Volume 34· Issue 3
Publisher page

Abstract

Automated composition-structure-processing phase diagram creation is critical for high-throughput experimental material studies. In particular, diffractogram datasets with large background signals are especially difficult to identify the phase regions. In this work, we proposed a novel graph segmentation algorithm from computer vision to solve the phase diagram prediction problem from X-ray diffraction data with large background signals. We introduced a novel background subtraction algorithm with graph-based clustering/segmentation to build the BGPhase algorithm. Experiments on three datasets with the Al–Cu–Mo material family showed that our phase attribution algorithm can achieve high prediction accuracy ranging from 88.6 to 94.8% or with MCC scores ranging from 0.715 to 0.890. The algorithm can be accessed online at http://mleg.cse.sc.edu/bgphase .
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Electron and X-Ray Spectroscopy Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, People's Republic of China

School of Mechanical Engineering, Guizhou University, Guiyang, Guizhou, People's Republic of China

Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, USA

Funding

National Natural Science Foundation of China · China National Intelligent Manufacturing Foundation · Guizhou Province Key Project of Scientific Research Foundation · Guizhou Province Higher Education Improvement Fund

References (32)

Show source-provided references
1. Ward C. Materials Genome Initiative for Global Competitiveness. In 23rd Advanced Aerospace Materials and Processes (AeroMat) Conference and Exposition; 2012. ASM.
2. 10.1103/PhysRevA.43.316110.1103/PhysRevA.43.3161 ↗
3. 10.1107/S002188980400039110.1107/S0021889804000391 ↗
4. 10.1016/j.commatsci.2008.03.05110.1016/j.commatsci.2008.03.051 ↗
5. 10.1016/j.csda.2006.11.00610.1016/j.csda.2006.11.006 ↗
6. Cunningham GJ. · 2011
7. Ermon S, Bras RL, Suram SK, Pattern decomposition with complex combinatorial constraints: application to materials discovery. arXiv preprint arXiv:1411.7441, 2014.10.1609/aaai.v29i1.9233 ↗
8. 10.1016/j.apsusc.2007.04.09110.1016/j.apsusc.2007.04.091 ↗
9. 10.1016/S0169-4332(03)00919-X10.1016/S0169-4332(03)00919-X ↗
10. 10.1007/s11837-006-0150-510.1007/s11837-006-0150-5 ↗
11. Kullmann O. Theory and applications of Satisfiability Testing-SAT 2009: 12th International Conference, SAT 2009, Swansea, UK, 2009 June 30–July 3. Proceedings. Vol. 5584; 2009. Springer.10.1007/978-3-642-02777-2 ↗
12. 10.1007/s11837-007-0039-y10.1007/s11837-007-0039-y ↗
13. 10.1021/ci700218p10.1021/ci700218p ↗
14. 10.1016/j.actamat.2010.09.06810.1016/j.actamat.2010.09.068 ↗
15. 10.1016/j.compchemeng.2008.08.01210.1016/j.compchemeng.2008.08.012 ↗
16. 10.1016/S0926-860X(00)00643-810.1016/S0926-860X(00)00643-8 ↗
17. 10.1179/00070598979827053110.1179/000705989798270531 ↗
18. 10.1088/0957-4484/26/44/44400210.1088/0957-4484/26/44/444002 ↗
19. 10.1063/1.321680910.1063/1.3216809 ↗
20. 10.1063/1.275548710.1063/1.2755487 ↗
21. 10.1007/978-3-642-23786-7_3910.1007/978-3-642-23786-7_39 ↗
22. 10.1107/S002188980401117310.1107/S0021889804011173 ↗
23. 10.1016/j.jcat.2006.04.03610.1016/j.jcat.2006.04.036 ↗
24. 10.1038/srep0636710.1038/srep06367 ↗
25. 10.1557/jmr.2015.8010.1557/jmr.2015.80 ↗
26. 10.1007/s11837-016-2033-810.1007/s11837-016-2033-8 ↗
27. 10.1021/acscombsci.6b0012110.1021/acscombsci.6b00121 ↗
28. 10.1021/acscombsci.6b0015310.1021/acscombsci.6b00153 ↗
29. 10.1021/co500157910.1021/co5001579 ↗
30. 10.1016/j.patcog.2011.03.00510.1016/j.patcog.2011.03.005 ↗
31. 10.1016/S0010-4485(97)00082-110.1016/S0010-4485(97)00082-1 ↗
32. 10.1023/B:VISI.0000022288.19776.7710.1023/B:VISI.0000022288.19776.77 ↗