Semi-Supervised Approach to Phase Identification from Combinatorial Sample Diffraction Patterns
- 436 Downloads
Manual attribution of crystallographic phases from high-throughput x-ray diffraction studies is an arduous task, and represents a rate-limiting step in high-throughput exploration of new materials. Here, we demonstrate a semi-supervised machine learning technique, SS-AutoPhase, which uses a two-step approach to identify automatically phases from diffraction data. First, clustering analysis is used to select a representative subset of samples automatically for human analysis. Second, an AdaBoost classifier uses the labeled samples to identify the presence of the different phases in diffraction data. SS-AutoPhase was used to identify the metallographic phases in 278 diffraction patterns from a FeGaPd composition spread sample. The accuracy of SS-AutoPhase was >82.6% for all phases when 15% of the diffraction patterns were used for training. The SS-AutoPhase predicted phase diagram showed excellent agreement with human expert analysis. Furthermore it was able to determine and identify correctly a previously unreported phase.
KeywordsHierarchal Cluster Analysis Human Expert Dynamic Time Warping Fe3Si Training Sample Size
The work is funded in part by the Advanced Research Projects Agency-Energy (ARPA-E), U.S. Department of Energy, under Award DE-AR0000492. We would like to acknowledge the support of the South Carolina SmartState Center for Strategic Approaches to the Generation of Electricity (SAGE).
- 1.National Science and Technology Council, Materials Genome Initiative for Global Competitiveness (2011).Google Scholar
- 3.National Science and Technology Council, Materials Genome Initiative Strategic Plan (2014).Google Scholar
- 4.M.L. Green, J.R. Hattrick-Simpers, I. Takeuchi, S.C. Barron, A.M. Joshi, T. Chiang, A. Mehta, and A. Davydov, Fulfilling the Promise of the Materials Genome Initiative via High-Throughput Experimentation (2014).Google Scholar
- 6.D.J. Arriola, E.M. Carnahan, P.D. Hustad, R.L. Kuhlman, and T.T. Wenzel, Science 714, 312 (2006).Google Scholar
- 11.A. Holzwarth and W.F. Maier, Platin. Met. Rev. 44, 16 (2000).Google Scholar
- 14.G.J. Cunningham (Master’s Thesis, Instituto Superior Técnico, 2011).Google Scholar
- 16.R. Le Bras, T. Damoulas, J.M. Gregoire, A. Sabharwal, C.P. Gomes, and R.B. Van Dover, Lect. Notes Comput. Sci. 6878, 508 (2011).Google Scholar
- 17.S. Ermon, R. Le Bras, S.K. Suram, J.M. Gregoire, C.P. Gomes, B. Selman, and R.B. Van Dover, arXiv. 1411, 7441 (2014).Google Scholar
- 22.Citrin Informatics, Fe-Ga-Pd, Ciritrination, http://citrination.com.
- 23.C. Long, CombiView, https://sourceforge.net/projects/xrdsuite.
- 25.J.A. Hartigan and M.A. Wong, J. R. Stat. Soc. C App. 28, 100 (1979).Google Scholar
- 26.D. Arthur and S. Vassilvitskii, Proceedings of Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, p. 1027 (2007).Google Scholar
- 31.J. Cui (PhD Thesis, University of Minnesota 2002).Google Scholar
- 36.A. Jain, G. Hautier, C.J. Moore, S.P. Ong, C.C. Fischer, T. Mueller, K.A. Persson, and G. Ceder, Mater. Sci. 50, 2295 (2011).Google Scholar
- 38.M. Klintenberg, The Electronic Structure Project, http://gurka.fysik.uu.se/esp.
- 39.E. Tadmor, R. Elliot, and I. Takeuichi, Rise of Data in Materials Research, http://riseofdata.org/umd-workshop.