Feature extraction and spatial imaging of synchrotron radiation X-ray diffraction patterns using unsupervised machine learning

References

• Miao J, Charalambous P, Kirz J, et al. D. Extending the methodology of X-ray crystallography to allow imaging of micrometre-sized non-crystalline specimens. Nature. 1999;400(6742):342. doi: 10.1038/22498
   Web of Science ®Google Scholar
• Robinson I, Harder R. Coherent X-ray diffraction imaging of strain at the nanoscale. Nat Mater. 2009;8(4):291. doi: 10.1038/nmat2400
   PubMed Web of Science ®Google Scholar
• Tamura N, Celestre RS, MacDowell AA, et al. Submicron x-ray diffraction and its applications to problems in materials and environmental science. Rev Sci Instrum. 2002;73(3):1369. doi: 10.1063/1.1436539
   Web of Science ®Google Scholar
• Nikitenko S, Beale AM, Eerden MJ, et al. Implementation of a combined SAXS/WAXS/QEXAFS set-up for time-resolved in situ experiments. J Synchrotron Rad. 2008;15(6):632. doi: 10.1107/S0909049508023327
   PubMedGoogle Scholar
• Mimura H, Handa S, Kimura T, et al. Breaking the 10 nm barrier in hard-X-ray focusing. Nat Phys. 2010;6(2):122. doi: 10.1038/nphys1457
   Web of Science ®Google Scholar
• Chao W, Fischer P, Tyliszczak T, et al. Real space soft x-ray imaging at 10 nm spatial resolution. Opt Express. 2012;20(9):9777. doi: 10.1364/OE.20.009777
   PubMed Web of Science ®Google Scholar
• Mohacsi I, Vartiainen I, Rösner B, et al. Interlaced zone plate optics for hard X-ray imaging in the 10 nm range. Sci Rep. 2017;7(1):43624. doi: 10.1038/srep43624
   Google Scholar
• Denes P, Doering D, Padmore HA, et al. A fast, direct x-ray detection charge-coupled device. Rev Sci Instrum. 2009;80:083302. doi: 10.1063/1.3187222
   PubMed Web of Science ®Google Scholar
• Denes P, Schmitt B. Pixel detectors for diffraction-limited storage rings. J Synchrotron Rad. 2014;21(5):1006. doi: 10.1107/S1600577514017135
   PubMedGoogle Scholar
• Kameshima T, Ono S, Kudo T, et al. Development of an X-ray pixel detector with multi-port charge-coupled device for X-ray free-electron laser experiments. Rev Sci Instrum. 2014;85(3):03110. doi: 10.1063/1.4867668
   Web of Science ®Google Scholar
• Sasaki T, Suzuki H, Sai A, et al. In situ Real-Time X-ray reciprocal space mapping during InGaAs/GaAs growth for understanding strain relaxation mechanisms. Appl Phys Express. 2009;2:08550. doi: 10.1143/APEX.2.085501
   Web of Science ®Google Scholar
• Richard MI, Highland MJ, Fister TT, et al. In situ synchrotron x-ray studies of strain and composition evolution during metal-organic chemical vapor deposition of InGaN. Appl Phys Lett. 2010;96(5):051911. doi: 10.1063/1.3293441
   Web of Science ®Google Scholar
• Hu W, Suzuki H, Sasaki T, et al. High-speed three-dimensional reciprocal-space mapping during molecular beam epitaxy growth of InGaAs. J Appl Crystallogr. 2012;45(5):1046. doi: 10.1107/S0021889812036175
   Google Scholar
• Jung J, Yoon J, Park HK, et al. Microstructure design using machine learning generated low dimensional and continuous design space. Materialia. 2020;11:100690. doi: 10.1016/j.mtla.2020.100690
   Google Scholar
• Ramirez JM, Liu Q, Vakarin V, et al. Graded SiGe waveguides with broadband low-loss propagation in the mid infrared. Opt Express. 2018;26(2):870–12. doi: 10.1364/OE.26.000870
   PubMed Web of Science ®Google Scholar
• Kutsukake K, Usami N, Ujihara T, et al. On the origin of strain fluctuation in strained-si grown on SiGe-on-insulator and SiGe virtual substrates. Appl Phys Lett. 2004;85(8):1335–1337. doi: 10.1063/1.1784036
   Web of Science ®Google Scholar
• Nagata K, Sugita S, Okada M. Bayesian spectral deconvolution with the exchange Monte Carlo method. Neural Networks. 2012;28:82–89. doi: 10.1016/j.neunet.2011.12.001
   PubMed Web of Science ®Google Scholar
• Matsumura T, Nagamura N, Akaho S, et al. Spectrum adapted the expectation-maximization algorithm for high-throughput peak shift analysis. Sci Technol Adv Mater. 2019;20(1):733–745.
   PubMed Web of Science ®Google Scholar
• Shinotsuka H, Nagata K, Yoshikawa H, et al. Development of spectral decomposition based on Bayesian information criterion with estimation of confidence interval. Sci Technol Adv Mater. 2020;21(1):402–419. doi: 10.1080/14686996.2020.1773210
   PubMed Web of Science ®Google Scholar
• Lee DD, Seung HS. Learning the parts of objects by non-negative matrix factorization. Nature. 1999;401(6755):788–791. doi: 10.1038/44565
   PubMed Web of Science ®Google Scholar
• Lee D, Seung HS. Algorithms for non-negative matrix factorization. Adv Neural Inf Process Syst. 2001; 13.
   Google Scholar
• Friedman J, Hastie T, Tibshirani R. The elements of statistical learning. In: Bühlmann P, Diggle P, Gather U, editors. Volume 1 Springer series in statistics. New York (NY): Springer; 2001.
   Google Scholar
• Cichocki A, Zdunek R, Phan A, et al. Nonnegative matrix and tensor factorizations: applications to Exploratory Multi-way Data Analysis and blind source separation. New Jersey: Wiley; 2009.
   Google Scholar
• Févotte C, Bertin N, Durrieu JL. Nonnegative matrix factorization with the Itakura-Saito divergence: with application to music analysis. Neural Comput. 2009;21(3):793–830. doi: 10.1162/neco.2008.04-08-771
   PubMed Web of Science ®Google Scholar
• Honma M, Akiyama K, Uemura M, et al. Super-resolution imaging with radio interferometry using sparse modelling. Publ Astron Soc Jpn. 2014;66(95):1–14.
   Google Scholar
• Shiga M, Tatsumi K, Muto S, et al. Sparse modeling of EELS and EDX spectral imaging data by nonnegative matrix factorization. Ultramicroscopy. 2016;170:43–59. doi: 10.1016/j.ultramic.2016.08.006
   PubMed Web of Science ®Google Scholar
• Long CJ, Bunker D, Li X, et al. Rapid identification of structural phases in combinatorial thin-film libraries using x-ray diffraction and non-negative matrix factorization. Rev Sci Instum. 2009;80(10):103902.
   PubMed Web of Science ®Google Scholar
• Kusne AG, Keller D, Anderson A, et al. High-throughput determination of structural phase diagram and constituent phases using GRENDEL. Nanotech. 2015;26(44):444002. doi: 10.1088/0957-4484/26/44/444002
   PubMed Web of Science ®Google Scholar
• Stefano S, Bras RL, Suram SK, et al. Pattern decomposition with complex combinatorial constraints: application to materials discovery. Proc Twenty-Ninth AAAI Conf Art Int. 2015;29(1). doi: 10.1609/aaai.v29i1.9233
   Google Scholar
• Bai J, Bjorck J, Xue Y, et al. Relaxation methods for constrained matrix factorization problems: solving the phase mapping problem in materials discovery. International Conference on AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems. Springer, Cham; 2017. doi: 10.1007/978-3-319-59776-8_9
   Google Scholar
• Suram SK, Xue Y, Bai J, et al. Automated phase mapping with AgileFD and its application to light absorber discovery in the V–mn–nb oxide system. ACS Comb Sci. 2016;19(1):37–46.
   PubMed Web of Science ®Google Scholar
• Stanev V, Vesselinov VV, Kusne AG, et al. Unsupervised phase mapping of X-ray diffraction data by nonnegative matrix factorization integrated with custom clustering. Npj Comput Mater. 2018;4:43. doi: 10.1038/s41524-018-0099-2
   Web of Science ®Google Scholar
• Jha D, Kusne AG, Bahrani RA, et al. Peak area detection network for directly learning phase regions from raw x-ray diffraction patterns. 2019 International Joint Conference on Neural Networks (IJCNN). IEEE; 2019: pp.1–8. doi: 10.1109/IJCNN.2019.8852096
   Google Scholar
• Fukami S, Nakagawa Y, Hainey MF Jr, et al. Epitaxial growth of SiGe on Si substrate by printing and firing of Al–ge mixed paste. Jpn J Appl Phys. 2019;58(4):045504–1–6. doi: 10.7567/1347-4065/ab00e5
   Web of Science ®Google Scholar
• Cichocki A, PHAN A-H. Fast local algorithms for large scale nonnegative matrix and tensor factorizations. IEICE Trans Fundamentals. 2009;92(3):708–721. doi: 10.1587/transfun.E92.A.708
   Google Scholar
• Fevotte C, Idier J. Algorithms for nonnegative matrix factorization with the beta-divergence. Neural Comput. 2011;23(9):2421–2456. doi: 10.1162/NECO_a_00168
   Web of Science ®Google Scholar
• Hoyer P. Non-negative matrix factorization with sparseness constraints. J Mac Learn Res. 2004;5:1457–1469.
   Web of Science ®Google Scholar
• Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825–2830.
   Web of Science ®Google Scholar
• Virtanen P, Gommers R, Oliphant TE, et al. Fundamental algorithms for scientific computing in Python. Nat Methods. 2020;17(3):261–272.
   PubMed Web of Science ®Google Scholar
• Ament SE, Stein HS, Guevarra D, et al. Multi-component background learning automates signal detection for spectroscopic data. Npj Comput Mater. 2019;5(1):77. doi: 10.1038/s41524-019-0213-0
   Google Scholar
• Augustin L, Bach F, Févotte C Online algorithms for nonnegative matrix actorization with the Itakura-Saito divergence. 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). New Paltz, NY, USA: IEEE; 2011. p. 313–316. doi:10.1109/ASPAA.2011.6082314
   Google Scholar