Skip to main content
SpringerLink
Log in

Flexible Unsupervised Binary Change Detection Algorithm Identifies Phase Transitions in Continuous Image Streams

  • Technical Article
  • Published:
Integrating Materials and Manufacturing Innovation Aims and scope Submit manuscript

Abstract

Sequences of projection images collected during in situ tomography experiments can capture the formation of patterns in crystallization and yield their three-dimensional growth morphologies. These image streams generate enormous and high dimensional datasets that span the full extent of a phase transition. Detecting from the continuous image stream the characteristic times and temperatures at which the phase transition initiates is a challenge because the phase change is often swift and subtle. Here, we show a flexible unsupervised binary classification algorithm to identify a change point during data intensive experiments. The algorithm makes a prediction based on statistical metrics and has a quantifiable error bound. Applied to two in situ X-ray tomography experimental datasets collected at a synchrotron light source, the developed method can detect the moment at which the solid phase emerges from the parent liquid phase upon crystallization and without performing computationally expensive volume reconstructions. Our approach is verified using a simulated X-ray phantom and its performance evaluated with respect to solidification parameters. The method presented here can be broadly applied to other Big Data problems where time series can be classified without the need for additional training data.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Christian JW (2002) The theory of transformations in metals and alloys. Elsevier, Amsterdam

    Google Scholar 

  2. Emmerich H (2014) Heterogeneous nucleation and microstructure formation: from a model systems to applied metal physics. JOM 66(8):1493–1495. https://doi.org/10.1007/s11837-014-1035-7

    Article  Google Scholar 

  3. Spaepen F (1994) Homogeneous nucleation and the temperature dependence of the crystal-melt interfacial tension. In: Solid state physics. Academic Press, New York, vol 47, p 1

  4. Shahani AJ et al (2020) Characterization of metals in four dimensions. Mater Res Lett 812:462–476. https://doi.org/10.1080/21663831.2020.1809544

    Article  CAS  Google Scholar 

  5. Withers PJ (2007) X-ray nanotomography. Mater Today 10(12):26–34. https://doi.org/10.1016/S1369-7021(07)70305-X

    Article  CAS  Google Scholar 

  6. Maire E, Withers PJ (2014) Quantitative X-ray tomography. Int Mater Rev 59(1):1–43. https://doi.org/10.1179/1743280413Y.0000000023

    Article  CAS  Google Scholar 

  7. Nguyen-Thi H et al (2012) On the interest of synchrotron X-ray imaging for the study of solidification in metallic alloys. Comptes Rendus Phys 13(3):237–245. https://doi.org/10.1016/j.crhy.2011.11.010

    Article  CAS  Google Scholar 

  8. Reinhart G et al (2008) In-situ and real-time analysis of the formation of strains and microstructure defects during solidification of Al-3.5 Wt Pct Ni alloys. Metall Mater Trans A 39(4):865–874. https://doi.org/10.1007/s11661-007-9449-2

    Article  CAS  Google Scholar 

  9. Shahani AJ, Xiao X, Voorhees PW (2016) The mechanism of eutectic growth in highly anisotropic materials. Nat Commun 7(1):1–7. https://doi.org/10.1038/ncomms12953

    Article  CAS  Google Scholar 

  10. Moniri S, Xiao X, Shahani AJ (2019) The mechanism of eutectic modification by trace impurities. Sci Rep 9(1):1–13. https://doi.org/10.1038/s41598-019-40455-3

    Article  CAS  Google Scholar 

  11. Zhou T, Song Z, Sundmacher K (2019) Big data creates new opportunities for materials research: a review on methods and applications of machine learning for materials design. Engineering 5(6):1017–1026. https://doi.org/10.1016/j.eng.2019.02.011

    Article  CAS  Google Scholar 

  12. Han I, Xiao X, Shahani AJ (2017) Probing the growth and melting pathways of a decagonal quasicrystal in real-time. Sci Rep 7(1):1–10. https://doi.org/10.1038/s41598-017-17821-0

    Article  CAS  Google Scholar 

  13. Herlach DM, Feuerbacher B (1991) Non-equilibrium solidification of undercooled metallic melts. Adv Space Res 11(7):255–262. https://doi.org/10.1016/0273-1177(91)90293-S

    Article  CAS  Google Scholar 

  14. Sun W, Ceder G (2017) Induction time of a polymorphic transformation. CrystEngComm 19(31):4576–4585. https://doi.org/10.1039/C7CE00766C

    Article  CAS  Google Scholar 

  15. Gürsoy D et al (2014) TomoPy: a framework for the analysis of synchrotron tomographic data. J Synchrotron Radiat 21:1188–1193. https://doi.org/10.1107/S1600577514013939

    Article  Google Scholar 

  16. Aditya MK et al (2015) TIMBIR: a method for time-space reconstruction from interlaced views. IEEE Trans Comput Imaging 1(2):96–111. https://doi.org/10.1109/TCI.2015.2431913

    Article  Google Scholar 

  17. Liotti E et al (2018) Crystal nucleation in metallic alloys using x-ray radiography and machine learning. Sci Adv 4(4):eaar4004. https://doi.org/10.1126/sciadv.aar4004

    Article  CAS  Google Scholar 

  18. Aminikhanghahi S, Cook DJ (2017) A survey of methods for time series change point detection. Knowl Inf Syst 51(2):339–367. https://doi.org/10.1007/s10115-016-0987-z

    Article  Google Scholar 

  19. Bagnall A et al (2017) The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov 31(3):606–660. https://doi.org/10.1007/s10618-016-0483-9

    Article  Google Scholar 

  20. Adorf CS et al (2020) Analysis of self-assembly pathways with unsupervised machine learning algorithms. J Phys Chem B 124(1):69–78. https://doi.org/10.1021/acs.jpcb.9b09621

    Article  CAS  Google Scholar 

  21. Dowd BA et al. (1999) Developments in synchrotron x-ray computed microtomography at the National Synchrotron Light Source. In: Ulrich Bonse, pp 224–236. https://doi.org/10.1117/12.363725

  22. Guido Van Rossum, Drake Fred L Jr (1995) Python tutorial. Centrum voor Wiskunde en Informatica, Amsterdam

    Google Scholar 

  23. Pedregosa F et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830

    Google Scholar 

  24. Oliphant Travis (2006) NumPy: a guide to NumPy. Trelgol Publishing, USA. http://www.numpy.org/

  25. The HDF Group. Hierarchical Data Format, version 5. http://www.hdfgroup.org/HDF5/.1997-NNNN

  26. Han I, Xiao X, Shahani AJ (2017) Probing the growth and melting pathways of a decagonal quasicrystal in real-time. Sci Rep 7:1–10. https://doi.org/10.18126/M2K910

    Article  Google Scholar 

  27. Moniri S, Xiao X, Shahani AJ (2020) Dataset for “Singly-twinned growth of Si crystals upon chemical modification”. Phys Rev Mater 4:063403. https://doi.org/10.7302/812m-d307

    Article  CAS  Google Scholar 

  28. Chao P (2020) Sinogram change point detection. https://github.com/shahaniRG/sinogram_changepoint_detection

  29. Ratke L, Voorhees PW (2011) Growth and coarsening: Ostwald ripening in material processing. Springer, Berlin

    Google Scholar 

  30. MATLAB. version 9.6.0 (R2019a). Natick, Massachusetts: The MathWorks Inc., 2019

  31. Steurer W (2018) Quasicrystals: what do we know? What do we want to know? What can we know? Acta Crystallogr Sect A Found Adv 74(1):1–11. https://doi.org/10.1107/S2053273317016540

    Article  CAS  Google Scholar 

  32. Holland-Moritz D, Herlach DM, Urban K (1993) Observation of the undercoolability of quasicrystal-forming alloys by electromagnetic levitation. Phys Rev Lett 71(8):1196–1199. https://doi.org/10.1103/PhysRevLett.71.1196

    Article  CAS  Google Scholar 

  33. Frank FC, Mott NF (1952) Supercooling of liquids. Proc R Soc Lond Ser A Math Phys Sci 215(1120):43–46. https://doi.org/10.1098/rspa.1952.0194

    Article  CAS  Google Scholar 

  34. Als-Nielsen J, McMorrow D (2011) Elements of modern x-ray physics, 1st edn. Wiley, New York. https://doi.org/10.1002/9781119998365

    Book  Google Scholar 

  35. Fundamentals of X-ray physics. In: Buzug T (ed) Computed tomography: from photon statistics to modern cone-beam CT. Springer, Berlin, Heidelberg, 2008, pp 15–73. https://doi.org/10.1007/978-3-540-39408-2_2

  36. Jake Lever MK, Altman N (2017) Principal component analysis. Nat Methods 14(7):641–642. https://doi.org/10.1038/nmeth.4346

    Article  CAS  Google Scholar 

  37. Everitt BS et al (2011) Cluster analysis, 5th ed. Wiley, Chichester

    Book  Google Scholar 

  38. Wierzchon S, Klopotek M (2018) Modern algorithms of cluster analysis. Studies in big data. Springer, Cham. https://doi.org/10.1007/978-3-319-69308-8

    Book  Google Scholar 

  39. Bezdek JC, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10(2):191–203. https://doi.org/10.1016/0098-3004(84)90020-7

    Article  Google Scholar 

  40. Pal NR, Bezdek JC (1995) On cluster validity for the fuzzy c-means model. IEEE Trans Fuzzy Syst 3(3):370–379. https://doi.org/10.1109/91.413225

    Article  Google Scholar 

  41. Yokoyama Y et al (1997) Preparation of decagonal Al-Ni-Co single quasicrystal by Czochralski method. Mater Trans JIM 38(11):943–949

    Article  CAS  Google Scholar 

  42. Moniri S, Xiao X, Shahani AJ (2020) Singly-twinned growth of Si crystals upon chemical modification. Phys Rev Mater 4(6):063403. https://doi.org/10.1103/PhysRevMaterials.4.063403

    Article  CAS  Google Scholar 

  43. Leo HL, Lebrun N (2003) Aluminium-Copper-Silicon. Landolt-Börnstein-Group IV. Phys Chem 11A2:13. https://doi.org/10.1007/10915967_9

    Article  Google Scholar 

  44. Mathiesen RH et al (2011) X-ray videomicroscopy studies of Eutectic Al-Si solidification in Al-Si-Cu. Metall Mater Trans A 42(1):170–180. https://doi.org/10.1007/s11661-010-0443-8

    Article  CAS  Google Scholar 

  45. Jiang H (2015) Computed tomography principles, design, artifacts, and recent advances. SPIE, Bellingham, Washington

    Google Scholar 

  46. Andersson J-O et al (2002) Thermo-Calc & DICTRA, computational tools for materials science. Calphad 26(2):273–312. https://doi.org/10.1016/S0364-5916(02)00037-8

    Article  CAS  Google Scholar 

  47. Han I et al (2019) A side-by-side comparison of the solidification dynamics of quasicrystalline and approximant phases in the Al-Co-Ni system. Acta Crystallogr Sect A Found Adv 75(2):281–296. https://doi.org/10.1107/S2053273318017114

    Article  CAS  Google Scholar 

  48. Hamilton DR, Seidensticker RG (2020) Propagation mechanism of germanium dendrites. J Appl Phys 31(7):1165–1168. https://doi.org/10.1063/1.1735796

    Article  Google Scholar 

  49. Porter DA, Easterling KE (1992) Phase transformations in metals and alloys (revised reprint), 3rd edn. CRC Press, Boca Raton

    Book  Google Scholar 

Download references

Acknowledgements

We gratefully acknowledge financial support from the National Science Foundation (NSF) CAREER program under Award No. 1847855. We thank Dr. Insung Han, Dr. Saman Moniri, Dr. Caleb Reese, Dr. Riddhiman Bhattacharya, and Dr. Nancy Senabulya for assisting in the synchrotron-based experiment; and Pavel Shevshenko for assistance in sample preparation. This research used resources of the Advanced Photon Source, a U.S. Department of Energy (DOE) Office of Science User Facility operated for the DOE Office of Science by Argonne National Laboratory under Contract No. DE-AC02-06CH11357.

Author information

Authors and Affiliations

  1. Department of Materials Science and Engineering, University of Michigan, Ann Arbor, MI, 48109, USA

    Paul Chao & Ashwin J. Shahani

  2. National Synchrotron Light Source II (NSLS-II), Brookhaven National Laboratory, Upton, NY, 11973, USA

    Xianghui Xiao

Authors
  1. Paul Chao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xianghui Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ashwin J. Shahani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ashwin J. Shahani.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3587 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chao, P., Xiao, X. & Shahani, A.J. Flexible Unsupervised Binary Change Detection Algorithm Identifies Phase Transitions in Continuous Image Streams. Integr Mater Manuf Innov 10, 72–81 (2021). https://doi.org/10.1007/s40192-021-00199-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40192-021-00199-3

Keywords

Search

Navigation