Hostname: page-component-77c89778f8-vsgnj Total loading time: 0 Render date: 2024-07-19T11:58:37.690Z Has data issue: false hasContentIssue false
  • English
  • Français

Identifying hidden high-dimensional structure/property relationships using self-organizing maps

Published online by Cambridge University Press:  24 April 2019

Amanda S. Barnard Open the ORCID record for Amanda S. Barnard [Opens in a new window] ,
Benyamin Motevalli  and
Baichuan Sun
Amanda S. Barnard*
Affiliation:
CSIRO Data61, Door 34 Village Street, Docklands, VIC 3008, Australia
Benyamin Motevalli
Affiliation:
CSIRO Data61, Door 34 Village Street, Docklands, VIC 3008, Australia
Baichuan Sun
Affiliation:
CSIRO Data61, Door 34 Village Street, Docklands, VIC 3008, Australia
*
Address all correspondence to Amanda S. Barnard at amanda.barnard@data61.csiro.au
Get access

Abstract

Unlike other data intensive domains, understanding distributions, trends, correlations, and relationships in materials data sets typically involves navigating high-dimensional spaces with only a limited number of observations. Under these conditions extracting structure/property relationships is not straightforward and considerable attention must be given to the reduction of feature space before predictions can be made. Here we have used Kohonen networks (self-organizing maps) to identify hidden structure/property relationships in computational sets of twinned and single-crystal diamond nanoparticles based on structural similarity in multiple dimensions, and confirmed the importance of a limited number of surface chemical features using regression.

Type
Research Letters
Information
MRS Communications , Volume 9 , Issue 2 , June 2019 , pp. 730 - 736
Copyright
Copyright © Materials Research Society 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1.Agrawal, A. and Choudhary, A.: Perspective: materials informatics and big data: realization of the fourth paradigm of science in materials science. APL Mater. 4, 053208 (2016).Google Scholar
2.Jain, A., Hautier, G., Ong, S.P., and Persson, K.: New opportunities for materials informatics: resources and data mining techniques for uncovering hidden relationships. J. Mater. Res. 31, 977 (2016).Google Scholar
3.Sun, B., Fernandez, M., and Barnard, A.S.: Statistics, damned statistics and nanoscience – using data science to meet the challenge of nanomaterial complexity. Nano Horiz. 1, 89 (2016).Google Scholar
4.Ramprasad, R, Batra, R, Pilania, G, Mannodi-Kanakkithodi, A, and Kim, C: Machine learning in materials informatics: recent applications and prospects. Comput. Mater. 3, 54 (2017).Google Scholar
5.Ramakrishnan, R. and von Lilienfeld, A.: Machine learning, quantum chemistry, and chemical space. Rev. Comput. Chem. 30, 225 (2017).Google Scholar
6.Sun, B., Fernandez, M. and Barnard, A.S.: Machine learning for silver nanoparticle electron transfer property prediction. J. Chem. Info. Mod. 57, 2413 (2017).Google Scholar
7.Ward, L. and Wolverton, C.: Atomistic calculations and materials informatics: a review. Curr. Opin. Solid State Mater. Sci., 21, 167 (2017).Google Scholar
8.Swann, E., Sun, B., Cleland, D.M., and Barnard, A.S.: Representing molecular and materials data for unsupervised machine learning. Molec. Simulat. 44, 905 (2018).Google Scholar
9.Kohonen, T.: The self-organizing map. Neurocomputing 21, 1 (1998).Google Scholar
10.Bishop, C.: Neural Networks for Pattern Recognition (Oxford University Press, USA, 1995).Google Scholar
11.Gasteiger, J., Li, X. X., Rudolph, C., Sadowski, J., and Zupan, J.: Representation of molecular electrostatic potentials by topological feature maps. J. Am. Chem. Soc. 116, 46084 (1994).Google Scholar
12.Sun, B. and Barnard, A.S.: Texture based image classification for nanoparticle surface characterisation and machine learning. J. Phys.: Mater. 1, 016001 (2018).Google Scholar
13.Wittek, P., Gao, S.C., Lim, I.S., and Zhao, L.: An efficient parallel library for self-organizing maps. J. Stat. Software, 78, 1 (2017).Google Scholar
14.Barnard, A.: Nanodiamond Data Set, v1. CSIRO Data Collection (2016) doi: 10.4225/08/571F076D050B1.Google Scholar
15.Barnard, A.: Twinned Nanodiamond Data Set, v2. CSIRO Data Collection (2018) doi: 10.25919/5be375f444e69.Google Scholar
16.Sun, B. and Barnard, A.S.: Impact of speciation on the electron charge transfer properties of nanodiamond drug carriers. Nanoscale 8, 14264 (2016).Google Scholar
17.Osswald, S., Yushin, G., Mochalin, V., Kucheyev, S. O., and Gogotsi, Y.: Control of sp2/sp3 carbon ratio and surface chemistry of nanodiamond powders by selective oxidation in air. J. Am. Chem. Soc. 128, 11635 (2006).Google Scholar
18.Ginés, L., Mandal, S., Ahmed, A., Cheng, C.-L., Sow, M., and Williams, O.A.: Positive zeta potential of nanodiamonds. Nanoscale 9, 12549 (2017).Google Scholar
19.Ho, T. K.: Random Decision Forests. In Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, pp. 278 (1995).Google Scholar
20.Williams, O.A., Hees, J., Dieker, C., Jäger, W., Kirste, L., and Nebel, C.E.: Size-Dependent reactivity of diamond nanoparticles. ACS Nano 4, 4824 (2010).Google Scholar
21.Nagl, A., Hemelaar, S. R., and Schirhagl, R.: Improving surface and defect center chemistry of fluorescent nanodiamonds for imaging purposes—a review. Anal Bioanal. Chem. 407, 7521 (2015).Google Scholar
22.Turcheniuk, K. and Mochalin, V.: Biomedical applications of nanodiamond (Review). Nanotechnology 28, 252001 (2017).Google Scholar
23.Barnard, A.S.: Predicting the impact of structural diversity on the performance of nanodiamond drug carriers. Nanoscale 10, 8893 (2018).Google Scholar
24.Stehlik, S., Ondic, L., Berhane, A.M., Aharonovich, I., Girard, H.A., Arnault, J.-C., and Rezek, B.: Photoluminescence of nanodiamonds influenced by charge transfer from silicon and metal substrates. Diamond Relat. Mater. 63, 91 (2016).Google Scholar
Supplementary material: PDF

Barnard et al. supplementary material

Barnard et al. supplementary material 1

Download Barnard et al. supplementary material(PDF)
PDF 7.3 MB