Overview of Bayesian Optimization in Materials Science

Part of the SpringerBriefs in the Mathematics of Materials book series (BRIEFSMAMA, volume 3)


Like any other field of research, materials science involves a lot of trial and error: in the process of creating a new material or device, we will inevitably make several prototypes which fail to perform as hoped.


  1. 1.
    Quote by President Obama, June 2011 at Carnegie Mellon University. See https://www.obamawhitehouse.archives.gov/mgi for more details.
  2. 2.
    Hinuma Y, et al. Discovery of earth-abundant nitride semiconductors by computational screening and high-pressure synthesis. Nat Commun. 2016;7:11962.CrossRefGoogle Scholar
  3. 3.
    Seko A, et al. Prediction of low-thermal-conductivity compounds with first-principles anharmonic lattice-dynamics calculations and Bayesian optimization. Phys Rev Lett. 2015;115:205901.CrossRefGoogle Scholar
  4. 4.
    Seko A, et al. Machine learning with systematic density-functional theory calculations: application to melting temperatures of single- and binary-component solids. Phys Rev B. 2014;89:054303.CrossRefGoogle Scholar
  5. 5.
    Balachandran PV, et al. Adaptive strategies for materials design using uncertainties. Sci Rep. 2016;6:19660.CrossRefGoogle Scholar
  6. 6.
    Kiyohara S, et al. Acceleration of stable interface structure searching using a Kriging approach. Jpn J Appl Phys. 2016;55:045502.CrossRefGoogle Scholar
  7. 7.
    Ju S, et al. Designing nanostructures for photon transport via Bayesian optimization. Phys Rev X. 2017;7:021024.Google Scholar
  8. 8.
    Ueno T, et al. COMBO: An efficient Bayesian optimization library for materials science. Mater Discov. 2016;4:18.CrossRefGoogle Scholar
  9. 9.
    Rupp M, et al. Fast and accurate modeling of molecular atomization energies with machine learning. Phys Rev Lett. 2012;108:058301.CrossRefGoogle Scholar
  10. 10.
    Hansen K, et al. Assessment and validation of machine learning methods for predicting molecular atomization energies. J Chem Theory Comput. 2013;9:3404.CrossRefGoogle Scholar
  11. 11.
    Huo, H, Rupp, M. Unified representation for machine learning of molecules and crystals. arXiv:1704.06439v1 [physics.chem-ph].

Copyright information

© The Author(s) 2017

Authors and Affiliations

  1. 1.Institute for Integrated Cell-Materials Sciences (iCeMS)Kyoto UniversityKyotoJapan

Personalised recommendations