Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements.

Journal: Nature communications
Published Date: May 30, 2022

Abstract

Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. Here we report a development of universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, which include a diverse set of virtual structures used to attain the universality. We demonstrated the applicability of PFP in selected domains: lithium diffusion in LiFeSOF, molecular adsorption in metal-organic frameworks, an order-disorder transition of Cu-Au alloys, and material discovery for a Fischer-Tropsch catalyst. They showcase the power of PFP, and this technology provides a highly useful tool for material discovery.

Authors

  • So Takamoto
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan. takamoto@preferred.jp.
  • Chikashi Shinagawa
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Daisuke Motoki
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Kosuke Nakago
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Wenwen Li
    School of Geographical Sciences and Urban Planning, Arizona State University, Tempe, AZ 85287, USA.
  • Iori Kurata
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Taku Watanabe
    Division of Respiratory Medicine, Department of Internal Medicine, Hokkaido University Graduate School of Medicine, Sapporo, Japan.
  • Yoshihiro Yayama
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Hiroki Iriguchi
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Yusuke Asano
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Tasuku Onodera
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Takafumi Ishii
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Takao Kudo
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Hideki Ono
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan.
  • Ryohto Sawada
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Ryuichiro Ishitani
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Marc Ong
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Taiki Yamaguchi
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Toshiki Kataoka
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Akihide Hayashi
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Nontawat Charoenphakdee
    Preferred Networks, Inc., 100-0004, 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan.
  • Takeshi Ibuka
    Central Technical Research Laboratory, ENEOS Corporation, 231-0815, 8 Chidoricho, Naka-ku, Yokohama, Kanagawa, Japan. ibuka.takeshi@eneos.com.

Keywords

External Resources

Popular Topics
Recent Journals