ACS Publications. Most Trusted. Most Cited. Most Read
My Activity
CONTENT TYPES

Figure 1Loading Img
RETURN TO ISSUEPREVA: Structure, Spectr...A: Structure, Spectroscopy, and Reactivity of Molecules and ClustersNEXT

DeePKS + ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials

  • Wenfei Li
    Wenfei Li
    AI for Science Institute, Beijing100080, P. R. China
    More by Wenfei Li
  • Qi Ou
    Qi Ou
    AI for Science Institute, Beijing100080, P. R. China
    More by Qi Ou
  • Yixiao Chen
    Yixiao Chen
    Program in Applied and Computational Mathematics, Princeton University, Princeton, New Jersey08544, United States
    More by Yixiao Chen
  • Yu Cao
    Yu Cao
    HEDPS, CAPT, College of Engineering and School of Physics, Peking University, Beijing100871, P. R. China
    More by Yu Cao
  • Renxi Liu
    Renxi Liu
    HEDPS, CAPT, College of Engineering and School of Physics, Peking University, Beijing100871, P. R. China
    More by Renxi Liu
  • Chunyi Zhang
    Chunyi Zhang
    Department of Physics, Temple University, Philadelphia, Pennsylvania19122, United States
    More by Chunyi Zhang
  • Daye Zheng
    Daye Zheng
    AI for Science Institute, Beijing100080, P. R. China
    More by Daye Zheng
  • Chun Cai
    Chun Cai
    AI for Science Institute, Beijing100080, P. R. China
    DP Technology, Beijing100080, P. R. China
    More by Chun Cai
  • Xifan Wu
    Xifan Wu
    Department of Physics, Temple University, Philadelphia, Pennsylvania19122, United States
    More by Xifan Wu
  • Han Wang*
    Han Wang
    Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Huayuan Road 6, Beijing100088, P. R. China
    *Email: [email protected]
    More by Han Wang
  • Mohan Chen*
    Mohan Chen
    HEDPS, CAPT, College of Engineering and School of Physics, Peking University, Beijing100871, P. R. China
    *Email: [email protected]
    More by Mohan Chen
  • , and 
  • Linfeng Zhang*
    Linfeng Zhang
    AI for Science Institute, Beijing100080, P. R. China
    DP Technology, Beijing100080, P. R. China
    *Email: [email protected]
Cite this: J. Phys. Chem. A 2022, 126, 49, 9154–9164
Publication Date (Web):December 1, 2022
https://doi.org/10.1021/acs.jpca.2c05000
Copyright © 2022 American Chemical Society

    Article Views

    876

    Altmetric

    -

    Citations

    LEARN ABOUT THESE METRICS
    Other access options
    Supporting Info (1)»

    Abstract

    Abstract Image

    Recently, the development of machine learning (ML) potentials has made it possible to perform large-scale and long-time molecular simulations with the accuracy of quantum mechanical (QM) models. However, for different levels of QM methods, such as density functional theory (DFT) at the meta-GGA level and/or with exact exchange, quantum Monte Carlo, etc., generating a sufficient amount of data for training an ML potential has remained computationally challenging due to their high cost. In this work, we demonstrate that this issue can be largely alleviated with Deep Kohn–Sham (DeePKS), an ML-based DFT model. DeePKS employs a computationally efficient neural network-based functional model to construct a correction term added upon a cheap DFT model. Upon training, DeePKS offers closely matched energies and forces compared with high-level QM method, but the number of training data required is orders of magnitude less than that required for training a reliable ML potential. As such, DeePKS can serve as a bridge between expensive QM models and ML potentials: one can generate a decent amount of high-accuracy QM data to train a DeePKS model and then use the DeePKS model to label a much larger amount of configurations to train an ML potential. This scheme for periodic systems is implemented in a DFT package ABACUS, which is open source and ready for use in various applications.

    Read this article

    To access this article, please review the available access options below.

    Get instant access

    Purchase Access

    Read this article for 48 hours. Check out below using your ACS ID or as a guest.

    Recommended

    Access through Your Institution

    You may have access to this article through your institution.

    Your institution does not have access to this content. You can change your affiliated institution below.

    Supporting Information

    ARTICLE SECTIONS
    Jump To

    The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acs.jpca.2c05000.

    • Computational details of the original water data set with the SCAN0 functional applied in ref (17) and salt water data set with the SCAN functional applied in ref (52) oxygen–oxygen RDF for pure water at different pressures and for salt water with various concentrations, oxygen–sodium RDF, oxygen–chloride RDF, and ion–ion RDF for salt water, given by SCAN–DeePMD and DeePKS–DeePMD; run time of DFT SCF calculation for liquid water at different levels of theory; composition of DeePKS and DeePMD training sets for salt water; and the number of NaCl ion pairs and water molecules contained in the periodic cubic cell for each investigated concentration of salt water (PDF)

    Terms & Conditions

    Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

    Cited By

    This article is cited by 2 publications.

    1. Sophie Baker, Joshua Pagotto, Timothy T. Duignan, Alister J. Page. High-Throughput Aqueous Electrolyte Structure Prediction Using IonSolvR and Equivariant Graph Neural Network Potentials. The Journal of Physical Chemistry Letters 2023, 14 (42) , 9508-9515. https://doi.org/10.1021/acs.jpclett.3c01783
    2. Qi Ou, Ping Tuo, Wenfei Li, Xiaoxu Wang, Yixiao Chen, Linfeng Zhang. DeePKS Model for Halide Perovskites with the Accuracy of a Hybrid Functional. The Journal of Physical Chemistry C 2023, 127 (37) , 18755-18764. https://doi.org/10.1021/acs.jpcc.3c04703

    Pair your accounts.

    Export articles to Mendeley

    Get article recommendations from ACS based on references in your Mendeley library.

    Pair your accounts.

    Export articles to Mendeley

    Get article recommendations from ACS based on references in your Mendeley library.

    You’ve supercharged your research process with ACS and Mendeley!

    STEP 1:
    Click to create an ACS ID

    Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

    Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

    Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

    MENDELEY PAIRING EXPIRED
    Your Mendeley pairing has expired. Please reconnect