ACS Publications. Most Trusted. Most Cited. Most Read
DeePKS + ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
My Activity

Figure 1Loading Img
    A: Structure, Spectroscopy, and Reactivity of Molecules and Clusters

    DeePKS + ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
    Click to copy article linkArticle link copied!

    • 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
    • Linfeng Zhang*
      Linfeng Zhang
      AI for Science Institute, Beijing100080, P. R. China
      DP Technology, Beijing100080, P. R. China
      *Email: [email protected]
    Other Access OptionsSupporting Information (1)

    The Journal of Physical Chemistry A

    Cite this: J. Phys. Chem. A 2022, 126, 49, 9154–9164
    Click to copy citationCitation copied!
    https://doi.org/10.1021/acs.jpca.2c05000
    Published December 1, 2022
    Copyright © 2022 American Chemical Society

    Abstract

    Click to copy section linkSection link copied!
    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.

    Copyright © 2022 American Chemical Society

    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. Add or change your institution or let them know you’d like them to include access.

    Supporting Information

    Click to copy section linkSection link copied!

    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

    Click to copy section linkSection link copied!
    Citation Statements
    Explore this article's citation statements on scite.ai

    This article is cited by 8 publications.

    1. Pengchao Zhang, Xuefei Xu. Propensity of Water Self-Ions at Air(Oil)–Water Interfaces Revealed by Deep Potential Molecular Dynamics with Enhanced Sampling. Langmuir 2025, 41 (5) , 3675-3683. https://doi.org/10.1021/acs.langmuir.4c05004
    2. Wai-Pan Ng, Zili Zhang, Jun Yang. Accurate Neural Network Fine-Tuning Approach for Transferable Ab Initio Energy Prediction across Varying Molecular and Crystalline Scales. Journal of Chemical Theory and Computation 2025, Article ASAP.
    3. Pengchao Zhang, Axel Tosello Gardini, Xuefei Xu, Michele Parrinello. Intramolecular and Water Mediated Tautomerism of Solvated Glycine. Journal of Chemical Information and Modeling 2024, 64 (9) , 3599-3604. https://doi.org/10.1021/acs.jcim.4c00273
    4. 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
    5. 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
    6. Kyle Bystrom, Boris Kozinsky. Nonlocal machine-learned exchange functional for molecules and solids. Physical Review B 2024, 110 (7) https://doi.org/10.1103/PhysRevB.110.075130
    7. Jin Xiao, YiXiao Chen, LinFeng Zhang, Han Wang, Tong Zhu. A machine learning-based high-precision density functional method for drug-like molecules. Artificial Intelligence Chemistry 2024, 2 (1) , 100037. https://doi.org/10.1016/j.aichem.2023.100037
    8. Xiao Xie, Mengteng Chen, Yawei Yu, Jia Li, Mingwen Zhao, Linyang Li. Structural phase transitions, mechanical properties, and electronic band structures of room-temperature ferromagnetic monolayers ScMP2 (M = Mn and Cr). Results in Physics 2023, 53 , 106988. https://doi.org/10.1016/j.rinp.2023.106988

    The Journal of Physical Chemistry A

    Cite this: J. Phys. Chem. A 2022, 126, 49, 9154–9164
    Click to copy citationCitation copied!
    https://doi.org/10.1021/acs.jpca.2c05000
    Published December 1, 2022
    Copyright © 2022 American Chemical Society

    Article Views

    1186

    Altmetric

    -

    Citations

    Learn about these metrics

    Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to reflect usage leading up to the last few days.

    Citations are the number of other articles citing this article, calculated by Crossref and updated daily. Find more information about Crossref citation counts.

    The Altmetric Attention Score is a quantitative measure of the attention that a research article has received online. Clicking on the donut icon will load a page at altmetric.com with additional details about the score and the social media presence for the given article. Find more information on the Altmetric Attention Score and how the score is calculated.