ACS Publications. Most Trusted. Most Cited. Most Read
Data-Efficient Machine Learning Potentials from Transfer Learning of Periodic Correlated Electronic Structure Methods: Liquid Water at AFQMC, CCSD, and CCSD(T) Accuracy
My Activity

Figure 1Loading Img
    Molecular Mechanics

    Data-Efficient Machine Learning Potentials from Transfer Learning of Periodic Correlated Electronic Structure Methods: Liquid Water at AFQMC, CCSD, and CCSD(T) Accuracy
    Click to copy article linkArticle link copied!

    Other Access OptionsSupporting Information (2)

    Journal of Chemical Theory and Computation

    Cite this: J. Chem. Theory Comput. 2023, 19, 14, 4510–4519
    Click to copy citationCitation copied!
    https://doi.org/10.1021/acs.jctc.2c01203
    Published February 2, 2023
    Copyright © 2023 American Chemical Society

    Abstract

    Click to copy section linkSection link copied!
    Abstract Image

    Obtaining the atomistic structure and dynamics of disordered condensed-phase systems from first-principles remains one of the forefront challenges of chemical theory. Here we exploit recent advances in periodic electronic structure and provide a data-efficient approach to obtain machine-learned condensed-phase potential energy surfaces using AFQMC, CCSD, and CCSD(T) from a very small number (≤200) of energies by leveraging a transfer learning scheme starting from lower-tier electronic structure methods. We demonstrate the effectiveness of this approach for liquid water by performing both classical and path integral molecular dynamics simulations on these machine-learned potential energy surfaces. By doing this, we uncover the interplay of dynamical electron correlation and nuclear quantum effects across the entire liquid range of water while providing a general strategy for efficiently utilizing periodic correlated electronic structure methods to explore disordered condensed-phase systems.

    Copyright © 2023 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.jctc.2c01203.

    • Additional details for the electronic structure calculations, training of machine learning models, molecular dynamics simulations, and the calculation of diffusion coefficients and vibrational density of states. Benchmarks for the transferability of relative training set performance, transfer learning procedure, and the effect of stochastic error in the AFQMC energies. Comparison of results when different electronic structure methods are used to initialize the transfer learning procedure. Comparison of results with MB-Pol and revPBE0-D3. Datasets used to train our MLPs (HF, BLYP, revPBE0-D3, CCSD, CCSD(T), and AFQMC). Weights for our CCSD, CCSD(T), and AFQMC committee MLPs. The datasets and weights for the MLPs shared here are in formats specific to the n2p2 package, v2.1.0. (64) (PDF)

    • (ZIP)

    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 37 publications.

    1. Amir Omranpour, Jan Elsner, K. Nikolas Lausch, Jörg Behler. Machine Learning Potentials for Heterogeneous Catalysis. ACS Catalysis 2025, 15 (3) , 1616-1634. https://doi.org/10.1021/acscatal.4c06717
    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. Sung Wook Moon, Soohaeng Yoo Willow, Tae Hyeon Park, Seung Kyu Min, Chang Woo Myung. Machine Learning Nonadiabatic Dynamics: Eliminating Phase Freedom of Nonadiabatic Couplings with the State-Interaction State-Averaged Spin-Restricted Ensemble-Referenced Kohn–Sham Approach. Journal of Chemical Theory and Computation 2025, Article ASAP.
    4. Nore Stolte, János Daru, Harald Forbert, Dominik Marx, Jörg Behler. Random Sampling Versus Active Learning Algorithms for Machine Learning Potentials of Quantum Liquid Water. Journal of Chemical Theory and Computation 2025, 21 (2) , 886-899. https://doi.org/10.1021/acs.jctc.4c01382
    5. Maksim Kulichenko, Benjamin Nebgen, Nicholas Lubbers, Justin S. Smith, Kipton Barros, Alice E. A. Allen, Adela Habib, Emily Shinkle, Nikita Fedik, Ying Wai Li, Richard A. Messerly, Sergei Tretiak. Data Generation for Machine Learning Interatomic Potentials and Beyond. Chemical Reviews 2024, 124 (24) , 13681-13714. https://doi.org/10.1021/acs.chemrev.4c00572
    6. Nore Stolte, János Daru, Harald Forbert, Jörg Behler, Dominik Marx. Nuclear Quantum Effects in Liquid Water Are Marginal for Its Average Structure but Significant for Dynamics. The Journal of Physical Chemistry Letters 2024, 15 (49) , 12144-12150. https://doi.org/10.1021/acs.jpclett.4c02925
    7. Wei Tian, Chenyu Wang, Ke Zhou. The Dynamic Diversity and Invariance of Ab Initio Water. Journal of Chemical Theory and Computation 2024, 20 (23) , 10667-10675. https://doi.org/10.1021/acs.jctc.4c01191
    8. Hong-Zhou Ye, Timothy C. Berkelbach. Periodic Local Coupled-Cluster Theory for Insulators and Metals. Journal of Chemical Theory and Computation 2024, 20 (20) , 8948-8959. https://doi.org/10.1021/acs.jctc.4c00936
    9. Gopal R. Iyer, Noah Whelpley, Juha Tiihonen, Paul R. C. Kent, Jaron T. Krogel, Brenda M. Rubenstein. Force-Free Identification of Minimum-Energy Pathways and Transition States for Stochastic Electronic Structure Theories. Journal of Chemical Theory and Computation 2024, 20 (17) , 7416-7429. https://doi.org/10.1021/acs.jctc.4c00214
    10. Jian Wang, Haitao Hei, Yonggang Zheng, Hongwu Zhang, Hongfei Ye. Five-Site Water Models for Ice and Liquid Water Generated by a Series–Parallel Machine Learning Strategy. Journal of Chemical Theory and Computation 2024, 20 (17) , 7533-7545. https://doi.org/10.1021/acs.jctc.4c00440
    11. Benjamin X. Shi, David J. Wales, Angelos Michaelides, Chang Woo Myung. Going for Gold(-Standard): Attaining Coupled Cluster Accuracy in Oxide-Supported Nanoclusters. Journal of Chemical Theory and Computation 2024, 20 (12) , 5306-5316. https://doi.org/10.1021/acs.jctc.4c00379
    12. Niamh O’Neill, Benjamin X. Shi, Kara Fong, Angelos Michaelides, Christoph Schran. To Pair or not to Pair? Machine-Learned Explicitly-Correlated Electronic Structure for NaCl in Water. The Journal of Physical Chemistry Letters 2024, 15 (23) , 6081-6091. https://doi.org/10.1021/acs.jpclett.4c01030
    13. Qi Yu, Chen Qu, Paul L. Houston, Apurba Nandi, Priyanka Pandey, Riccardo Conte, Joel M. Bowman. A Status Report on “Gold Standard” Machine-Learned Potentials for Water. The Journal of Physical Chemistry Letters 2023, 14 (36) , 8077-8087. https://doi.org/10.1021/acs.jpclett.3c01791
    14. Marcel Ruth, Dennis Gerbig, Peter R. Schreiner. Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies. Journal of Chemical Theory and Computation 2023, 19 (15) , 4912-4920. https://doi.org/10.1021/acs.jctc.3c00274
    15. Zoran Sukurma, Martin Schlipf, Moritz Humer, Amir Taheridehkordi, Georg Kresse. Benchmark Phaseless Auxiliary-Field Quantum Monte Carlo Method for Small Molecules. Journal of Chemical Theory and Computation 2023, 19 (15) , 4921-4934. https://doi.org/10.1021/acs.jctc.3c00322
    16. Chen Qu, Qi Yu, Paul L. Houston, Riccardo Conte, Apurba Nandi, Joel M. Bowman. Interfacing q-AQUA with a Polarizable Force Field: The Best of Both Worlds. Journal of Chemical Theory and Computation 2023, 19 (12) , 3446-3459. https://doi.org/10.1021/acs.jctc.3c00334
    17. Francesco Guidarelli Mattioli, Francesco Sciortino, John Russo. Are Neural Network Potentials Trained on Liquid States Transferable to Crystal Nucleation? A Test on Ice Nucleation in the mW Water Model. The Journal of Physical Chemistry B 2023, 127 (17) , 3894-3901. https://doi.org/10.1021/acs.jpcb.3c00693
    18. Amir Omranpour, Jörg Behler. A high-dimensional neural network potential for Co 3 O 4. Journal of Physics: Condensed Matter 2025, 37 (9) , 095701. https://doi.org/10.1088/1361-648X/ad9f09
    19. Fabian L Thiemann, Niamh O’Neill, Venkat Kapil, Angelos Michaelides, Christoph Schran. Introduction to machine learning potentials for atomistic simulations. Journal of Physics: Condensed Matter 2025, 37 (7) , 073002. https://doi.org/10.1088/1361-648X/ad9657
    20. Dietmar Paschek, Johanna Busch, Angel Mary Chiramel Tony, Ralf Ludwig, Anne Strate, Nore Stolte, Harald Forbert, Dominik Marx. When theory meets experiment: What does it take to accurately predict 1H NMR dipolar relaxation rates in neat liquid water from theory?. The Journal of Chemical Physics 2025, 162 (5) https://doi.org/10.1063/5.0249826
    21. Basile Herzog, Alejandro Gallo, Felix Hummel, Michael Badawi, Tomáš Bučko, Sébastien Lebègue, Andreas Grüneis, Dario Rocca. Coupled cluster finite temperature simulations of periodic materials via machine learning. npj Computational Materials 2024, 10 (1) https://doi.org/10.1038/s41524-024-01249-y
    22. Alice E. A. Allen, Nicholas Lubbers, Sakib Matin, Justin Smith, Richard Messerly, Sergei Tretiak, Kipton Barros. Learning together: Towards foundation models for machine learning interatomic potentials with meta-learning. npj Computational Materials 2024, 10 (1) https://doi.org/10.1038/s41524-024-01339-x
    23. Bo Thomsen, Yuki Nagai, Keita Kobayashi, Ikutaro Hamada, Motoyuki Shiga. Self-learning path integral hybrid Monte Carlo with mixed ab initio and machine learning potentials for modeling nuclear quantum effects in water. The Journal of Chemical Physics 2024, 161 (20) https://doi.org/10.1063/5.0230464
    24. Tong Jiang, Moritz K. A. Baumgarten, Pierre-François Loos, Ankit Mahajan, Anthony Scemama, Shu Fay Ung, Jinghong Zhang, Fionn D. Malone, Joonho Lee. Improved modularity and new features in ipie : Toward even larger AFQMC calculations on CPUs and GPUs at zero and finite temperatures. The Journal of Chemical Physics 2024, 161 (16) https://doi.org/10.1063/5.0225596
    25. Thorren Kirschbaum, Annika Bande. Transfer learning for molecular property predictions from small datasets. AIP Advances 2024, 14 (10) https://doi.org/10.1063/5.0214754
    26. Bienfait K. Isamura, Paul L. A. Popelier. Transfer learning of hyperparameters for fast construction of anisotropic GPR models: design and application to the machine-learned force field FFLUX. Physical Chemistry Chemical Physics 2024, 26 (36) , 23677-23691. https://doi.org/10.1039/D4CP01862A
    27. Soohaeng Yoo Willow, Dong Geon Kim, R. Sundheep, Amir Hajibabaei, Kwang S. Kim, Chang Woo Myung. Active sparse Bayesian committee machine potential for isothermal–isobaric molecular dynamics simulations. Physical Chemistry Chemical Physics 2024, 26 (33) , 22073-22082. https://doi.org/10.1039/D4CP01801J
    28. Stuart C. Althorpe. Path Integral Simulations of Condensed-Phase Vibrational Spectroscopy. Annual Review of Physical Chemistry 2024, 75 (1) , 397-420. https://doi.org/10.1146/annurev-physchem-090722-124705
    29. Amir Omranpour, Pablo Montero De Hijes, Jörg Behler, Christoph Dellago. Perspective: Atomistic simulations of water and aqueous systems with machine learning potentials. The Journal of Chemical Physics 2024, 160 (17) https://doi.org/10.1063/5.0201241
    30. Eli Pollak. A personal perspective of the present status and future challenges facing thermal reaction rate theory. The Journal of Chemical Physics 2024, 160 (15) https://doi.org/10.1063/5.0199557
    31. John L A Gardner, Kathryn T Baker, Volker L Deringer. Synthetic pre-training for neural-network interatomic potentials. Machine Learning: Science and Technology 2024, 5 (1) , 015003. https://doi.org/10.1088/2632-2153/ad1626
    32. Toshio Yamaguchi. Historical development of a study of the structure and dynamics of liquids and solutions. Journal of Molecular Liquids 2024, 395 , 123919. https://doi.org/10.1016/j.molliq.2023.123919
    33. Hui Yang. Optimized English Translation System Using Multi-Level Semantic Extraction and Text Matching. IEEE Access 2024, 12 , 96527-96536. https://doi.org/10.1109/ACCESS.2024.3426652
    34. Alea Miako Tokita, Jörg Behler. How to train a neural network potential. The Journal of Chemical Physics 2023, 159 (12) https://doi.org/10.1063/5.0160326
    35. Austin O. Atsango, Tobias Morawietz, Ondrej Marsalek, Thomas E. Markland. Developing machine-learned potentials to simultaneously capture the dynamics of excess protons and hydroxide ions in classical and path integral simulations. The Journal of Chemical Physics 2023, 159 (7) https://doi.org/10.1063/5.0162066
    36. Quin H. Hu, Andrew M. Johannesen, Daniel S. Graham, Jason D. Goodpaster. Neural network potentials for reactive chemistry: CASPT2 quality potential energy surfaces for bond breaking. Digital Discovery 2023, 2 (4) , 1058-1069. https://doi.org/10.1039/D3DD00051F
    37. Silvan Käser, Markus Meuwly. Transfer-learned potential energy surfaces: Toward microsecond-scale molecular dynamics simulations in the gas phase at CCSD(T) quality. The Journal of Chemical Physics 2023, 158 (21) https://doi.org/10.1063/5.0151266

    Journal of Chemical Theory and Computation

    Cite this: J. Chem. Theory Comput. 2023, 19, 14, 4510–4519
    Click to copy citationCitation copied!
    https://doi.org/10.1021/acs.jctc.2c01203
    Published February 2, 2023
    Copyright © 2023 American Chemical Society

    Article Views

    2951

    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.