Transferable Water Potentials Using Equivariant Neural Networks

Maxson, Tristan; Szilvási, Tibor

doi:10.1021/acs.jpclett.4c00605

Title: Transferable Water Potentials Using Equivariant Neural Networks

Journal Article · Thu Mar 28 00:00:00 UTC 2024 · Journal of Physical Chemistry Letters

DOI: https://doi.org/10.1021/acs.jpclett.4c00605 · OSTI ID:2938318

^[1];

^[1]

Univ. of Alabama, Tuscaloosa, AL (United States)

Machine learning interatomic potentials (MLIPs) have emerged as a technique that promises quantum theory accuracy for reduced cost. It has been proposed [J. Chem. Phys. 2023, 158, 084111] that MLIPs trained on solely liquid water data cannot accurately transfer to the vapor–liquid equilibrium while recovering the many-body decomposition (MBD) analysis of gas-phase water clusters. This suggests that MLIPs do not directly learn the physically correct interactions of water molecules, limiting transferability. In this work, we show that MLIPs using equivariant architecture and trained on 3200 liquid water structures reproduces liquid-phase water properties (e.g., density within 0.003 g/cm³ between 230 and 365 K), vapor–liquid equilibrium properties up to 550 K, the MBD analysis of gas-phase water cluster up to six-body interactions, and the relative energy and the vibrational density of states of ice phases. We show that potentials developed using equivariant MLIPs allow transferability for arbitrary phases of water that remain stable in nanosecond long simulations.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Univ. of Alabama, Tuscaloosa, AL (United States); University of Alabama, Tuscaloosa, AL (United States)

Sponsoring Organization:: National Energy Research Scientific Computing Center (NERSC); National Science Foundation (NSF); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)

Grant/Contract Number:: AC02-05CH11231; SC0023112; SC0024654

OSTI ID:: 2938318

Journal Information:: Journal of Physical Chemistry Letters, Journal Name: Journal of Physical Chemistry Letters Journal Issue: 14 Vol. 15; ISSN 1948-7185

Publisher:: American Chemical SocietyCopyright Statement

Country of Publication:: United States

Language:: English

References (63)

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science Deringer, Volker L.; Caro, Miguel A.; Csányi, Gábor Advanced Materials, Vol. 31, Issue 46 https://doi.org/10.1002/adma.201902765	journal	September 2019
PACKMOL: A package for building initial configurations for molecular dynamics simulations Martínez, L.; Andrade, R.; Birgin, E. G. Journal of Computational Chemistry, Vol. 30, Issue 13 https://doi.org/10.1002/jcc.21224	journal	October 2009
A priori calculation of molecular properties to chemical accuracy Helgaker, Trygve; Ruden, Torgeir A.; Jørgensen, Poul Journal of Physical Organic Chemistry, Vol. 17, Issue 11 https://doi.org/10.1002/poc.841	journal	August 2004
The Stopping and Range of Ions in Matter Ziegler, James F.; Biersack, Jochen P. Treatise on Heavy-Ion Science https://doi.org/10.1007/978-1-4615-8103-1_3	book	January 1985
The infrared spectra of amorphous solid water and ice Ic between 10 and 140 K Hagen, W.; Tielens, A. G. G. M.; Greenberg, J. M. Chemical Physics, Vol. 56, Issue 3 https://doi.org/10.1016/0301-0104(81)80158-9	journal	April 1981
On the Transferability of Three Water Models Developed by Adaptive Force Matching Hu, Hongyi; Ma, Zhonghua; Wang, Feng Annual Reports in Computational Chemistry https://doi.org/10.1016/B978-0-444-63378-1.00002-1	book	January 2014
Machine-learning interatomic potentials for materials science Mishin, Y. Acta Materialia, Vol. 214 https://doi.org/10.1016/j.actamat.2021.116980	journal	August 2021
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis Ong, Shyue Ping; Richards, William Davidson; Jain, Anubhav Computational Materials Science, Vol. 68 https://doi.org/10.1016/j.commatsci.2012.10.028	journal	February 2013
Batch active learning for accelerating the development of interatomic potentials Wilson, Nathan; Willhelm, Daniel; Qian, Xiaoning Computational Materials Science, Vol. 208 https://doi.org/10.1016/j.commatsci.2022.111330	journal	June 2022
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics Wang, Han; Zhang, Linfeng; Han, Jiequn Computer Physics Communications, Vol. 228 https://doi.org/10.1016/j.cpc.2018.03.016	journal	July 2018
LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales Thompson, Aidan P.; Aktulga, H. Metin; Berger, Richard Computer Physics Communications, Vol. 271 https://doi.org/10.1016/j.cpc.2021.108171	journal	February 2022
Getting the Right Answers for the Right Reasons: Toward Predictive Molecular Simulations of Water with Many-Body Potential Energy Functions Paesani, Francesco Accounts of Chemical Research, Vol. 49, Issue 9 https://doi.org/10.1021/acs.accounts.6b00285	journal	August 2016
Modeling Molecular Interactions in Water: From Pairwise to Many-Body Potential Energy Functions Cisneros, Gerardo Andrés; Wikfeldt, Kjartan Thor; Ojamäe, Lars Chemical Reviews, Vol. 116, Issue 13 https://doi.org/10.1021/acs.chemrev.5b00644	journal	May 2016
Recent Advances for Improving the Accuracy, Transferability, and Efficiency of Reactive Force Fields Leven, Itai; Hao, Hongxia; Tan, Songchen Journal of Chemical Theory and Computation, Vol. 17, Issue 6 https://doi.org/10.1021/acs.jctc.1c00118	journal	May 2021
MB-pol(2023): Sub-chemical Accuracy for Water Simulations from the Gas to the Liquid Phase Zhu, Xuanyu; Riera, Marc; Bull-Vulpe, Ethan F. Journal of Chemical Theory and Computation, Vol. 19, Issue 12 https://doi.org/10.1021/acs.jctc.3c00326	journal	May 2023
DFT-Quality Adsorption Simulations in Metal–Organic Frameworks Enabled by Machine Learning Potentials Goeminne, Ruben; Vanduyfhuys, Louis; Van Speybroeck, Veronique Journal of Chemical Theory and Computation, Vol. 19, Issue 18 https://doi.org/10.1021/acs.jctc.3c00495	journal	August 2023
Many-Body Interactions in Ice Pham, C. Huy; Reddy, Sandeep K.; Chen, Karl Journal of Chemical Theory and Computation, Vol. 13, Issue 4 https://doi.org/10.1021/acs.jctc.6b01248	journal	March 2017
Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground Schran, Christoph; Behler, Jörg; Marx, Dominik Journal of Chemical Theory and Computation, Vol. 16, Issue 1 https://doi.org/10.1021/acs.jctc.9b00805	journal	November 2019
Machine Learning Interatomic Potentials and Long-Range Physics Anstine, Dylan M.; Isayev, Olexandr The Journal of Physical Chemistry A, Vol. 127, Issue 11 https://doi.org/10.1021/acs.jpca.2c06778	journal	February 2023
Performance and Cost Assessment of Machine Learning Interatomic Potentials Zuo, Yunxing; Chen, Chi; Li, Xiangguo The Journal of Physical Chemistry A, Vol. 124, Issue 4 https://doi.org/10.1021/acs.jpca.9b08723	journal	October 2019
Neural Network Water Model Based on the MB-Pol Many-Body Potential Muniz, Maria Carolina; Car, Roberto; Panagiotopoulos, Athanassios Z. The Journal of Physical Chemistry B, Vol. 127, Issue 42 https://doi.org/10.1021/acs.jpcb.3c04629	journal	October 2023
Characterizing Structure-Dependent TiS₂/Water Interfaces Using Deep-Neural-Network-Assisted Molecular Dynamics Li, Lesheng; Calegari Andrade, Marcos F.; Car, Roberto The Journal of Physical Chemistry C, Vol. 127, Issue 20 https://doi.org/10.1021/acs.jpcc.2c08581	journal	May 2023
Enhancing the Quality and Reliability of Machine Learning Interatomic Potentials through Better Reporting Practices Maxson, Tristan; Soyemi, Ademola; Chen, Benjamin W. J. The Journal of Physical Chemistry C, Vol. 128, Issue 16 https://doi.org/10.1021/acs.jpcc.4c00028	journal	March 2024
Efficient Atomic-Resolution Uncertainty Estimation for Neural Network Potentials Using a Replica Ensemble Jeong, Wonseok; Yoo, Dongsun; Lee, Kyuhyun The Journal of Physical Chemistry Letters, Vol. 11, Issue 15 https://doi.org/10.1021/acs.jpclett.0c01614	journal	June 2020
Hydrogen Coupling on Platinum Using Artificial Neural Network Potentials and DFT Rice, Peter S.; Liu, Zhi-Pan; Hu, P. The Journal of Physical Chemistry Letters, Vol. 12, Issue 43 https://doi.org/10.1021/acs.jpclett.1c02998	journal	October 2021
Anomalies and Local Structure of Liquid Water from Boiling to the Supercooled Regime as Predicted by the Many-Body MB-pol Model Gartner, Thomas E.; Hunter, Kelly M.; Lambros, Eleftherios The Journal of Physical Chemistry Letters, Vol. 13, Issue 16 https://doi.org/10.1021/acs.jpclett.2c00567	journal	April 2022
A Status Report on “Gold Standard” Machine-Learned Potentials for Water Yu, Qi; Qu, Chen; Houston, Paul L. The Journal of Physical Chemistry Letters, Vol. 14, Issue 36 https://doi.org/10.1021/acs.jpclett.3c01791	journal	September 2023
Chemisorbed and Physisorbed Water at the TiO ₂ /Water Interface Hosseinpour, Saman; Tang, Fujie; Wang, Fenglong The Journal of Physical Chemistry Letters, Vol. 8, Issue 10 https://doi.org/10.1021/acs.jpclett.7b00564	journal	May 2017
Chemical Reactions and Solvation at Liquid Interfaces: A Microscopic Perspective Benjamin, Ilan Chemical Reviews, Vol. 96, Issue 4 https://doi.org/10.1021/cr950230+	journal	January 1996
Development of a “First Principles” Water Potential with Flexible Monomers: Dimer Potential Energy Surface, VRT Spectrum, and Second Virial Coefficient Babin, Volodymyr; Leforestier, Claude; Paesani, Francesco Journal of Chemical Theory and Computation, Vol. 9, Issue 12 https://doi.org/10.1021/ct400863t	journal	November 2013
Development of a “First Principles” Water Potential with Flexible Monomers. II: Trimer Potential Energy Surface, Third Virial Coefficient, and Small Clusters Babin, Volodymyr; Medders, Gregory R.; Paesani, Francesco Journal of Chemical Theory and Computation, Vol. 10, Issue 4 https://doi.org/10.1021/ct500079y	journal	March 2014
Development of a “First-Principles” Water Potential with Flexible Monomers. III. Liquid Phase Properties Medders, Gregory R.; Babin, Volodymyr; Paesani, Francesco Journal of Chemical Theory and Computation, Vol. 10, Issue 8 https://doi.org/10.1021/ct5004115	journal	July 2014
Molecular Dynamics of Supercritical Water Using a Flexible SPC Model Mizan, Tahmid I.; Savage, Phillip E.; Ziff, Robert M. The Journal of Physical Chemistry, Vol. 98, Issue 49 https://doi.org/10.1021/j100100a042	journal	December 1994
Structure and Dynamics of the TIP3P, SPC, and SPC/E Water Models at 298 K Mark, Pekka; Nilsson, Lennart The Journal of Physical Chemistry A, Vol. 105, Issue 43 https://doi.org/10.1021/jp003020w	journal	November 2001
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials Batzner, Simon; Musaelian, Albert; Sun, Lixin Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-29939-5	journal	May 2022
Learning local equivariant representations for large-scale atomistic dynamics Musaelian, Albert; Batzner, Simon; Johansson, Anders Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-36329-y	journal	February 2023
Realistic phase diagram of water from “first principles” data-driven quantum simulations Bore, Sigbjørn Løland; Paesani, Francesco Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-38855-1	journal	June 2023
Solvation free energies for periodic surfaces: comparison of implicit and explicit solvation models Steinmann, Stephan N.; Sautet, Philippe; Michel, Carine Physical Chemistry Chemical Physics, Vol. 18, Issue 46 https://doi.org/10.1039/C6CP04094B	journal	January 2016
Machine learning for reparameterization of four-site water models: TIP4P-BG and TIP4P-BGT Ye, Hong-fei; Wang, Jian; Zheng, Yong-gang Physical Chemistry Chemical Physics, Vol. 23, Issue 17 https://doi.org/10.1039/D0CP05831A	journal	January 2021
A first-principles machine-learning force field for heterogeneous ice nucleation on microcline feldspar Piaggi, Pablo M.; Selloni, Annabella; Panagiotopoulos, Athanassios Z. Faraday Discussions, Vol. 249 https://doi.org/10.1039/D3FD00100H	journal	January 2024
Molecular density functional theory of solvation: From polar solvents to water Zhao, Shuangliang; Ramirez, Rosa; Vuilleumier, Rodolphe The Journal of Chemical Physics, Vol. 134, Issue 19 https://doi.org/10.1063/1.3589142	journal	May 2011
The Nose–Hoover thermostat Evans, D. J.; Holian, B. L. The Journal of Chemical Physics, Vol. 83, Issue 8 https://doi.org/10.1063/1.449071	journal	October 1985
Nosé–Hoover chains: The canonical ensemble via continuous dynamics Martyna, Glenn J.; Klein, Michael L.; Tuckerman, Mark The Journal of Chemical Physics, Vol. 97, Issue 4 https://doi.org/10.1063/1.463940	journal	August 1992
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy APL Materials, Vol. 1, Issue 1 https://doi.org/10.1063/1.4812323	journal	July 2013
On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice Reddy, Sandeep K.; Straight, Shelby C.; Bajaj, Pushp The Journal of Chemical Physics, Vol. 145, Issue 19 https://doi.org/10.1063/1.4967719	journal	November 2016
Temperature-dependent vibrational spectra and structure of liquid water from classical and quantum simulations with the MB-pol potential energy function Reddy, Sandeep K.; Moberg, Daniel R.; Straight, Shelby C. The Journal of Chemical Physics, Vol. 147, Issue 24 https://doi.org/10.1063/1.5006480	journal	December 2017
Improve the performance of machine-learning potentials by optimizing descriptors Gao, Hao; Wang, Junjie; Sun, Jian The Journal of Chemical Physics, Vol. 150, Issue 24 https://doi.org/10.1063/1.5097293	journal	June 2019
Machine learning for interatomic potential models Mueller, Tim; Hernandez, Alberto; Wang, Chuhong The Journal of Chemical Physics, Vol. 152, Issue 5 https://doi.org/10.1063/1.5126336	journal	February 2020
Solvation at metal/water interfaces: An ab initio molecular dynamics benchmark of common computational approaches Heenen, Hendrik H.; Gauthier, Joseph A.; Kristoffersen, Henrik H. The Journal of Chemical Physics, Vol. 152, Issue 14 https://doi.org/10.1063/1.5144912	journal	April 2020
When do short-range atomistic machine-learning models fall short? Yue, Shuwen; Muniz, Maria Carolina; Calegari Andrade, Marcos F. The Journal of Chemical Physics, Vol. 154, Issue 3 https://doi.org/10.1063/5.0031215	journal	January 2021
Vapor–liquid equilibrium of water with the MB-pol many-body potential Muniz, Maria Carolina; Gartner, Thomas E.; Riera, Marc The Journal of Chemical Physics, Vol. 154, Issue 21 https://doi.org/10.1063/5.0050068	journal	June 2021
A deep potential model with long-range electrostatic interactions Zhang, Linfeng; Wang, Han; Muniz, Maria Carolina The Journal of Chemical Physics, Vol. 156, Issue 12 https://doi.org/10.1063/5.0083669	journal	March 2022
Fast uncertainty estimates in deep learning interatomic potentials Zhu, Albert; Batzner, Simon; Musaelian, Albert The Journal of Chemical Physics, Vol. 158, Issue 16 https://doi.org/10.1063/5.0136574	journal	April 2023
A “short blanket” dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions? Zhai, Yaoguang; Caruso, Alessandro; Bore, Sigbjørn Løland The Journal of Chemical Physics, Vol. 158, Issue 8 https://doi.org/10.1063/5.0142843	journal	February 2023
DeePMD-kit v2: A software package for deep potential models Zeng, Jinzhe; Zhang, Duo; Lu, Denghui The Journal of Chemical Physics, Vol. 159, Issue 5 https://doi.org/10.1063/5.0155600	journal	August 2023
The atomic simulation environment—a Python library for working with atoms Hjorth Larsen, Ask; Jørgen Mortensen, Jens; Blomqvist, Jakob Journal of Physics: Condensed Matter, Vol. 29, Issue 27 https://doi.org/10.1088/1361-648X/aa680e	journal	June 2017
Energy contour exploration with potentiostatic kinematics Waters, Michael J.; Rondinelli, James M. Journal of Physics: Condensed Matter, Vol. 33, Issue 44 https://doi.org/10.1088/1361-648X/ac1af0	journal	August 2021
Benchmarking structural evolution methods for training of machine learned interatomic potentials Waters, Michael J.; Rondinelli, James M. Journal of Physics: Condensed Matter, Vol. 34, Issue 38 https://doi.org/10.1088/1361-648X/ac7f73	journal	July 2022
High-dimensional neural network potentials for metal surfaces: A prototype study for copper Artrith, Nongnuch; Behler, Jörg Physical Review B, Vol. 85, Issue 4 https://doi.org/10.1103/PhysRevB.85.045439	journal	January 2012
Phase Diagram of Water from Computer Simulation Sanz, E.; Vega, C.; Abascal, J. L. F. Physical Review Letters, Vol. 92, Issue 25 https://doi.org/10.1103/PhysRevLett.92.255701	journal	June 2004
The Properties of Water in Biological Systems Cooke, R.; Kuntz, I. D. Annual Review of Biophysics and Bioengineering, Vol. 3, Issue 1 https://doi.org/10.1146/annurev.bb.03.060174.000523	journal	June 1974
On the transferability of the SPC/L water model to biomolecular simulation Glättli, Alice; Oostenbrink, Chris; Daura, Xavier Brazilian Journal of Physics, Vol. 34, Issue 1 https://doi.org/10.1590/S0103-97332004000100015	journal	March 2004
Probing the role of acid site distribution on water structure in aluminosilicate zeolites: insights from molecular dynamics Zheng, Mingze; Bukowski, Brandon C. https://doi.org/10.26434/chemrxiv-2023-pg96c	preprint	October 2023

Similar Records

MS25: Materials Science-Focused Benchmark Data Set for Machine Learning Interatomic Potentials

Journal Article · Thu Jul 31 00:00:00 UTC 2025 · Journal of Chemical Information and Modeling · OSTI ID:3006207

Maxson, Tristan; Soyemi, Ademola; Zhang, Xinglong; +2 more

Enhancing the Quality and Reliability of Machine Learning Interatomic Potentials through Better Reporting Practices

Journal Article · Wed Mar 20 00:00:00 UTC 2024 · Journal of Physical Chemistry. C · OSTI ID:2573725

Maxson, Tristan; Soyemi, Ademola; Chen, Benjamin W. J.; +1 more

Neural Network Water Model Based on the MB-Pol Many-Body Potential

Journal Article · Thu Oct 12 00:00:00 UTC 2023 · The Journal of Physical Chemistry B · OSTI ID:2998839

Muniz, Maria Carolina; Car, Roberto; Panagiotopoulos, Athanassios Z.

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Chemical structure
Energy
Stress
Vapor liquid equilibrium
Water
chemical structure
energy
stress
vapor liquid equilibrium
water

Title: Transferable Water Potentials Using Equivariant Neural Networks

Citation Formats

References (63)

Similar Records

Related Subjects