A Universal Augmentation Framework for Long-Range Electrostatics in Machine Learning Interatomic Potentials

Kim, Dongjin; Wang, Xiaoyu; Vargas, Santiago; Zhong, Peichen; King, Daniel S.; Inizan, Theo Jaffrelot; Cheng, Bingqing

doi:10.1021/acs.jctc.5c01400

Title: A Universal Augmentation Framework for Long-Range Electrostatics in Machine Learning Interatomic Potentials

Journal Article · Wed Dec 10 00:00:00 UTC 2025 · Journal of Chemical Theory and Computation

DOI: https://doi.org/10.1021/acs.jctc.5c01400 · OSTI ID:3023386

^[1]; Wang, Xiaoyu ^[1];

^[2];

^[1]; King, Daniel S. ^[1]; Inizan, Theo Jaffrelot ^[1];

^[3]

University of California, Berkeley, CA (United States)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
University of California, Berkeley, CA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Institute of Science and Technology Austria (ISTA), Klosterneuburg (Austria)

Most current machine learning interatomic potentials (MLIPs) rely on short-range approximations, without explicit treatment of long-range electrostatics. To address this, we recently developed the Latent Ewald Summation (LES) method, which infers electrostatic interactions, polarization, and Born effective charges (BECs), just by learning from energy and force training data. Here, in this study, we present LES as a standalone library, compatible with any short-range MLIP, and demonstrate its integration with methods such as MACE, NequIP, Allegro, CACE, CHGNet, and UMA. We benchmark LES-enhanced models on distinct systems, including bulk water, polar dipeptides, and gold dimer adsorption on defective substrates, and show that LES not only captures correct electrostatics but also improves accuracy. Additionally, we scale LES to large and chemically diverse data by training MACELES-OFF on the SPICE set containing molecules and clusters, making a universal MLIP with electrostatics for organic systems, including biomolecules. MACELES-OFF is more accurate than its short-range counterpart (MACE-OFF) trained on the same data set, predicts dipoles and BECs reliably, and has better descriptions of bulk liquids. By enabling efficient long-range electrostatics without directly training on electrical properties, LES paves the way for electrostatic foundation MLIPs.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: National Energy Research Scientific Computing Center (NERSC); National Institutes of Health (NIH); USDOE Office of Science (SC), High Energy Physics (HEP)

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 3023386

Journal Information:: Journal of Chemical Theory and Computation, Journal Name: Journal of Chemical Theory and Computation Journal Issue: 24 Vol. 21; ISSN 1549-9626; ISSN 1549-9618

Publisher:: American Chemical SocietyCopyright Statement

Country of Publication:: United States

Language:: English

References (79)

Solvation effects on alanine dipeptide: A MP2/cc-pVTZ//MP2/6-31G** study of (?, ?) energy maps and conformers in the gas phase, ether, and water Wang, Zhi-Xiang; Duan, Yong Journal of Computational Chemistry, Vol. 25, Issue 14 https://doi.org/10.1002/jcc.20092	journal	January 2004
Improved side-chain torsion potentials for the Amber ff99SB protein force field Lindorff-Larsen, Kresten; Piana, Stefano; Palmo, Kim Proteins: Structure, Function, and Bioinformatics https://doi.org/10.1002/prot.22711	journal	January 2010
P y SCF: the Python-based simulations of chemistry framework : The PySCF program Sun, Qiming; Berkelbach, Timothy C.; Blunt, Nick S. Wiley Interdisciplinary Reviews: Computational Molecular Science, Vol. 8, Issue 1 https://doi.org/10.1002/wcms.1340	journal	September 2017
Deconstructing Classical Water Models at Interfaces and in Bulk Remsing, Richard C.; Rodgers, Jocelyn M.; Weeks, John D. Journal of Statistical Physics, Vol. 145, Issue 2 https://doi.org/10.1007/s10955-011-0299-3	journal	August 2011
GROMACS: A message-passing parallel molecular dynamics implementation Berendsen, H. J. C.; van der Spoel, D.; van Drunen, R. Computer Physics Communications, Vol. 91, Issue 1-3 https://doi.org/10.1016/0010-4655(95)00042-E	journal	September 1995
Construction of higher order symplectic integrators Yoshida, Haruo Physics Letters A, Vol. 150, Issue 5-7 https://doi.org/10.1016/0375-9601(90)90092-3	journal	November 1990
PLUMED 2: New feathers for an old bird Tribello, Gareth A.; Bonomi, Massimiliano; Branduardi, Davide Computer Physics Communications, Vol. 185, Issue 2 https://doi.org/10.1016/j.cpc.2013.09.018	journal	February 2014
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
Automatic atom type and bond type perception in molecular mechanical calculations Wang, Junmei; Wang, Wei; Kollman, Peter A. Journal of Molecular Graphics and Modelling, Vol. 25, Issue 2 https://doi.org/10.1016/j.jmgm.2005.12.005	journal	October 2006
Machine Learning Force Fields Unke, Oliver T.; Chmiela, Stefan; Sauceda, Huziel E. Chemical Reviews https://doi.org/10.1021/acs.chemrev.0c01111	journal	March 2021
Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems Keith, John A.; Vassilev-Galindo, Valentin; Cheng, Bingqing Chemical Reviews, Vol. 121, Issue 16 https://doi.org/10.1021/acs.chemrev.1c00107	journal	July 2021
TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations Pelaez, Raul P.; Simeon, Guillem; Galvelis, Raimondas Journal of Chemical Theory and Computation, Vol. 20, Issue 10 https://doi.org/10.1021/acs.jctc.4c00253	journal	May 2024
PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges Unke, Oliver T.; Meuwly, Markus Journal of Chemical Theory and Computation, Vol. 15, Issue 6 https://doi.org/10.1021/acs.jctc.9b00181	journal	April 2019
Do Molecular Dynamics Force Fields Capture Conformational Dynamics of Alanine in Water? Zhang, Shuting; Schweitzer-Stenner, Reinhard; Urbanc, Brigita Journal of Chemical Theory and Computation, Vol. 16, Issue 1 https://doi.org/10.1021/acs.jctc.9b00588	journal	November 2019
Physics-Inspired Equivariant Descriptors of Nonbonded Interactions Huguenin-Dumittan, Kevin K.; Loche, Philip; Haoran, Ni The Journal of Physical Chemistry Letters, Vol. 14, Issue 43 https://doi.org/10.1021/acs.jpclett.3c02375	journal	October 2023
Quantum Dynamics and Spectroscopy of Ab Initio Liquid Water: The Interplay of Nuclear and Electronic Quantum Effects Marsalek, Ondrej; Markland, Thomas E. The Journal of Physical Chemistry Letters, Vol. 8, Issue 7 https://doi.org/10.1021/acs.jpclett.7b00391	journal	March 2017
Discovering a Transferable Charge Assignment Model Using Machine Learning Sifain, Andrew E.; Lubbers, Nicholas; Nebgen, Benjamin T. The Journal of Physical Chemistry Letters, Vol. 9, Issue 16 https://doi.org/10.1021/acs.jpclett.8b01939	journal	July 2018
The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts Tran, Richard; Lan, Janice; Shuaibi, Muhammed ACS Catalysis, Vol. 13, Issue 5 https://doi.org/10.1021/acscatal.2c05426	journal	February 2023
Metadynamics with Adaptive Gaussians Branduardi, Davide; Bussi, Giovanni; Parrinello, Michele Journal of Chemical Theory and Computation, Vol. 8, Issue 7 https://doi.org/10.1021/ct3002464	journal	June 2012
MACE-OFF: Short-Range Transferable Machine Learning Force Fields for Organic Molecules Kovács, Dávid Péter; Moore, J. Harry; Browning, Nicholas J. Journal of the American Chemical Society, Vol. 147, Issue 21 https://doi.org/10.1021/jacs.4c07099	journal	May 2025
Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields Kabylda, Adil; Frank, J. Thorben; Suárez-Dou, Sergio Journal of the American Chemical Society, Vol. 147, Issue 37 https://doi.org/10.1021/jacs.5c09558	journal	August 2025
A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer Ko, Tsz Wai; Finkler, Jonas A.; Goedecker, Stefan Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-020-20427-2	journal	January 2021
Self-consistent determination of long-range electrostatics in neural network potentials Gao, Ang; Remsing, Richard C. Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-29243-2	journal	March 2022
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
Machine learning of charges and long-range interactions from energies and forces King, Daniel S.; Kim, Dongjin; Zhong, Peichen Nature Communications, Vol. 16, Issue 1 https://doi.org/10.1038/s41467-025-63852-x	journal	October 2025
Machine learning force fields for molecular liquids: Ethylene Carbonate/Ethyl Methyl Carbonate binary solvent Magdău, Ioan-Bogdan; Arismendi-Arrieta, Daniel J.; Smith, Holly E. npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-01100-w	journal	August 2023
Incorporating long-range electrostatics in neural network potentials via variational charge equilibration from shortsighted ingredients Shaidu, Yusuf; Pellegrini, Franco; Küçükbenli, Emine npj Computational Materials, Vol. 10, Issue 1 https://doi.org/10.1038/s41524-024-01225-6	journal	March 2024
Cartesian atomic cluster expansion for machine learning interatomic potentials Cheng, Bingqing npj Computational Materials, Vol. 10, Issue 1 https://doi.org/10.1038/s41524-024-01332-4	journal	July 2024
Latent Ewald summation for machine learning of long-range interactions Cheng, Bingqing npj Computational Materials, Vol. 11, Issue 1 https://doi.org/10.1038/s41524-025-01577-7	journal	March 2025
Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry Ko, Tsz Wai; Deng, Bowen; Nassar, Marcel npj Computational Materials, Vol. 11, Issue 1 https://doi.org/10.1038/s41524-025-01742-y	journal	August 2025
Promoting transparency and reproducibility in enhanced molecular simulations Nature Methods, Vol. 16, Issue 8, p. 670-673 https://doi.org/10.1038/s41592-019-0506-8	journal	July 2019
QMugs, quantum mechanical properties of drug-like molecules Isert, Clemens; Atz, Kenneth; Jiménez-Luna, José Scientific Data, Vol. 9, Issue 1 https://doi.org/10.1038/s41597-022-01390-7	journal	June 2022
SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials Eastman, Peter; Behara, Pavan Kumar; Dotson, David L. Scientific Data, Vol. 10, Issue 1 https://doi.org/10.1038/s41597-022-01882-6	journal	January 2023
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling Deng, Bowen; Zhong, Peichen; Jun, KyuJung Nature Machine Intelligence, Vol. 5, Issue 9 https://doi.org/10.1038/s42256-023-00716-3	journal	September 2023
A predictive machine learning force-field framework for liquid electrolyte development Gong, Sheng; Zhang, Yumin; Mu, Zhenliang Nature Machine Intelligence, Vol. 7, Issue 4 https://doi.org/10.1038/s42256-025-01009-7	journal	April 2025
A universal graph deep learning interatomic potential for the periodic table Chen, Chi; Ong, Shyue Ping Nature Computational Science, Vol. 2, Issue 11 https://doi.org/10.1038/s43588-022-00349-3	journal	November 2022
NewtonNet: A Newtonian message passing network for deep learning of interatomic potentials and forces Haghighatlari, Mojtaba; Li, Jie; Guan, Xingyi Digital Discovery https://doi.org/10.1039/d2dd00008c	journal	January 2022
Scalable hybrid deep neural networks/polarizable potentials biomolecular simulations including long-range effects Jaffrelot Inizan, Théo; Plé, Thomas; Adjoua, Olivier Chemical Science, Vol. 14, Issue 20 https://doi.org/10.1039/d2sc04815a	journal	January 2023
Force-field-enhanced neural network interactions: from local equivariant embedding to atom-in-molecule properties and long-range effects Plé, Thomas; Lagardère, Louis; Piquemal, Jean-Philip Chemical Science, Vol. 14, Issue 44 https://doi.org/10.1039/d3sc02581k	journal	January 2023
AIMNet2: a neural network potential to meet your neutral, charged, organic, and elemental-organic needs Anstine, Dylan M.; Zubatyuk, Roman; Isayev, Olexandr Chemical Science, Vol. 16, Issue 23 https://doi.org/10.1039/d4sc08572h	journal	January 2025
Comparison of simple potential functions for simulating liquid water Jorgensen, William L.; Chandrasekhar, Jayaraman; Madura, Jeffry D. The Journal of Chemical Physics, Vol. 79, Issue 2 https://doi.org/10.1063/1.445869	journal	July 1983
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
The structure of water around the compressibility minimum Skinner, L. B.; Benmore, C. J.; Neuefeind, J. C. The Journal of Chemical Physics, Vol. 141, Issue 21 https://doi.org/10.1063/1.4902412	journal	December 2014
Incorporating long-range physics in atomic-scale machine learning Grisafi, Andrea; Ceriotti, Michele The Journal of Chemical Physics, Vol. 151, Issue 20 https://doi.org/10.1063/1.5128375	journal	November 2019
Learning intermolecular forces at liquid–vapor interfaces Niblett, Samuel P.; Galib, Mirza; Limmer, David T. The Journal of Chemical Physics, Vol. 155, Issue 16 https://doi.org/10.1063/5.0067565	journal	October 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
Quantum dynamics using path integral coarse-graining Musil, Félix; Zaporozhets, Iryna; Noé, Frank The Journal of Chemical Physics, Vol. 157, Issue 18 https://doi.org/10.1063/5.0120386	journal	November 2022
Derivative learning of tensorial quantities—Predicting finite temperature infrared spectra from first principles Schmiedmayer, Bernhard; Kresse, Georg The Journal of Chemical Physics, Vol. 161, Issue 8 https://doi.org/10.1063/5.0217243	journal	August 2024
Density-based long-range electrostatic descriptors for machine learning force fields Faller, Carolin; Kaltak, Merzuk; Kresse, Georg The Journal of Chemical Physics, Vol. 161, Issue 21 https://doi.org/10.1063/5.0245615	journal	December 2024
Fast and flexible long-range models for atomistic machine learning Loche, Philip; Huguenin-Dumittan, Kevin K.; Honarmand, Melika The Journal of Chemical Physics, Vol. 162, Issue 14 https://doi.org/10.1063/5.0251713	journal	April 2025
Intrinsic backbone preferences are fully present in blocked amino acids Avbelj, F.; Grdadolnik, S. G.; Grdadolnik, J. Proceedings of the National Academy of Sciences, Vol. 103, Issue 5 https://doi.org/10.1073/pnas.0510420103	journal	January 2006
Short solvent model for ion correlations and hydrophobic association Gao, Ang; Remsing, Richard C.; Weeks, John D. Proceedings of the National Academy of Sciences, Vol. 117, Issue 3 https://doi.org/10.1073/pnas.1918981117	journal	January 2020
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
PubChem 2025 update Kim, Sunghwan; Chen, Jie; Cheng, Tiejun Nucleic Acids Research, Vol. 53, Issue D1 https://doi.org/10.1093/nar/gkae1059	journal	November 2024
Structural Relaxation Made Simple Bitzek, Erik; Koskinen, Pekka; Gähler, Franz Physical Review Letters, Vol. 97, Issue 17 https://doi.org/10.1103/PhysRevLett.97.170201	journal	October 2006
Dynamical matrices, Born effective charges, dielectric permittivity tensors, and interatomic force constants from density-functional perturbation theory Gonze, Xavier; Lee, Changyol Physical Review B, Vol. 55, Issue 16 https://doi.org/10.1103/physrevb.55.10355	journal	April 1997
Atomic cluster expansion for accurate and transferable interatomic potentials Drautz, Ralf Physical Review B, Vol. 99, Issue 1 https://doi.org/10.1103/physrevb.99.014104	journal	January 2019
Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method Barducci, Alessandro; Bussi, Giovanni; Parrinello, Michele Physical Review Letters, Vol. 100, Issue 2 https://doi.org/10.1103/physrevlett.100.020603	journal	January 2008
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons Bartók, Albert P.; Payne, Mike C.; Kondor, Risi Physical Review Letters, Vol. 104, Issue 13 https://doi.org/10.1103/physrevlett.104.136403	journal	April 2010
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces Behler, Jörg; Parrinello, Michele Physical Review Letters, Vol. 98, Issue 14 https://doi.org/10.1103/physrevlett.98.146401	journal	April 2007
Charge-constrained atomic cluster expansion Rinaldi, Matteo; Bochkarev, Anton; Lysogorskiy, Yury Physical Review Materials, Vol. 9, Issue 3 https://doi.org/10.1103/physrevmaterials.9.033802	journal	March 2025
De Novo Protein Design: Fully Automated Sequence Selection Dahiyat, Bassil I.; Mayo, Stephen L. Science, Vol. 278, Issue 5335 https://doi.org/10.1126/science.278.5335.82	journal	October 1997
Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials Shapeev, Alexander V. Multiscale Modeling & Simulation, Vol. 14, Issue 3 https://doi.org/10.1137/15m1054183	journal	January 2016
CRC Handbook of Chemistry and Physics Haynes, W. M.; Lide, David R.; Bruno, Thomas J. CRC press https://doi.org/10.1201/9781315380476	book	June 2016
Infrared Intensities of Liquids XX: The Intensity of the OH Stretching Band of Liquid Water Revisited, and the Best Current Values of the Optical Constants of H ₂ O(l) at 25°C between 15,000 and 1 cm ⁻¹ Bertie, John E.; Lan, Zhida Applied Spectroscopy, Vol. 50, Issue 8 https://doi.org/10.1366/0003702963905385	journal	August 1996
Capturing long-range interaction with reciprocal space neural network Yu, Hongyu; Hong, Liangliang; Chen, Shiyou arXiv https://doi.org/10.48550/arXiv.2211.16684	preprint	January 2022
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs Passaro, Saro; Zitnick, C. Lawrence arXiv https://doi.org/10.48550/arXiv.2302.03655	preprint	January 2023
Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models Barroso-Luque, Luis; Shuaibi, Muhammed; Fu, Xiang arXiv https://doi.org/10.48550/arXiv.2410.12771	preprint	January 2024
Electrostatic interactions in atomistic and machine-learned potentials for polar materials Monacelli, Lorenzo; Marzari, Nicola arXiv https://doi.org/10.48550/arXiv.2412.01642	preprint	January 2024
Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction Fu, Xiang; Wood, Brandon M.; Barroso-Luque, Luis arXiv https://doi.org/10.48550/arXiv.2502.12147	preprint	January 2025
Extending the RANGE of Graph Neural Networks: Relaying Attention Nodes for Global Encoding Caruso, Alessandro; Venturin, Jacopo; Giambagli, Lorenzo arXiv https://doi.org/10.48550/arXiv.2502.13797	preprint	January 2025
Foundation Models for Atomistic Simulation of Chemistry and Materials Yuan, Eric C. -Y.; Liu, Yunsheng; Chen, Junmin arXiv https://doi.org/10.48550/arXiv.2503.10538	preprint	January 2025
Machine learning interatomic potential can infer electrical response Zhong, Peichen; Kim, Dongjin; King, Daniel S. arXiv https://doi.org/10.48550/arXiv.2504.05169	preprint	January 2025
High-performance training and inference for deep equivariant interatomic potentials Tan, Chuin Wei; Descoteaux, Marc L.; Kotak, Mit arXiv https://doi.org/10.48550/arXiv.2504.16068	preprint	January 2025
Efficient Long-Range Machine Learning Force Fields for Liquid and Materials Properties Weber, John L.; Guha, Rishabh D.; Agarwal, Garvit arXiv https://doi.org/10.48550/arXiv.2505.06462	preprint	January 2025
The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models Levine, Daniel S.; Shuaibi, Muhammed; Spotte-Smith, Evan Walter Clark arXiv https://doi.org/10.48550/arXiv.2505.08762	preprint	January 2025
UMA: A Family of Universal Models for Atoms Wood, Brandon M.; Dzamba, Misko; Fu, Xiang arXiv https://doi.org/10.48550/arXiv.2506.23971	preprint	January 2025
The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains Krishnapriyan, Aditi; Qu, Eric Advances in Neural Information Processing Systems 37 https://doi.org/10.52202/079017-4412	conference	January 2024

Similar Records

Systematic softening in universal machine learning interatomic potentials

Journal Article · Fri Jan 10 00:00:00 UTC 2025 · npj Computational Materials · OSTI ID:2528028

Deng, Bowen; Choi, Yunyeong; Zhong, Peichen; +6 more

Modeling the behavior of concentrated aqueous HNO₃ using machine learning interatomic potentials

Journal Article · Tue Jan 06 00:00:00 UTC 2026 · Journal of Chemical Physics · OSTI ID:3013819

Dinpajooh, Mohammadhasan; Lacount, Michael D.; Muller, Scott E.; +5 more

Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost

Journal Article · Tue Nov 18 00:00:00 UTC 2025 · Digital Discovery · OSTI ID:3015170

Baghishov, Ilgar Intizam Oglu; Janssen, Jan; Henkelman, Graeme; +1 more

Title: A Universal Augmentation Framework for Long-Range Electrostatics in Machine Learning Interatomic Potentials

Citation Formats

References (79)

Similar Records

Related Subjects