Cluster-Graph Fingerprinting: A Framework for Quantitative Analysis of Machine-Learned Interatomic Model Training and Simulation Data

Laubach, Benjamin R.; Lordi, Vincenzo; Lindsey, Rebecca K.

doi:10.1021/acs.jcim.5c02179

Title: Cluster-Graph Fingerprinting: A Framework for Quantitative Analysis of Machine-Learned Interatomic Model Training and Simulation Data

Journal Article · Wed Dec 31 00:00:00 UTC 2025 · Journal of Chemical Information and Modeling

DOI: https://doi.org/10.1021/acs.jcim.5c02179 · OSTI ID:3017968

Laubach, Benjamin R. ^[1];

^[2];

^[1]

Univ. of Michigan, Ann Arbor, MI (United States)
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Machine-learned interatomic models represent a significant advancement in simulation methods, extending the predictive ability of first-principles methods to previously inaccessible length and time scales. However, the data-driven nature of these models can lead to difficult-to-detect errors that can compromise prediction accuracy. To address this challenge, we introduce a novel fingerprinting approach based on the Chebyshev Interaction Model for Efficient Simulation (ChIMES) ML-IAM graph-based descriptor. Our strategy enables efficient and statistically rigorous analysis of system configurations used in ML-IAM training and those generated by their application, e.g., in molecular dynamics simulations. We demonstrate that these fingerprints can effectively assess novelty of a configuration relative to an existing data set and determine dissimilarity among individual configurations, which are two key tasks in workflows for active learning-based ML-IAM training, data set curation, and on-the-fly uncertainty quantification.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Organization:: National Science Foundation; USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC52-07NA27344

OSTI ID:: 3017968

Report Number(s):: LLNL-JRNL-2005542

Journal Information:: Journal of Chemical Information and Modeling, Journal Name: Journal of Chemical Information and Modeling Journal Issue: 1 Vol. 66; ISSN 1549-9596; ISSN 1549-960X

Publisher:: American Chemical SocietyCopyright Statement

Country of Publication:: United States

Language:: English

References (71)

A generalized expression for the similarity of spectra: application to powder diffraction pattern classification de Gelder, R.; Wehrens, R.; Hageman, J. A. Journal of Computational Chemistry, Vol. 22, Issue 3 https://doi.org/10.1002/1096-987X(200102)22:3<273::AID-JCC1001>3.0.CO;2-0	journal	January 2001
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
Semiempirical GGA-type density functional constructed with a long-range dispersion correction Grimme, Stefan Journal of Computational Chemistry, Vol. 27, Issue 15, p. 1787-1799 https://doi.org/10.1002/jcc.20495	journal	January 2006
Embedding of Molecular Structure Using Molecular Hypergraph Variational Autoencoder with Metric Learning Koge, Daiki; Ono, Naoaki; Huang, Ming Molecular Informatics, Vol. 40, Issue 2 https://doi.org/10.1002/minf.202000203	journal	November 2020
Machine‐Learning a Solution for Reactive Atomistic Simulations of Energetic Materials Lindsey, Rebecca K.; Huy Pham, Cong; Goldman, Nir Propellants, Explosives, Pyrotechnics, Vol. 47, Issue 8 https://doi.org/10.1002/prep.202200001	journal	March 2022
Mahalanobis distance McLachlan, G. J. Resonance, Vol. 4, Issue 6 https://doi.org/10.1007/BF02834632	journal	June 1999
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set Kresse, G.; Furthmüller, J. Computational Materials Science, Vol. 6, Issue 1, p. 15-50 https://doi.org/10.1016/0927-0256(96)00008-0	journal	July 1996
The Mahalanobis distance De Maesschalck, R.; Jouan-Rimbaud, D.; Massart, D. L. Chemometrics and Intelligent Laboratory Systems, Vol. 50, Issue 1, p. 1-18 https://doi.org/10.1016/S0169-7439(99)00047-7	journal	January 2000
Active learning of linearly parametrized interatomic potentials Podryabinkin, Evgeny V.; Shapeev, Alexander V. Computational Materials Science, Vol. 140 https://doi.org/10.1016/j.commatsci.2017.08.031	journal	December 2017
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
Deep learning methods for molecular representation and property prediction Li, Zhen; Jiang, Mingjian; Wang, Shuang Drug Discovery Today, Vol. 27, Issue 12 https://doi.org/10.1016/j.drudis.2022.103373	journal	December 2022
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials Thompson, A. P.; Swiler, L. P.; Trott, C. R. Journal of Computational Physics, Vol. 285 https://doi.org/10.1016/j.jcp.2014.12.018	journal	March 2015
Detecting multivariate outliers: Use a robust variant of the Mahalanobis distance Leys, Christophe; Klein, Olivier; Dominicy, Yves Journal of Experimental Social Psychology, Vol. 74 https://doi.org/10.1016/j.jesp.2017.09.011	journal	January 2018
A unified deep neural network potential capable of predicting thermal conductivity of silicon in different phases Li, R.; Lee, E.; Luo, T. Materials Today Physics, Vol. 12 https://doi.org/10.1016/j.mtphys.2020.100181	journal	March 2020
Learning a Mahalanobis distance metric for data clustering and classification Xiang, Shiming; Nie, Feiping; Zhang, Changshui Pattern Recognition, Vol. 41, Issue 12 https://doi.org/10.1016/j.patcog.2008.05.018	journal	December 2008
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals Chen, Chi; Ye, Weike; Zuo, Yunxing Chemistry of Materials, Vol. 31, Issue 9 https://doi.org/10.1021/acs.chemmater.9b01294	journal	April 2019
ChIMES: A Force Matched Potential with Explicit Three-Body Interactions for Molten Carbon Lindsey, Rebecca K.; Fried, Laurence E.; Goldman, Nir Journal of Chemical Theory and Computation, Vol. 13, Issue 12 https://doi.org/10.1021/acs.jctc.7b00867	journal	November 2017
Application of the ChIMES Force Field to Nonreactive Molecular Systems: Water at Ambient Conditions Lindsey, Rebecca K.; Fried, Laurence E.; Goldman, Nir Journal of Chemical Theory and Computation, Vol. 15, Issue 1 https://doi.org/10.1021/acs.jctc.8b00831	journal	November 2018
General Atomic Neighborhood Fingerprint for Machine Learning-Based Methods Batra, Rohit; Tran, Huan Doan; Kim, Chiho The Journal of Physical Chemistry C, Vol. 123, Issue 25 https://doi.org/10.1021/acs.jpcc.9b03925	journal	June 2019
High-Accuracy Semiempirical Quantum Models Based on a Minimal Training Set Pham, Cong Huy; Lindsey, Rebecca K.; Fried, Laurence E. The Journal of Physical Chemistry Letters, Vol. 13, Issue 13 https://doi.org/10.1021/acs.jpclett.2c00453	journal	March 2022
Extreme Metastability of Diamond and its Transformation to the BC8 Post-Diamond Phase of Carbon Nguyen-Cong, Kien; Willman, Jonathan T.; Gonzalez, Joseph M. The Journal of Physical Chemistry Letters, Vol. 15, Issue 4 https://doi.org/10.1021/acs.jpclett.3c03044	journal	January 2024
Genetic Optimization of Training Sets for Improved Machine Learning Models of Molecular Properties Browning, Nicholas J.; Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole The Journal of Physical Chemistry Letters, Vol. 8, Issue 7 https://doi.org/10.1021/acs.jpclett.7b00038	journal	March 2017
Insightful classification of crystal structures using deep learning Ziletti, Angelo; Kumar, Devinder; Scheffler, Matthias Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-018-05169-6	journal	July 2018
Ultrafast shock synthesis of nanocarbon from a liquid precursor Armstrong, Michael R.; Lindsey, Rebecca K.; Goldman, Nir Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-019-14034-z	journal	January 2020
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks Schwalbe-Koda, Daniel; Tan, Aik Rui; Gómez-Bombarelli, Rafael Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-25342-8	journal	August 2021
Chemistry-mediated Ostwald ripening in carbon-rich C/O systems at extreme conditions Lindsey, Rebecca K.; Goldman, Nir; Fried, Laurence E. Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-29024-x	journal	March 2022
Active machine learning model for the dynamic simulation and growth mechanisms of carbon on metal surface Zhang, Di; Yi, Peiyun; Lai, Xinmin Nature Communications, Vol. 15, Issue 1 https://doi.org/10.1038/s41467-023-44525-z	journal	January 2024
Model-free estimation of completeness, uncertainties, and outliers in atomistic machine learning using information theory Schwalbe-Koda, Daniel; Hamel, Sebastien; Sadigh, Babak Nature Communications, Vol. 16, Issue 1 https://doi.org/10.1038/s41467-025-59232-0	journal	April 2025
On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events Vandermause, Jonathan; Torrisi, Steven B.; Batzner, Simon npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-0283-z	journal	March 2020
Atomistic Line Graph Neural Network for improved materials property predictions Choudhary, Kamal; DeCost, Brian npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00650-1	journal	November 2021
Ultra-fast interpretable machine-learning potentials Xie, Stephen R.; Rupp, Matthias; Hennig, Richard G. npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-01092-7	journal	September 2023
ChIMES Carbon 2.0: A transferable machine-learned interatomic model harnessing multifidelity training data Lindsey, Rebecca K.; Bastea, Sorin; Hamel, Sebastien npj Computational Materials, Vol. 11, Issue 1 https://doi.org/10.1038/s41524-024-01497-y	journal	February 2025
Machine-learned potentials for next-generation matter simulations Friederich, Pascal; Häse, Florian; Proppe, Jonny Nature Materials, Vol. 20, Issue 6 https://doi.org/10.1038/s41563-020-0777-6	journal	May 2021
Comparing molecules and solids across structural and alchemical space De, Sandip; Bartók, Albert P.; Csányi, Gábor Physical Chemistry Chemical Physics, Vol. 18, Issue 20 https://doi.org/10.1039/C6CP00415F	journal	January 2016
A quantitative uncertainty metric controls error in neural network-driven chemical discovery Janet, Jon Paul; Duan, Chenru; Yang, Tzuhsiung Chemical Science, Vol. 10, Issue 34 https://doi.org/10.1039/C9SC02298H	journal	January 2019
Full-dimensional, ab initio potential energy and dipole moment surfaces for water Wang, Yimin; Shepler, Benjamin C.; Braams, Bastiaan J. The Journal of Chemical Physics, Vol. 131, Issue 5 https://doi.org/10.1063/1.3196178	journal	January 2009
Atom-centered symmetry functions for constructing high-dimensional neural network potentials Behler, Jörg The Journal of Chemical Physics, Vol. 134, Issue 7 https://doi.org/10.1063/1.3553717	journal	February 2011
Flexible, ab initio potential, and dipole moment surfaces for water. I. Tests and applications for clusters up to the 22-mer Wang, Yimin; Huang, Xinchuan; Shepler, Benjamin C. The Journal of Chemical Physics, Vol. 134, Issue 9 https://doi.org/10.1063/1.3554905	journal	March 2011
A fingerprint based metric for measuring similarities of crystalline structures Zhu, Li; Amsler, Maximilian; Fuhrer, Tobias The Journal of Chemical Physics, Vol. 144, Issue 3 https://doi.org/10.1063/1.4940026	journal	January 2016
Perspective: Machine learning potentials for atomistic simulations Behler, Jörg The Journal of Chemical Physics, Vol. 145, Issue 17 https://doi.org/10.1063/1.4966192	journal	November 2016
Less is more: Sampling chemical space with active learning Smith, Justin S.; Nebgen, Ben; Lubbers, Nicholas The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5023802	journal	June 2018
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
DFTB+, a software package for efficient approximate density functional theory based atomistic simulations Hourahine, B.; Aradi, B.; Blum, V. The Journal of Chemical Physics, Vol. 152, Issue 12 https://doi.org/10.1063/1.5143190	journal	March 2020
Many-body reactive force field development for carbon condensation in C/O systems under extreme conditions Lindsey, Rebecca K.; Goldman, Nir; Fried, Laurence E. The Journal of Chemical Physics, Vol. 153, Issue 5 https://doi.org/10.1063/5.0012840	journal	August 2020
Active learning for robust, high-complexity reactive atomistic simulations Lindsey, Rebecca K.; Fried, Laurence E.; Goldman, Nir The Journal of Chemical Physics, Vol. 153, Issue 13 https://doi.org/10.1063/5.0021965	journal	October 2020
Investigating 3,4-bis(3-nitrofurazan-4-yl)furoxan detonation with a rapidly tuned density functional tight binding model Lindsey, Rebecca K.; Bastea, Sorin; Goldman, Nir The Journal of Chemical Physics, Vol. 154, Issue 16 https://doi.org/10.1063/5.0047800	journal	April 2021
Machine learned interatomic potential for dispersion strengthened plasma facing components Sikorski, E. L.; Cusentino, M. A.; McCarthy, M. J. The Journal of Chemical Physics, Vol. 158, Issue 11 https://doi.org/10.1063/5.0135269	journal	March 2023
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
Local-environment-guided selection of atomic structures for the development of machine-learning potentials Li, Renzhe; Zhou, Chuan; Singh, Akksay The Journal of Chemical Physics, Vol. 160, Issue 7 https://doi.org/10.1063/5.0187892	journal	February 2024
The Mahalanobis Distance for Functional Data With Applications to Classification Galeano, Pedro; Joseph, Esdras; Lillo, Rosa E. Technometrics, Vol. 57, Issue 2 https://doi.org/10.1080/00401706.2014.902774	journal	April 2015
Permutationally invariant potential energy surfaces in high dimensionality Braams, Bastiaan J.; Bowman, Joel M. International Reviews in Physical Chemistry, Vol. 28, Issue 4 https://doi.org/10.1080/01442350903234923	journal	October 2009
Structure identification methods for atomistic simulations of crystalline materials Stukowski, Alexander Modelling and Simulation in Materials Science and Engineering, Vol. 20, Issue 4 https://doi.org/10.1088/0965-0393/20/4/045021	journal	May 2012
Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations Miksch, April M.; Morawietz, Tobias; Kästner, Johannes Machine Learning: Science and Technology, Vol. 2, Issue 3 https://doi.org/10.1088/2632-2153/abfd96	journal	July 2021
Unified representation of molecules and crystals for machine learning Huo, Haoyan; Rupp, Matthias Machine Learning: Science and Technology, Vol. 3, Issue 4 https://doi.org/10.1088/2632-2153/aca005	journal	November 2022
Ab initiomolecular dynamics for liquid metals Kresse, G.; Hafner, J. Physical Review B, Vol. 47, Issue 1, p. 558-561 https://doi.org/10.1103/PhysRevB.47.558	journal	January 1993
Ab initio molecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium Kresse, G.; Hafner, J. Physical Review B, Vol. 49, Issue 20, p. 14251-14269 https://doi.org/10.1103/PhysRevB.49.14251	journal	May 1994
Projector augmented-wave method Blöchl, P. E. Physical Review B, Vol. 50, Issue 24, p. 17953-17979 https://doi.org/10.1103/PhysRevB.50.17953	journal	December 1994
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set Kresse, G.; Furthmüller, J. Physical Review B, Vol. 54, Issue 16, p. 11169-11186 https://doi.org/10.1103/PhysRevB.54.11169	journal	October 1996
Self-consistent-charge density-functional tight-binding method for simulations of complex materials properties Elstner, M.; Porezag, D.; Jungnickel, G. Physical Review B, Vol. 58, Issue 11, p. 7260-7268 https://doi.org/10.1103/PhysRevB.58.7260	journal	September 1998
From ultrasoft pseudopotentials to the projector augmented-wave method Kresse, G.; Joubert, D. Physical Review B, Vol. 59, Issue 3, p. 1758-1775 https://doi.org/10.1103/PhysRevB.59.1758	journal	January 1999
On representing chemical environments Bartók, Albert P.; Kondor, Risi; Csányi, Gábor Physical Review B, Vol. 87, Issue 18 https://doi.org/10.1103/PhysRevB.87.184115	journal	May 2013
Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations Ward, Logan; Liu, Ruoqian; Krishna, Amar Physical Review B, Vol. 96, Issue 2 https://doi.org/10.1103/PhysRevB.96.024104	journal	July 2017
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
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert Physical Review Letters, Vol. 108, Issue 5 https://doi.org/10.1103/PhysRevLett.108.058301	journal	January 2012
Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics Zhang, Linfeng; Han, Jiequn; Wang, Han Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.143001	journal	April 2018
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties Xie, Tian; Grossman, Jeffrey C. Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.145301	journal	April 2018
Generalized Gradient Approximation Made Simple Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868 https://doi.org/10.1103/PhysRevLett.77.3865	journal	October 1996
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
Active learning of uniformly accurate interatomic potentials for materials simulation Zhang, Linfeng; Lin, De-Ye; Wang, Han Physical Review Materials, Vol. 3, Issue 2 https://doi.org/10.1103/PhysRevMaterials.3.023804	journal	February 2019
Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery Park, Cheol Woo; Wolverton, Chris Physical Review Materials, Vol. 4, Issue 6 https://doi.org/10.1103/PhysRevMaterials.4.063801	journal	June 2020
Metrics for graph comparison: A practitioner’s guide Wills, Peter; Meyer, François G. PLOS ONE, Vol. 15, Issue 2 https://doi.org/10.1371/journal.pone.0228728	journal	February 2020

Similar Records

Davis Computational Spectroscopy Workflow—From Structure to Spectra

Journal Article · Fri Aug 27 00:00:00 UTC 2021 · Journal of Chemical Information and Modeling · OSTI ID:1860888

Cavalcante, L. S. R.; Daemen, Luke L.; Goldman, Nir; +1 more

Intraatomic correlation correction in the FORS model

Journal Article · Thu May 23 04:00:00 UTC 1985 · J. Phys. Chem.; (United States) · OSTI ID:5133773

Lam, B; Schmidt, M W; Ruedenberg, K

Transformer Masked Autoencoders for RF Device Fingerprinting

Conference · Fri Dec 06 04:00:00 UTC 2024 · OSTI ID:2496593

Parpart, Gavin G.; Tu, Jonathan H.; Clymer, Bradley J.; +2 more

Related Subjects

36 MATERIALS SCIENCE
75 CONDENSED MATTER PHYSICS
SUPERCONDUCTIVITY AND SUPERFLUIDITY
97 MATHEMATICS AND COMPUTING
Chemistry
Materials science
Mathematics and Computing
Physics - Condensed matter physics
cluster chemistry
density functional theory
forensic chemistry
liquids
machine learning

Title: Cluster-Graph Fingerprinting: A Framework for Quantitative Analysis of Machine-Learned Interatomic Model Training and Simulation Data

Citation Formats

References (71)

Similar Records

Related Subjects