Automated discovery of a robust interatomic potential for aluminum

Smith, Justin Steven; Nebgen, Benjamin Tyler; Mathew, Nithin; Chen, Jie; Lubbers, Nicholas Edward; Burakovsky, Leonid; Tretiak, Sergei; Nam, Hai Ah; Germann, Timothy Clark; Fensin, Saryu Jindal; Barros, Kipton Marcos

doi:10.1038/s41467-021-21376-0

Automated discovery of a robust interatomic potential for aluminum

Journal Article · Mon Feb 22 23:00:00 EST 2021 · Nature Communications

DOI:https://doi.org/10.1038/s41467-021-21376-0· OSTI ID:1807862

^[1]; ^[1]; ^[1]; ^[1]; ^[1]; ^[1]; ^[1]; ^[1]; ^[1]; ^[1]; ^[1]

Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Machine learning, trained on quantum mechanics (QM) calculations, is a powerful tool for modeling potential energy surfaces. A critical factor is the quality and diversity of the training dataset. Here we present a highly automated approach to dataset construction and demonstrate the method by building a potential for elemental aluminum (ANI-Al). In our active learning scheme, the ML potential under development is used to drive non-equilibrium molecular dynamics simulations with time-varying applied temperatures. Whenever a configuration is reached for which the ML uncertainty is large, new QM data is collected. The ML model is periodically retrained on all available QM data. The final ANI-Al potential makes very accurate predictions of radial distribution function in melt, liquid-solid coexistence curve, and crystal properties such as defect energies and barriers. We perform a 1.3M atom shock simulation and show that ANI-Al force predictions shine in their agreement with new reference DFT calculations.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Office of Science (SC); USDOE Laboratory Directed Research and Development (LDRD) Program; Nicholas C. Metropolis Postdoctoral Fellowship; Center for Nonlinear Studies (CNLS)

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 1807862

Report Number(s):: LA-UR--20-22194

Journal Information:: Nature Communications, Journal Name: Nature Communications Journal Issue: 1 Vol. 12; ISSN 2041-1723

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

References (80)

Hydrogen Transfer in Energetic Materials from ReaxFF and DFT Calculations Sergeev, Oleg V.; Yanilkin, Alexey V. The Journal of Physical Chemistry A, Vol. 121, Issue 16 https://doi.org/10.1021/acs.jpca.6b13088	journal	April 2017
Adaptive machine learning framework to accelerate ab initio molecular dynamics Botu, Venkatesh; Ramprasad, Rampi International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24836	journal	December 2014
Fast Parallel Algorithms for Short-Range Molecular Dynamics Plimpton, Steve Journal of Computational Physics, Vol. 117, Issue 1 https://doi.org/10.1006/jcph.1995.1039	journal	March 1995
High pressure melting and equation of state of aluminium Hänström, A.; Lazor, P. Journal of Alloys and Compounds, Vol. 305, Issue 1-2 https://doi.org/10.1016/S0925-8388(00)00736-2	journal	June 2000
Plastic anisotropy in b.c.c. transition metals Duesbery, M. S.; Vitek, V. Acta Materialia, Vol. 46, Issue 5 https://doi.org/10.1016/S1359-6454(97)00367-4	journal	March 1998
Measurement of the density of liquid aluminum alloys by an x-ray attenuation technique Smith, Patrick M.; Elmer, John W.; Gallegos, Gilbert F. Scripta Materialia, Vol. 40, Issue 8 https://doi.org/10.1016/S1359-6462(99)00043-3	journal	March 1999
The modified embedded-atom method interatomic potentials and recent progress in atomistic simulations Lee, Byeong-Joo; Ko, Won-Seok; Kim, Hyun-Kyu Calphad, Vol. 34, Issue 4 https://doi.org/10.1016/j.calphad.2010.10.007	journal	December 2010
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
Accelerating high-throughput searches for new alloys with active learning of interatomic potentials Gubaev, Konstantin; Podryabinkin, Evgeny V.; Hart, Gus L. W. Computational Materials Science, Vol. 156 https://doi.org/10.1016/j.commatsci.2018.09.031	journal	January 2019
PHON: A program to calculate phonons using the small displacement method Alfè, Dario Computer Physics Communications, Vol. 180, Issue 12 https://doi.org/10.1016/j.cpc.2009.03.010	journal	December 2009
Structural phase transitions in aluminium above 320 GPa Fiquet, Guillaume; Narayana, Chandrabhas; Bellin, Christophe Comptes Rendus Geoscience, Vol. 351, Issue 2-3 https://doi.org/10.1016/j.crte.2018.08.006	journal	February 2019
Active-learning strategies in computer-assisted drug discovery Reker, Daniel; Schneider, Gisbert Drug Discovery Today, Vol. 20, Issue 4 https://doi.org/10.1016/j.drudis.2014.12.004	journal	April 2015
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
A triangulation-based method to identify dislocations in atomistic models Stukowski, Alexander Journal of the Mechanics and Physics of Solids, Vol. 70 https://doi.org/10.1016/j.jmps.2014.06.009	journal	October 2014
Atomic interaction of the MEAM type for the study of intermetallics in the Al–U alloy Pascuet, M. I.; Fernández, J. R. Journal of Nuclear Materials, Vol. 467 https://doi.org/10.1016/j.jnucmat.2015.09.030	journal	December 2015
Computational Surface Chemistry of Tetrahedral Amorphous Carbon by Combining Machine Learning and Density Functional Theory Deringer, Volker L.; Caro, Miguel A.; Jana, Richard Chemistry of Materials, Vol. 30, Issue 21 https://doi.org/10.1021/acs.chemmater.8b02410	journal	September 2018
Machine Learning of Partial Charges Derived from High-Quality Quantum-Mechanical Calculations Bleiziffer, Patrick; Schaller, Kay; Riniker, Sereina Journal of Chemical Information and Modeling, Vol. 58, Issue 3 https://doi.org/10.1021/acs.jcim.7b00663	journal	February 2018
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
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 Force Fields: Construction, Validation, and Outlook Botu, V.; Batra, R.; Chapman, J. The Journal of Physical Chemistry C, Vol. 121, Issue 1 https://doi.org/10.1021/acs.jpcc.6b10908	journal	December 2016
On-the-Fly Active Learning of Interatomic Potentials for Large-Scale Atomistic Simulations Jinnouchi, Ryosuke; Miwa, Kazutoshi; Karsai, Ferenc The Journal of Physical Chemistry Letters, Vol. 11, Issue 17 https://doi.org/10.1021/acs.jpclett.0c01061	journal	July 2020
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
Stacking fault energies and slip in nanocrystalline metals Van Swygenhoven, H.; Derlet, P. M.; Frøseth, A. G. Nature Materials, Vol. 3, Issue 6 https://doi.org/10.1038/nmat1136	journal	May 2004
Physically informed artificial neural networks for atomistic modeling of materials Pun, G. P. Purja; Batra, R.; Ramprasad, R. Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-10343-5	journal	May 2019
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning Smith, Justin S.; Nebgen, Benjamin T.; Zubatyuk, Roman Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-10827-4	journal	July 2019
A universal strategy for the creation of machine learning-based atomistic force fields Huan, Tran Doan; Batra, Rohit; Chapman, James npj Computational Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s41524-017-0042-y	journal	September 2017
De novo exploration and self-guided learning of potential-energy surfaces Bernstein, Noam; Csányi, Gábor; Deringer, Volker L. npj Computational Materials, Vol. 5, Issue 1 https://doi.org/10.1038/s41524-019-0236-6	journal	October 2019
Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide Sivaraman, Ganesh; Krishnamoorthy, Anand Narayanan; Baur, Matthias npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-00367-7	journal	July 2020
Machine learning for molecular and materials science Butler, Keith T.; Davies, Daniel W.; Cartwright, Hugh Nature, Vol. 559, Issue 7715 https://doi.org/10.1038/s41586-018-0337-2	journal	July 2018
Energy-free machine learning force field for aluminum Kruglov, Ivan; Sergeev, Oleg; Yanilkin, Alexey Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-08455-3	journal	August 2017
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost Smith, J. S.; Isayev, O.; Roitberg, A. E. Chemical Science, Vol. 8, Issue 4 https://doi.org/10.1039/C6SC05720A	journal	January 2017
Machine learning molecular dynamics for the simulation of infrared spectra Gastegger, Michael; Behler, Jörg; Marquetand, Philipp Chemical Science, Vol. 8, Issue 10 https://doi.org/10.1039/C7SC02267K	journal	January 2017
The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics Yao, Kun; Herr, John E.; Toth, David W. Chemical Science, Vol. 9, Issue 8 https://doi.org/10.1039/C7SC04934J	journal	January 2018
The melting lines of model systems calculated from coexistence simulations Morris, James R.; Song, Xueyu The Journal of Chemical Physics, Vol. 116, Issue 21 https://doi.org/10.1063/1.1474581	journal	June 2002
Reference Data for the Density and Viscosity of Liquid Aluminum and Liquid Iron Assael, Marc J.; Kakosimos, Konstantinos; Banish, R. Michael Journal of Physical and Chemical Reference Data, Vol. 35, Issue 1 https://doi.org/10.1063/1.2149380	journal	March 2006
General formulation of pressure and stress tensor for arbitrary many-body interaction potentials under periodic boundary conditions Thompson, Aidan P.; Plimpton, Steven J.; Mattson, William The Journal of Chemical Physics, Vol. 131, Issue 15 https://doi.org/10.1063/1.3245303	journal	October 2009
High energy x-ray scattering studies of the local order in liquid Al Mauro, N. A.; Bendert, J. C.; Vogt, A. J. The Journal of Chemical Physics, Vol. 135, Issue 4 https://doi.org/10.1063/1.3609925	journal	July 2011
A neural network potential-energy surface for the water dimer based on environment-dependent atomic energies and charges Morawietz, Tobias; Sharma, Vikas; Behler, Jörg The Journal of Chemical Physics, Vol. 136, Issue 6 https://doi.org/10.1063/1.3682557	journal	February 2012
On fluid-solid direct coexistence simulations: The pseudo-hard sphere model Espinosa, Jorge R.; Sanz, Eduardo; Valeriani, Chantal The Journal of Chemical Physics, Vol. 139, Issue 14 https://doi.org/10.1063/1.4823499	journal	October 2013
Molecular dynamics simulations of shock waves in hydroxyl-terminated polybutadiene melts: Mechanical and structural responses Fröhlich, Markus G.; Sewell, Thomas D.; Thompson, Donald L. The Journal of Chemical Physics, Vol. 140, Issue 2 https://doi.org/10.1063/1.4853695	journal	January 2014
Spherical harmonics based descriptor for neural network potentials: Structure and dynamics of Au ₁₄₇ nanocluster Jindal, Shweta; Chiriki, Siva; Bulusu, Satya S. The Journal of Chemical Physics, Vol. 146, Issue 20 https://doi.org/10.1063/1.4983392	journal	May 2017
Machine learning of molecular properties: Locality and active learning Gubaev, Konstantin; Podryabinkin, Evgeny V.; Shapeev, Alexander V. The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5005095	journal	June 2018
Hierarchical modeling of molecular energies using a deep neural network Lubbers, Nicholas; Smith, Justin S.; Barros, Kipton The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5011181	journal	June 2018
SchNet – A deep learning architecture for molecules and materials Schütt, K. T.; Sauceda, H. E.; Kindermans, P. -J. The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5019779	journal	June 2018
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
Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions Nguyen, Thuong T.; Székely, Eszter; Imbalzano, Giulio The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5024577	journal	June 2018
An entropy-maximization approach to automated training set generation for interatomic potentials Karabin, Mariia; Perez, Danny The Journal of Chemical Physics, Vol. 153, Issue 9 https://doi.org/10.1063/5.0013059	journal	September 2020
Analysis of semi-empirical interatomic potentials appropriate for simulation of crystalline and liquid Al and Cu Mendelev, M. I.; Kramer, M. J.; Becker, C. A. Philosophical Magazine, Vol. 88, Issue 12 https://doi.org/10.1080/14786430802206482	journal	April 2008
Intrinsic stacking faults in body-centred cubic crystals Vítek, V. Philosophical Magazine, Vol. 18, Issue 154 https://doi.org/10.1080/14786436808227500	journal	October 1968
Aluminium interatomic potential from density functional theory calculations with improved stacking fault energy Liu, Xiang-Yang; Ercolessi, Furio; Adams, James B. Modelling and Simulation in Materials Science and Engineering, Vol. 12, Issue 4 https://doi.org/10.1088/0965-0393/12/4/007	journal	May 2004
A thermodynamic approach to determine accurate potentials for molecular dynamics simulations: thermoelastic response of aluminum Winey, J. M.; Kubota, Alison; Gupta, Y. M. Modelling and Simulation in Materials Science and Engineering, Vol. 17, Issue 5 https://doi.org/10.1088/0965-0393/17/5/055004	journal	June 2009
Visualization and analysis of atomistic simulation data with OVITO–the Open Visualization Tool Stukowski, Alexander Modelling and Simulation in Materials Science and Engineering, Vol. 18, Issue 1 https://doi.org/10.1088/0965-0393/18/1/015012	journal	December 2009
openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding Poličar, Pavlin G.; Stražar, Martin; Zupan, Blaž https://doi.org/10.1101/731877	posted_content	August 2019
Canonical dynamics: Equilibrium phase-space distributions Hoover, William G. Physical Review A, Vol. 31, Issue 3 https://doi.org/10.1103/PhysRevA.31.1695	journal	March 1985
Melting line of aluminum from simulations of coexisting phases Morris, J. R.; Wang, C. Z.; Ho, K. M. Physical Review B, Vol. 49, Issue 5 https://doi.org/10.1103/PhysRevB.49.3109	journal	February 1994
Interatomic potentials for monoatomic metals from experimental data and ab initio calculations Mishin, Y.; Farkas, D.; Mehl, M. J. Physical Review B, Vol. 59, Issue 5 https://doi.org/10.1103/PhysRevB.59.3393	journal	February 1999
Thermodynamics of hexagonal-close-packed iron under Earth’s core conditions Alfè, D.; Price, G. D.; Gillan, M. J. Physical Review B, Vol. 64, Issue 4 https://doi.org/10.1103/PhysRevB.64.045123	journal	July 2001
Interatomic potentials for atomistic simulations of the Ti-Al system Zope, Rajendra R.; Mishin, Y. Physical Review B, Vol. 68, Issue 2 https://doi.org/10.1103/PhysRevB.68.024102	journal	July 2003
Rapid estimation of elastic constants by molecular dynamics simulation under constant stress Shinoda, Wataru; Shiga, Motoyuki; Mikami, Masuhiro Physical Review B, Vol. 69, Issue 13 https://doi.org/10.1103/PhysRevB.69.134103	journal	April 2004
Multistate modified embedded atom method Baskes, M. I.; Srinivasan, S. G.; Valone, S. M. Physical Review B, Vol. 75, Issue 9 https://doi.org/10.1103/PhysRevB.75.094113	journal	March 2007
Bulk aluminum at high pressure: A first-principles study Tambe, Michael J.; Bonini, Nicola; Marzari, Nicola Physical Review B, Vol. 77, Issue 17 https://doi.org/10.1103/PhysRevB.77.172102	journal	May 2008
Highly optimized embedded-atom-method potentials for fourteen fcc metals Sheng, H. W.; Kramer, M. J.; Cadien, A. Physical Review B, Vol. 83, Issue 13 https://doi.org/10.1103/PhysRevB.83.134118	journal	April 2011
Accuracy and transferability of Gaussian approximation potential models for tungsten Szlachta, Wojciech J.; Bartók, Albert P.; Csányi, Gábor Physical Review B, Vol. 90, Issue 10 https://doi.org/10.1103/PhysRevB.90.104108	journal	September 2014
Multiphase aluminum equations of state via density functional theory Sjostrom, Travis; Crockett, Scott; Rudin, Sven Physical Review B, Vol. 94, Issue 14 https://doi.org/10.1103/PhysRevB.94.144101	journal	October 2016
Machine learning based interatomic potential for amorphous carbon Deringer, Volker L.; Csányi, Gábor Physical Review B, Vol. 95, Issue 9 https://doi.org/10.1103/PhysRevB.95.094203	journal	March 2017
Machine learning for molecular dynamics with strongly correlated electrons Suwa, Hidemaro; Smith, Justin S.; Lubbers, Nicholas Physical Review B, Vol. 99, Issue 16 https://doi.org/10.1103/PhysRevB.99.161107	journal	April 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
Molecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces Li, Zhenwei; Kermode, James R.; De Vita, Alessandro Physical Review Letters, Vol. 114, Issue 9 https://doi.org/10.1103/PhysRevLett.114.096405	journal	March 2015
Data-Driven Learning of Total and Local Energies in Elemental Boron Deringer, Volker L.; Pickard, Chris J.; Csányi, Gábor Physical Review Letters, Vol. 120, Issue 15 https://doi.org/10.1103/PhysRevLett.120.156001	journal	April 2018
Semiempirical, Quantum Mechanical Calculation of Hydrogen Embrittlement in Metals Daw, Murray S.; Baskes, M. I. Physical Review Letters, Vol. 50, Issue 17 https://doi.org/10.1103/PhysRevLett.50.1285	journal	April 1983
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
Neural network potential for Al-Mg-Si alloys Kobayashi, Ryo; Giofré, Daniele; Junge, Till Physical Review Materials, Vol. 1, Issue 5 https://doi.org/10.1103/PhysRevMaterials.1.053604	journal	October 2017
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
Pushing the Limit of Molecular Dynamics with Ab Initio Accuracy to 100 Million Atoms with Machine Learning Jia, Weile; Wang, Han; Chen, Mohan SC20: International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1109/SC41405.2020.00009	conference	November 2020
Next generation interatomic potentials for condensed systems Handley, Christopher Michael; Behler, Jörg The European Physical Journal B, Vol. 87, Issue 7 https://doi.org/10.1140/epjb/e2014-50070-0	journal	July 2014
Query by committee Seung, H. S.; Opper, M.; Sompolinsky, H. Proceedings of the fifth annual workshop on Computational learning theory - COLT '92 https://doi.org/10.1145/130385.130417	conference	January 1992
Ab initio Force Constant Approach to Phonon Dispersion Relations of Diamond and Graphite Kresse, G.; Furthmüller, J.; Hafner, J. Europhysics Letters (EPL), Vol. 32, Issue 9 https://doi.org/10.1209/0295-5075/32/9/005	journal	December 1995
DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models Zhang, Yuzhi Mendeley https://doi.org/10.17632/sxybkgc5xc	dataset	January 2020
Simple and efficient algorithms for training machine learning potentials to force data Smith, Justin; Lubbers, Nicholas; Thompson, Aidan P. https://doi.org/10.2172/1763572	report	June 2020
Positron Lifetime Spectroscopy and Trapping at Vacancies in Aluminium Schaefer, Hans Eckhardt; Gugelmeier, R.; Schmolz, M. Materials Science Forum, Vol. 15-18 https://doi.org/10.4028/www.scientific.net/MSF.15-18.111	journal	January 1987

Similar Records

Active Learning Framework

Software · Tue Jan 03 19:00:00 EST 2023 · OSTI ID:code-115537

Learning together: Towards foundation models for machine learning interatomic potentials with meta-learning

Journal Article · Wed Jul 17 00:00:00 EDT 2024 · npj Computational Materials · OSTI ID:2403610

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
computational chemistry
computational science
method development
molecular dynamics

Automated discovery of a robust interatomic potential for aluminum

Citation Formats

References (80)

Similar Records

Related Subjects