The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Descriptors representing two- and three-body atomic distributions and their effects on the accuracy of machine-learned inter-atomic potentials
Abstract
When determining machine-learning models for inter-atomic potentials, the potential energy surface is often described as a non-linear function of descriptors representing two- and three-body atomic distribution functions. It is not obvious how the choice of the descriptors affects the efficiency of the training and the accuracy of the final machine-learned model. In this work, we formulate an efficient method to calculate descriptors that can separately represent two- and three-body atomic distribution functions, and we examine the effects of including only two- or three-body descriptors, as well as including both, in the regression model. Our study indicates that non-linear mixing of two- and three-body descriptors is essential for an efficient training and a high accuracy of the final machine-learned model. The efficiency can be further improved by weighting the two-body descriptors more strongly. We furthermore examine a sparsification of the three-body descriptors. The three-body descriptors usually provide redundant representations of the atomistic structure, and the number of descriptors can be significantly reduced without loss of accuracy by applying an automatic sparsification using a principal component analysis. Visualization of the reduced descriptors using three-body distribution functions in real-space indicates that the sparsification automatically removes the components that are less significant for describing the distribution function.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Generalized Gradient Approximation Made Simple
Perdew, J. P., Burke, K., & Ernzerhof, M. (1996) · Physical Review Letters · doi:10.1103/physrevlett.77.3865 · Cited by 215,824
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
Kresse, G., & Furthmüller, J. (1996) · Physical Review B · doi:10.1103/physrevb.54.11169 · Cited by 123,652
Self-citationProjector augmented-wave method
Blöchl, P. E. (1994) · Physical Review B · doi:10.1103/physrevb.50.17953 · Cited by 92,732
From ultrasoft pseudopotentials to the projector augmented-wave method
Kresse, G., & Joubert, D. (1999) · Physical Review B · doi:10.1103/physrevb.59.1758 · Cited by 85,307
Self-citationKresse, G., & Furthmüller, J. (1996) · Computational Materials Science · doi:10.1016/0927-0256(96)00008-0 · Cited by 75,638
Self-citationPolymorphic transitions in single crystals: A new molecular dynamics method
Parrinello, M., & Rahman, A. (1981) · Journal of Applied Physics · doi:10.1063/1.328693 · Cited by 19,790
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Behler, J., & Parrinello, M. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.146401 · Cited by 5,010
Crystal Structure and Pair Potentials: A Molecular-Dynamics Study
Parrinello, M., & Rahman, A. (1980) · Physical Review Letters · doi:10.1103/physrevlett.45.1196 · Cited by 3,701
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
Bartók, A. P., Payne, M. C., Kondor, R., & Csányi, G. (2010) · Physical Review Letters · doi:10.1103/physrevlett.104.136403 · Cited by 3,242
On representing chemical environments
Bartók, A. P., Kondor, R., & Csányi, G. (2013) · Physical Review B · doi:10.1103/physrevb.87.184115 · Cited by 2,572
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
Rupp, M., Tkatchenko, A., Müller, K.-R., & von Lilienfeld, O. A. (2012) · Physical Review Letters · doi:10.1103/physrevlett.108.058301 · Cited by 2,312
Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
Shapeev, A. V. (2016) · Multiscale Modeling & Simulation · doi:10.1137/15m1054183 · Cited by 1,510
Machine learning of accurate energy-conserving molecular force fields
Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, I., Schütt, K. T., & Müller, K.-R. (2017) · Science Advances · doi:10.1126/sciadv.1603015 · Cited by 1,175
Machine Learning Interatomic Potentials as Emerging Tools for Materials Science
Deringer, V. L., Caro, M. A., & Csányi, G. (2019) · Advanced Materials · doi:10.1002/adma.201902765 · Cited by 1,036
Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations
Behler, J. (2011) · Physical Chemistry Chemical Physics · doi:10.1039/c1cp21668f · Cited by 781
CUR matrix decompositions for improved data analysis
Mahoney, M. W., & Drineas, P. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0803205106 · Cited by 773
Machine learning unifies the modeling of materials and molecules
Bartók, A. P., De, S., Poelking, C., Bernstein, N., Kermode, J. R., Csányi, G., & Ceriotti, M. (2017) · Science Advances · doi:10.1126/sciadv.1701816 · Cited by 764
Behler, J. (2017) · Angewandte Chemie International Edition · doi:10.1002/anie.201703114 · Cited by 707
On-the-fly machine learning force field generation: Application to melting points
Jinnouchi, R., Karsai, F., & Kresse, G. (2019) · Physical Review B · doi:10.1103/physrevb.100.014105 · Cited by 680
Self-citationMachine learning based interatomic potential for amorphous carbon
Deringer, V. L., & Csányi, G. (2017) · Physical Review B · doi:10.1103/physrevb.95.094203 · Cited by 669
Jinnouchi, R., Lahnsteiner, J., Karsai, F., Kresse, G., & Bokdam, M. (2019) · Physical Review Letters · doi:10.1103/physrevlett.122.225701 · Cited by 635
Self-citationMolecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces
Li, Z., Kermode, J. R., & De Vita, A. (2015) · Physical Review Letters · doi:10.1103/physrevlett.114.096405 · Cited by 633
Gaussian approximation potentials: A brief tutorial introduction
Bartók, A. P., & Csányi, G. (2015) · International Journal of Quantum Chemistry · doi:10.1002/qua.24927 · Cited by 617
Machine Learning Force Fields: Construction, Validation, and Outlook
Botu, V., Batra, R., Chapman, J., & Ramprasad, R. (2017) · The Journal of Physical Chemistry C · doi:10.1021/acs.jpcc.6b10908 · Cited by 515
How van der Waals interactions determine the unique properties of water
Morawietz, T., Singraber, A., Dellago, C., & Behler, J. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1602375113 · Cited by 495
Machine Learning a General-Purpose Interatomic Potential for Silicon
Bartók, A. P., Kermode, J., Bernstein, N., & Csányi, G. (2018) · Physical Review X · doi:10.1103/physrevx.8.041048 · Cited by 470
Accelerating high-throughput searches for new alloys with active learning of interatomic potentials
Gubaev, K., Podryabinkin, E. V., Hart, G. L. W., & Shapeev, A. V. (2019) · Computational Materials Science · doi:10.1016/j.commatsci.2018.09.031 · Cited by 359
Nucleation mechanism for the direct graphite-to-diamond phase transition
Khaliullin, R. Z., Eshet, H., Kühne, T. D., Behler, J., & Parrinello, M. (2011) · Nature Materials · doi:10.1038/nmat3078 · Cited by 354
Alchemical and structural distribution based representation for universal quantum machine learning
Faber, F. A., Christensen, A. S., Huang, B., & von Lilienfeld, O. A. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5020710 · Cited by 334
Imbalzano, G., Anelli, A., Giofré, D., Klees, S., Behler, J., & Ceriotti, M. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5024611 · Cited by 330
Accuracy and transferability of Gaussian approximation potential models for tungsten
Szlachta, W. J., Bartók, A. P., & Csányi, G. (2014) · Physical Review B · doi:10.1103/physrevb.90.104108 · Cited by 327
High-dimensional neural network potentials for metal surfaces: A prototype study for copper
Artrith, N., & Behler, J. (2012) · Physical Review B · doi:10.1103/physrevb.85.045439 · Cited by 325
Huang, B., & von Lilienfeld, O. A. (2016) · The Journal of Chemical Physics · doi:10.1063/1.4964627 · Cited by 294
Moment Tensor PotentialsPreprint
Shapeev, A. V. (2016) · arXiv (Cornell University) · Cited by 288
Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm
Jinnouchi, R., & Asahi, R. (2017) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.7b02010 · Cited by 261
Self-citationBehler, J., Martoňák, R., Donadio, D., & Parrinello, M. (2008) · Physical Review Letters · doi:10.1103/physrevlett.100.185501 · Cited by 233
A universal strategy for the creation of machine learning-based atomistic force fields
Huan, T. D., Batra, R., Chapman, J., Krishnan, S., Chen, L., & Ramprasad, R. (2017) · npj Computational Materials · doi:10.1038/s41524-017-0042-y · Cited by 230
Natarajan, S. K., & Behler, J. (2016) · Physical Chemistry Chemical Physics · doi:10.1039/c6cp05711j · Cited by 209
Incompleteness of Atomic Structure Representations
Pozdnyakov, S. N., Willatt, M. J., Bartók, A. P., Ortner, C., Csányi, G., & Ceriotti, M. (2020) · Physical Review Letters · doi:10.1103/physrevlett.125.166001 · Cited by 197
Atom-density representations for machine learning
Willatt, M. J., Musil, F., & Ceriotti, M. (2019) · The Journal of Chemical Physics · doi:10.1063/1.5090481 · Cited by 179
Fast Crystallization of the Phase Change Compound GeTe by Large-Scale Molecular Dynamics Simulations
Sosso, G. C., Miceli, G., Caravati, S., Giberti, F., Behler, J., & Bernasconi, M. (2013) · The Journal of Physical Chemistry Letters · doi:10.1021/jz402268v · Cited by 165
Modeling the Phase-Change Memory Material, Ge2Sb2Te5, with a Machine-Learned Interatomic Potential
Mocanu, F. C., Konstantinou, K., Lee, T. H., Bernstein, N., Deringer, V. L., Cśanyi, G., & Elliott, S. R. (2018) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.8b06476 · Cited by 164
Miguel, A. (2019) · Physical review. B./Physical review. B · doi:10.1103/physrevb.100.024112 · Cited by 161
Representing molecule-surface interactions with symmetry-adapted neural networks
Behler, J., Lorenz, S., & Reuter, K. (2007) · The Journal of Chemical Physics · doi:10.1063/1.2746232 · Cited by 159
Efficient nonparametric n -body force fields from machine learning
Glielmo, A., Zeni, C., & Vita, A. D. (2018) · Physical review. B./Physical review. B · doi:10.1103/physrevb.97.184307 · Cited by 151
Willatt, M. J., Musil, F., & Ceriotti, M. (2018) · Physical Chemistry Chemical Physics · doi:10.1039/c8cp05921g · Cited by 141
Artrith, N., Hiller, B., & Behler, J. (2012) · physica status solidi (b) · doi:10.1002/pssb.201248370 · Cited by 130
Representing molecule-surface interactions with symmetry-adapted neural networks
Behler, J., Lorenz, S., & Reuter, K. (2007) · Max Planck Institute for Plasma Physics · Cited by 100
Interatomic potential construction with self-learning and adaptive database
Miwa, K., & Ohno, H. (2017) · Physical Review Materials · doi:10.1103/physrevmaterials.1.053801 · Cited by 43
Molecular dynamics study on β -phase vanadium monohydride with machine learning potential
Miwa, K., & Ohno, H. (2016) · Physical review. B./Physical review. B · doi:10.1103/physrevb.94.184109 · Cited by 32
Huang, M., Zhou, X., Zhang, Y., Zhou, L., Alducin, M., Jiang, B., & Guo, H. (2019) · Physical review. B./Physical review. B · doi:10.1103/physrevb.100.201407 · Cited by 32
Cited by
Gaussian Process Regression for Materials and Molecules
Deringer, V. L., Bartók, A. P., Bernstein, N., Wilkins, D. M., Ceriotti, M., & Csányi, G. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00022 · Cited by 1,221
Four Generations of High-Dimensional Neural Network Potentials
Behler, J. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.0c00868 · Cited by 873
Physics-Inspired Structural Representations for Molecules and Materials
Musil, F., Grisafi, A., Bartók, A. P., Ortner, C., Csányi, G., & Ceriotti, M. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00021 · Cited by 523
Zheng, M., & Bukowski, B. C. (2024) · The Journal of Physical Chemistry C · doi:10.1021/acs.jpcc.4c01087 · Cited by 18
A solution for 4-propylguaiacol hydrodeoxygenation without ring saturation
Zhang, Z., Li, Q., Wu, X., Bourmaud, C., Vlachos, D. G., Luterbacher, J., Bodi, A., & Hemberger, P. (2024) · Nature Communications · doi:10.1038/s41467-024-50724-z · Cited by 13
Metadata
- Authors
- Jinnouchi, R., Karsai, F., Verdi, C., Asahi, R., & Kresse, G.
- Venue
- The Journal of Chemical Physics
- Publisher
- AIP Publishing
- Published
- 2020-06-15
- Volume
- 152
- Issue
- 23
- Pages
- 234102-234102
- ISSN
- 0021-9606 (ISSN-L)
- 1089-7690
- OpenAlex
- W3035752258
- Cited by
- 256
- References
- 51
- FWCI
- 5.31
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.