The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
On representing chemical environments
Open accessAbstract
We review some recently published methods to represent atomic neighborhood environments, and analyze their relative merits in terms of their faithfulness and suitability for fitting potential energy surfaces. The crucial properties that such representations (sometimes called descriptors) must have are differentiability with respect to moving the atoms and invariance to the basic symmetries of physics: rotation, reflection, translation, and permutation of atoms of the same species. We demonstrate that certain widely used descriptors that initially look quite different are specific cases of a general approach, in which a finite set of basis functions with increasing angular wave numbers are used to expand the atomic neighborhood density function. Using the example system of small clusters, we quantitatively show that this expansion needs to be carried to higher and higher wave numbers as the number of neighbors increases in order to obtain a faithful representation, and that variants of the descriptors converge at very different rates. We also propose an altogether different approach, called Smooth Overlap of Atomic Positions, that sidesteps these difficulties by directly defining the similarity between any two neighborhood environments, and show that it is still closely connected to the invariant descriptors. We test the performance of the various representations by fitting models to the potential energy surface of small silicon clusters and the bulk crystal.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“General-purpose and systematically-convergent descriptions of chemical environments, such as those that are typically used to fit potentials or predict molecular properties 31,35 , provide a starting point that is considerably less biased than descriptors based on complicated heuristics that are designed from the outset to identify e.g. a stacking order, or the coordination of a site.”
From Unsupervised machine learning in atomistic simulations, between predictions and understanding (2019) · cites this paper as [31]
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 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
Information Theory, Inference, and Learning Algorithms
(2004) · Kybernetes · doi:10.1108/03684920410534506 · Cited by 4,937
Quantum Theory of Angular Momentum
Варшалович, Д. А., Moskalev, A. N., & Khersonskii, V. K. (1988) · WORLD SCIENTIFIC eBooks · doi:10.1142/0270 · Cited by 3,980
Bond-orientational order in liquids and glasses
Steinhardt, P. J., Nelson, D. R., & Ronchetti, M. (1983) · Physical review. B, Condensed matter · doi:10.1103/physrevb.28.784 · Cited by 3,511
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
Self-citationQuantum Theory Of Angular Momemtum
Варшалович, Д. А., Moskalev, A. N., & Khersonskii, V. K. (1988) · Cited by 3,060
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
Porezag, D. V., Frauenheim, T., Köhler, T., Seifert, G., & Kaschner, R. (1995) · Physical review. B, Condensed matter · doi:10.1103/physrevb.51.12947 · Cited by 2,191
Atom-centered symmetry functions for constructing high-dimensional neural network potentials
Behler, J. (2011) · The Journal of Chemical Physics · doi:10.1063/1.3553717 · Cited by 1,663
The Classical Groups: Their Invariants and Representations
Weyl, H. (1947) · doi:10.1515/9781400883905 · Cited by 1,603
Partridge, H., & Schwenke, D. W. (1997) · The Journal of Chemical Physics · doi:10.1063/1.473987 · Cited by 1,158
AtomEye: an efficient atomistic configuration viewer
Li, J. (2003) · Modelling and Simulation in Materials Science and Engineering · doi:10.1088/0965-0393/11/2/305 · Cited by 1,157
Permutationally invariant potential energy surfaces in high dimensionality
Braams, B., & Bowman, J. (2009) · International Reviews in Physical Chemistry · doi:10.1080/01442350903234923 · Cited by 841
Neural network models of potential energy surfaces
Blank, T. B., Brown, S. D., Calhoun, A. W., & Doren, D. J. (1995) · The Journal of Chemical Physics · doi:10.1063/1.469597 · Cited by 502
Molecular potential energy surfaces by interpolation
Ischtwan, J., & Collins, M. A. (1994) · The Journal of Chemical Physics · doi:10.1063/1.466801 · Cited by 475
Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networks
Lorenz, S., Groß, A., & Scheffler, M. (2004) · Chemical Physics Letters · doi:10.1016/j.cplett.2004.07.076 · Cited by 402
Molecular potential-energy surfaces for chemical reaction dynamics
Collins, M. A. (2002) · Theoretical Chemistry Accounts · doi:10.1007/s00214-002-0383-5 · Cited by 401
High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide
Artrith, N., Morawietz, T., & Behler, J. (2011) · Physical Review B · doi:10.1103/physrevb.83.153101 · Cited by 395
Computer simulation study of free energy barriers in crystal nucleation
van Duijneveldt, J. S., & Frenkel, D. (1992) · The Journal of Chemical Physics · doi:10.1063/1.462802 · Cited by 394
Real-Space Structure of Colloidal Hard-Sphere Glasses
van Blaaderen, A., & Wiltzius, P. (1995) · Science · doi:10.1126/science.270.5239.1177 · Cited by 381
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 326
The double-funnel energy landscape of the 38-atom Lennard-Jones cluster
Doye, J. P. K., Miller, M. A., & Wales, D. J. (1999) · The Journal of Chemical Physics · doi:10.1063/1.478595 · Cited by 311
Ab initio potential energy and dipole moment surfaces for H5O2+
Huang, X., Braams, B. J., & Bowman, J. M. (2005) · The Journal of Chemical Physics · doi:10.1063/1.1834500 · Cited by 292
Temperature and pressure dependent solubility of oxygen in water: a thermodynamic analysis
Tromans, D. (1998) · Hydrometallurgy · doi:10.1016/s0304-386x(98)00007-3 · Cited by 292
Gaussian Processes for Machine Learning
Ounpraseuth, S. (2008) · Journal of the American Statistical Association · doi:10.1198/jasa.2008.s219 · Cited by 282
Behler, J., Martoňák, R., Donadio, D., & Parrinello, M. (2008) · Physical Review Letters · doi:10.1103/physrevlett.100.185501 · Cited by 235
Gaussian Processes: A Method for Automatic QSAR Modeling of ADME Properties
Obrezanova, O., Cśanyi, G., Gola, J. M. R., & Segall, M. (2007) · Journal of Chemical Information and Modeling · doi:10.1021/ci7000633 · Cited by 214
New classical models for silicon structural energies
Biswas, R., & Hamann, D. R. (1987) · Physical review. B, Condensed matter · doi:10.1103/physrevb.36.6434 · Cited by 211
Highly compressed ammonia forms an ionic crystal
Pickard, C. J., & Needs, R. J. (2008) · Nature Materials · doi:10.1038/nmat2261 · Cited by 198
A Nested Molecule-Independent Neural Network Approach for High-Quality Potential Fits
Manzhos, S., Wang, X., Dawes, R., & Carrington, T. (2005) · The Journal of Physical Chemistry A · doi:10.1021/jp055253z · Cited by 197
Wales, D. J. (2001) · Cambridge University Press eBooks · doi:10.1017/cbo9780511721724 · Cited by 193
Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity
Swamidass, S. J., Chen, J. H., Bruand, J., Phung, P. T., Ralaivola, L., & Baldi, P. (2005) · Bioinformatics · doi:10.1093/bioinformatics/bti1055 · Cited by 192
Morawietz, T., Sharma, V., & Behler, J. (2012) · The Journal of Chemical Physics · doi:10.1063/1.3682557 · Cited by 185
Using neural networks to represent potential surfaces as sums of products
Manzhos, S., & Carrington, T. (2006) · The Journal of Chemical Physics · doi:10.1063/1.2387950 · Cited by 184
A global H2O potential energy surface for the reaction O(1D)+H2→OH+H
Ho, T., Hollebeek, T., RABITZ, H. A., Harding, L. B., & Schatz, G. C. (1996) · The Journal of Chemical Physics · doi:10.1063/1.472977 · Cited by 177
Efficient Sampling of Atomic Configurational Spaces
Pártay, L. B., Bartók, A. P., & Cśanyi, G. (2010) · The Journal of Physical Chemistry B · doi:10.1021/jp1012973 · Cited by 154
Self-citationNeural Networks in Chemical Reaction Dynamics
Raff, L. M., Komanduri, R., Hagan, M., & Bukkapatnam, S. (2012) · Oxford University Press eBooks · doi:10.1093/oso/9780199765652.001.0001 · Cited by 133
Representation of Intermolecular Potential Functions by Neural Networks
Gassner, H., Probst, M. M., Lauenstein, A., & Hermansson, K. (1998) · The Journal of Physical Chemistry A · doi:10.1021/jp972209d · Cited by 132
Classical and quasiclassical spectral analysis of CH5+ using an ab initio potential energy surface
Brown, A., Braams, B. J., Christoffel, K. M., Jin, Z., & Bowman, J. M. (2003) · The Journal of Chemical Physics · doi:10.1063/1.1622379 · Cited by 109
Maisuradze, G. G., Thompson, D. L., Wagner, A. F., & Minkoff, M. (2003) · The Journal of Chemical Physics · doi:10.1063/1.1617271 · Cited by 102
Crystal fingerprint space – a novel paradigm for studying crystal-structure sets
Valle, M., & Оганов, А. Р. (2010) · Acta Crystallographica Section A Foundations of Crystallography · doi:10.1107/s0108767310026395 · Cited by 99
An accurate analytic representation of the water pair potential
Cencek, W., Szalewicz, K., Leforestier, C., van Harrevelt, R., & van der Avoird, A. (2008) · Physical Chemistry Chemical Physics · doi:10.1039/b809435g · Cited by 99
An ab initio potential surface describing abstraction and exchange for H+CH4
Zhang, X., Braams, B. J., & Bowman, J. M. (2006) · The Journal of Chemical Physics · doi:10.1063/1.2162532 · Cited by 84
Quantum Calculations of Vibrational Energies of H3O2- on an ab Initio Potential
Huang, X., Braams, B. J., Carter, S. D., & Bowman, J. M. (2004) · Journal of the American Chemical Society · doi:10.1021/ja049801i · Cited by 83
Microscopic Origins of the Anomalous Melting Behavior of Sodium under High Pressure
Eshet, H., Khaliullin, R. Z., Kühne, T. D., Behler, J., & Parrinello, M. (2012) · Physical Review Letters · doi:10.1103/physrevlett.108.115701 · Cited by 77
Dynamically Polarizable Water Potential Based on Multipole Moments Trained by Machine Learning
Handley, C. M., & Popelier, P. L. A. (2009) · Journal of Chemical Theory and Computation · doi:10.1021/ct800468h · Cited by 71
Mountain, R. D., & Brown, A. C. (1984) · The Journal of Chemical Physics · doi:10.1063/1.447070 · Cited by 68
Guo, Y., Kawano, A., Thompson, D. L., Wagner, A. F., & Minkoff, M. (2004) · The Journal of Chemical Physics · doi:10.1063/1.1777572 · Cited by 67
Kaufmann, K., & Baumeister, W. P. (1989) · Journal of Physics B Atomic Molecular and Optical Physics · doi:10.1088/0953-4075/22/1/004 · Cited by 56
Silicon potentials investigated using density functional theory fitted neural networks
Sanville, E., Bholoa, A., Smith, R., & Kenny, S. D. (2008) · Journal of Physics Condensed Matter · doi:10.1088/0953-8984/20/28/285219 · Cited by 44
First-Principles Simulations on the Nature of the Melting Line of Sodium
Hernandez, E. R., & Íñiguez, J. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.055501 · Cited by 43
Tipping, R. H., & Forbes, A. (1971) · Journal of Molecular Spectroscopy · doi:10.1016/0022-2852(71)90276-1 · Cited by 27
Maschke, H. (1898) · Mathematische Annalen · doi:10.1007/bf01444297 · Cited by 25
Landau free energy curves for melting of quantum solids
Chakravarty, C., & Lynden-Bell, R. M. (2000) · The Journal of Chemical Physics · doi:10.1063/1.1316105 · Cited by 21
Kondor, R. (2007) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0701127 · Cited by 20
Self-citationConnections between the energy functional and interaction potentials for materials simulations
Taylor, C. D. (2009) · Physical Review B · doi:10.1103/physrevb.80.024104 · Cited by 15
Multipole expansions in four-dimensional hyperspherical harmonics
Meremianin, A. V. (2006) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/39/12/017 · Cited by 14
Caprio, M. A., Sviratcheva, K. D., & McCoy, A. E. (2010) · Journal of Mathematical Physics · doi:10.1063/1.3445529 · Cited by 13
Multipole expansions in four-dimensional hyperspherical harmonics
Meremianin, A. V. (2006) · MPG.PuRe (Max Planck Society) · Cited by 10
Can we really do computer-aided drug design?
Segall, M. (2011) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-011-9512-3 · Cited by 8
Research works printed but not linked: 1
- H. Weyl, 1946, The Classical Groups
Cited by
Sorted by citations
Recent advances and applications of machine learning in solid-state materials science
Schmidt, J., Marques, M. R. G., Botti, S., & Marques, M. A. L. (2019) · npj Computational Materials · doi:10.1038/s41524-019-0221-0 · Cited by 2,786
Machine learning and the physical sciences
Carleo, G., Cirac, J. I., Cranmer, K. S., Daudet, L., Schuld, M., Tishby, N., Vogt-Maranto, L., & Zdeborová, L. (2019) · Reviews of Modern Physics · doi:10.1103/revmodphys.91.045002 · Cited by 2,640
SchNet – A deep learning architecture for molecules and materials
Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A., & Müller, K.-R. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5019779 · Cited by 2,217
Wang, H., Zhang, L., Han, J., & Weinan, E. (2018) · Computer Physics Communications · doi:10.1016/j.cpc.2018.03.016 · Cited by 2,213
Inverse molecular design using machine learning: Generative models for matter engineering
Sánchez-Lengeling, B., & Aspuru‐Guzik, A. (2018) · Science · doi:10.1126/science.aat2663 · Cited by 2,177
Metadata
- Authors
- Bartók, A. P., Kondor, R., & Csányi, G.
- Affiliations
- University of Cambridge (GB)
- University of Chicago (US)
- Venue
- Physical Review B
- Publisher
- American Physical Society (APS)
- Published
- 2013-05-28
- Volume
- 87
- Issue
- 18
- ISSN
- 1098-0121 (ISSN-L)
- 1550-235X
- OpenAlex
- W2029413789
- Cited by
- 2,572
- References
- 60
- Citations by year
- 2026: 292 · 2025: 350 · 2024: 367 · 2023: 365 · 2022: 303 · 2021: 270 · 2020: 257 · 2019: 163 · 2018: 105 · 2017: 48 · 2016: 19 · 2015: 11 · 2014: 13 · 2013: 4
- FWCI
- 7.07
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Physical Review B (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Cambridge University Engineering Department Publications Database (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EP/K014560/1)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
- Physical Sciences › Chemistry › Physical and Theoretical Chemistry › Advanced Physical and Chemical Molecular Interactions
- Keywords
- potential energy surface fitting, basis function expansion, silicon clusters, small clusters
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
