journal article·2021-08-16Open access

Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials

Dongsun Yoo, Jisu Jung, Wonseok Jeong, Seungwu Han

npj Computational Materials· Volume 7· Issue 1

Abstract

Abstract The universal mathematical form of machine-learning potentials (MLPs) shifts the core of development of interatomic potentials to collecting proper training data. Ideally, the training set should encompass diverse local atomic environments but conventional approaches are prone to sampling similar configurations repeatedly, mainly due to the Boltzmann statistics. As such, practitioners handpick a large pool of distinct configurations manually, stretching the development period significantly. To overcome this hurdle, methods are being proposed that automatically generate training data. Herein, we suggest a sampling method optimized for gathering diverse yet relevant configurations semi-automatically. This is achieved by applying the metadynamics with the descriptor for the local atomic environment as a collective variable. As a result, the simulation is automatically steered toward unvisited local environment space such that each atom experiences diverse chemical environments without redundancy. We apply the proposed metadynamics sampling to H:Pt(111), GeTe, and Si systems. Throughout these examples, a small number of metadynamics trajectories can provide reference structures necessary for training high-fidelity MLPs. By proposing a semi-automatic sampling method tuned for MLPs, the present work paves the way to wider applications of MLPs to many challenging applications.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · Advanced Electron Microscopy Techniques and Applications · Advanced Materials Characterization Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (65)

Show source-provided references
1. Schmidt, J., Marques, M. R. G., Botti, S. & Marques, M. A. L. Recent advances and applications of machine learning in solid-state materials science. npj Comput. Mater. 5, 1–36 (2019).10.1038/s41524-019-0221-0 ↗
2. Yoo, D. et al. Atomic energy mapping of neural network potential. Phys. Rev. Mater. 3, 093802 (2019).10.1103/PhysRevMaterials.3.093802 ↗
3. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).10.1103/PhysRevLett.98.146401 ↗
4. Bartók, A. P., Payne, M. C., Kondor, R. & Csányi, G. Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 104, 136403 (2010).10.1103/PhysRevLett.104.136403 ↗
5. Shapeev, A. V. Moment tensor potentials: a class of systematically improvable interatomic potentials. Multiscale Model Simul. 14, 1153–1173 (2016).10.1137/15M1054183 ↗
6. Schütt, K. T., Arbabzadah, F., Chmiela, S., Müller, K. R. & Tkatchenko, A. Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017).10.1038/ncomms13890 ↗
7. Chmiela, S. et al. Machine learning of accurate energy-conserving molecular force fields. Sci. Adv. 3, e1603015 (2017).10.1126/sciadv.1603015 ↗
8. Lee, D., Lee, K., Yoo, D., Jeong, W. & Han, S. Crystallization of amorphous GeTe simulated by neural network potential addressing medium-range order. Comput. Mater. Sci. 181, 109725 (2020).10.1016/j.commatsci.2020.109725 ↗
9. Sosso, G. C. et al. Fast crystallization of the phase change compound GeTe by large-scale molecular dynamics simulations. J. Phys. Chem. Lett. 4, 4241–4246 (2013).10.1021/jz402268v ↗
10. Mocanu, F. C. et al. Modeling the phase-change memory material, Ge2Sb2Te5, with a Machine-learned interatomic potential. J. Phys. Chem. B 122, 8998–9006 (2018).10.1021/acs.jpcb.8b06476 ↗
11. Jeong, W., Yoo, D., Lee, K., Jung, J. & Han, S. Efficient atomic-resolution uncertainty estimation for neural network potentials using a replica ensemble. J. Phys. Chem. Lett. 11, 6090–6096 (2020).10.1021/acs.jpclett.0c01614 ↗
12. Hellström, M., Quaranta, V. & Behler, J. One-dimensional vs. two-dimensional proton transport processes at solid–liquid zinc-oxide–water interfaces. Chem. Sci. 10, 1232–1243 (2019).10.1039/C8SC03033B ↗
13. Sun, G. & Sautet, P. Metastable structures in cluster catalysis from first-principles: structural ensemble in reaction conditions and metastability triggered reactivity. J. Am. Chem. Soc. 140, 2812–2820 (2018).10.1021/jacs.7b11239 ↗
14. Hong, C. et al. Training machine-learning potentials for crystal structure prediction using disordered structures. Phys. Rev. B 102, 224104 (2020).10.1103/PhysRevB.102.224104 ↗
15. Ulissi, Z. W. et al. Machine-learning methods enable exhaustive searches for active bimetallic facets and reveal active site motifs for CO2 reduction. ACS Catal. 7, 6600–6608 (2017).10.1021/acscatal.7b01648 ↗
16. Rowe, P., Deringer, V. L., Gasparotto, P., Csányi, G. & Michaelides, A. An accurate and transferable machine learning potential for carbon. J. Chem. Phys. 153, 034702 (2020).10.1063/5.0005084 ↗
17. Bartók, A. P., Kermode, J., Bernstein, N. & Csányi, G. Machine learning a general-purpose interatomic potential for silicon. Phys. Rev. X 8, 041048 (2018).
18. Botu, V., Batra, R., Chapman, J. & Ramprasad, R. Machine learning force fields: construction, validation, and outlook. J. Phys. Chem. C. 121, 511–522 (2017).10.1021/acs.jpcc.6b10908 ↗
19. Zhang, L., Lin, D. Y., Wang, H., Car, R. & Weinan, E. Active learning of uniformly accurate interatomic potentials for materials simulation. Phys. Rev. Mater. 3, 023804 (2019).10.1103/PhysRevMaterials.3.023804 ↗
20. Sivaraman, G. et al. Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide. npj Comput. Mater. 6, 1–8 (2020).10.1038/s41524-020-00367-7 ↗
21. Tong, Q., Xue, L., Lv, J., Wang, Y. & Ma, Y. Accelerating CALYPSO structure prediction by data-driven learning of a potential energy surface. Faraday Discuss 211, 31–43 (2018).10.1039/C8FD00055G ↗
22. Deringer, V. L., Pickard, C. J. & Csányi, G. Data-driven learning of total and local energies in elemental boron. Phys. Rev. Lett. 120, 156001 (2018).10.1103/PhysRevLett.120.156001 ↗
23. Bernstein, N., Csányi, G. & Deringer, V. L. De novo exploration and self-guided learning of potential-energy surfaces. npj Comput. Mater. 5, 1–9 (2019).10.1038/s41524-019-0236-6 ↗
24. Karabin, M. & Perez, D. An entropy-maximization approach to automated training set generation for interatomic potentials. J. Chem. Phys. 153, 094110 (2020).10.1063/5.0013059 ↗
25. Laio, A. & Parrinello, M. Escaping free-energy minima. Proc. Natl. Acad. Sci. U.S.A. 99, 12562–12566 (2002).10.1073/pnas.202427399 ↗
26. Nishihara, Y., Hayashi, S. & Kato, S. A search for ligand diffusion pathway in myoglobin using a metadynamics simulation. Chem. Phys. Lett. 464, 220–225 (2008).10.1016/j.cplett.2008.09.012 ↗
27. Behler, J. Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011).10.1063/1.3553717 ↗
28. Bonati, L. & Parrinello, M. Silicon liquid structure and crystal nucleation from ab initio deep metadynamics. Phys. Rev. Lett. 121, 265701 (2018).10.1103/PhysRevLett.121.265701 ↗
29. Herr, J. E., Yao, K., McIntyre, R., Toth, D. W. & Parkhill, J. Metadynamics for training neural network model chemistries: a competitive assessment. J. Chem. Phys. 148, 241710 (2018).10.1063/1.5020067 ↗
30. Sosso, G. C., Miceli, G., Caravati, S., Behler, J. & Bernasconi, M. Neural network interatomic potential for the phase change material GeTe. Phys. Rev. B 85, 174103 (2012).10.1103/PhysRevB.85.174103 ↗
31. Gabardi, S., Sosso, G. G., Behler, J. & Bernasconi, M. Priming effects in the crystallization of the phase change compound GeTe from atomistic simulations. Faraday Discuss 213, 287–301 (2019).10.1039/C8FD00101D ↗
32. Branduardi, D., Bussi, G. & Parrinello, M. Metadynamics with adaptive gaussians. J. Chem. Theory Comput. 8, 2247–2254 (2012).10.1021/ct3002464 ↗
33. Plimpton, S. Fast parallel algorithms for short-range molecular dynamics. J. Comput. Phys. 117, 1–19 (1995).10.1006/jcph.1995.1039 ↗
34. Lee, K., Yoo, D., Jeong, W. & Han, S. SIMPLE-NN: an efficient package for training and executing neural-network interatomic potentials. Comput. Phys. Commun. 242, 95–103 (2019).10.1016/j.cpc.2019.04.014 ↗
35. Kresse, G. & Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B 54, 11169–11186 (1996).10.1103/PhysRevB.54.11169 ↗
36. Li, C. & Baek, J.-B. Recent advances in noble metal (Pt, Ru, and Ir)-based electrocatalysts for efficient hydrogen evolution reaction. ACS Omega 5, 31–40 (2020).10.1021/acsomega.9b03550 ↗
37. Taguchi, S., Aramata, A. & Enyo, M. Reduced CO2 on polycrystalline Pd and Pt electrodes in neutral solution: electrochemical and in situ Fourier transform IR studies. J. Electroanal. Chem. 372, 161–169 (1994).10.1016/0022-0728(93)03287-Y ↗
38. Wilde, M. et al. Influence of carbon deposition on the hydrogen distribution in Pd nanoparticles and their reactivity in olefin hydrogenation. Angew. Chem. Int. Ed. Engl. 47, 9289–9293 (2008).10.1002/anie.200801923 ↗
39. Zhai, F., Li, Y., Yang, Y., Jiang, S. & Shen, X. Abnormal subsurface hydrogen diffusion behaviors in heterogeneous hydrogenation reactions. J. Chem. Phys. 149, 174704 (2018).10.1063/1.5048533 ↗
40. Henkelman, G. & Jónsson, H. Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points. J. Chem. Phys. 113, 9978–9985 (2000).10.1063/1.1323224 ↗
41. Smidstrup, S., Pedersen, A., Stokbro, K. & Jónsson, H. Improved initial guess for minimum energy path calculations. J. Chem. Phys. 140, 214106 (2014).10.1063/1.4878664 ↗
42. Bădescu, S. C. et al. Energetics and vibrational states for hydrogen on Pt(111). Phys. Rev. Lett. 88, 136101 (2002).10.1103/PhysRevLett.88.136101 ↗
43. Ferrin, P., Kandoi, S., Nilekar, A. U. & Mavrikakis, M. Hydrogen adsorption, absorption and diffusion on and in transition metal surfaces: A DFT study. Surf. Sci. 606, 679–689 (2012).10.1016/j.susc.2011.12.017 ↗
44. Raoux, S., Wełnic, W. & Ielmini, D. Phase change materials and their application to nonvolatile memories. Chem. Rev. 110, 240–267 (2010).10.1021/cr900040x ↗
45. McLachlan, G. J. Discriminant Analysis and Statistical Pattern Recognition (John Wiley & Sons, Hoboken, NJ, 2004.)
46. Maesschalck, R. D., De Maesschalck, R., Jouan-Rimbaud, D. & Massart, D. L. The Mahalanobis distance. Chemom. Intell. Lab. Syst. 50, 1–18 (2000).10.1016/S0169-7439(99)00047-7 ↗
47. Roux, S. L., Le Roux, S. & Jund, P. Ring statistics analysis of topological networks: new approach and application to amorphous GeS2 and SiO2 systems. Comput. Mater. Sci. 49, 70–83 (2010).10.1016/j.commatsci.2010.04.023 ↗
48. Steinhardt, P. J., Nelson, D. R. & Ronchetti, M. Bond-orientational order in liquids and glasses. Phys. Rev. B 28, 784 (1983).10.1103/PhysRevB.28.784 ↗
49. Rohlfing, C. M. & Raghavachari, K. A theoretical study of small silicon clusters using an effective core potential. Chem. Phys. Lett. 167, 559–565 (1990).10.1016/0009-2614(90)85469-S ↗
50. Ho, K.-M. et al. Structures of medium-sized silicon clusters. Nature 392, 582–585 (1998).10.1038/33369 ↗
51. Tomanek, D. & Schluter, M. A. Calculation of magic numbers and the stability of small Si clusters. Phys. Rev. Lett. 56, 1055–1058 (1986).10.1103/PhysRevLett.56.1055 ↗
52. Jeong, W., Lee, K., Yoo, D., Lee, D. & Han, S. Toward reliable and transferable machine learning potentials: uniform training by overcoming sampling bias. J. Phys. Chem. C. 122, 22790–22795 (2018).10.1021/acs.jpcc.8b08063 ↗
53. Wang, C., Aoyagi, K., Wisesa, P. & Mueller, T. Lithium ion conduction in cathode coating materials from on-the-fly machine learning. Chem. Mater. 32, 3741–3752 (2020).10.1021/acs.chemmater.9b04663 ↗
54. Vandermause, J. et al. On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events. npj Comput. Mater. 6, 1–11 (2020).10.1038/s41524-020-0283-z ↗
55. Blöchl, P. E. Projector augmented-wave method. Phys. Rev. B 50, 17953–17979 (1994).10.1103/PhysRevB.50.17953 ↗
56. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865–3868 (1996).10.1103/PhysRevLett.77.3865 ↗
57. Grimme, S. Semiempirical GGA-type density functional constructed with a long-range dispersion correction. J. Comput. Chem. 27, 1787–1799 (2006).10.1002/jcc.20495 ↗
58. Sosso, G. C., Behler, J. & Bernasconi, M. Breakdown of Stokes-Einstein relation in the supercooled liquid state of phase change materials. Phys. Status Solidi B 249, 1880–1885 (2012).10.1002/pssb.201200355 ↗
59. Imbalzano, G. et al. Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials. J. Chem. Phys. 148, 241730 (2018).10.1063/1.5024611 ↗
60. Mahoney, M. W. & Drineas, P. CUR matrix decompositions for improved data analysis. Proc. Natl. Acad. Sci. U.S.A. 106, 697–702 (2009).10.1073/pnas.0803205106 ↗
61. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. arXiv. Preprint at https://arxiv.org/abs/1412.6980 (2014).
62. Stukowski, A. Visualization and analysis of atomistic simulation data with OVITO–the open visualization tool. Model. Simul. Mater. Sci. Eng. 18, 015012 (2010).10.1088/0965-0393/18/1/015012 ↗
63. Chadi, D. J. Reexamination of the Si(100) surface reconstruction. Appl. Opt. 19, 3971 (1980).10.1364/AO.19.003971 ↗
64. Menon, M., Lathiotakis, N. N. & Andriotis, A. N. The reconstruction of the Si(110) surface and its interaction with Si adatoms. Phys. Rev. B. 56, 1412 (1997).10.1103/PhysRevB.56.1412 ↗
65. Solares, S. D. et al. Density functional theory study of the geometry, energetics, and reconstruction process of Si(111) surfaces. Langmuir 21, 12404–12414 (2005).10.1021/la052029s ↗