Physics infused machine learning force fields for 2D materials monolayers

Abstract

Large-scale atomistic simulations of two-dimensional (2D) materials rely on highly accurate and efficient force fields. Here, we present a physics-infused machine learning framework that enables the efficient development and interpretability of interatomic interaction models for 2D materials. By considering the characteristics of chemical bonds and structural topology, we have devised a set of efficient descriptors. This enables accurate force field training using a small dataset. The machine learning force fields show great success in describing the phase transformation and domain switching behaviors of monolayer Group IV monochalcogenides, e.g., GeSe and PbTe. Notably, this type of force field can be readily extended to other non-transition 2D systems, such as hexagonal boron nitride (hBN), leveraging their structural similarity. Our work provides a straightforward but accurate extension of simulation time and length scales for 2D materials.

Keywords

2D materials / mechanical properties / machine learning force fields / structural evolution

References

[1] Saito Y,Iwasa Y.Highly crystalline 2D superconductors.Nat Rev Mater2017;2:16094

[2] Wang QH,Kis A,Strano MS.Electronics and optoelectronics of two-dimensional transition metal dichalcogenides.Nat Nanotechnol2012;7:699-712

[3] Balandin AA,Bao W.Superior thermal conductivity of single-layer graphene.Nano Lett2008;8:902-7

[4] Zhao LD,Zhang Y.Ultralow thermal conductivity and high thermoelectric figure of merit in SnSe crystals.Nature2014;508:373-7

[5] Prashantha Kumar HG, Anthony Xavior M. Graphene reinforced metal matrix composite (GRMMC): a review.Procedia Eng2014;97:1033-40

[6] Lee C,Kalb W.Frictional characteristics of atomically thin sheets.Science2010;328:76-80

[7] Li S,Carpick RW.The evolving quality of frictional contact with graphene.Nature2016;539:541-5

[8] Chang K,Lin H.Discovery of robust in-plane ferroelectricity in atomic-thick SnTe.Science2016;353:274-8

[9] Fei Z,Palomaki TA.Ferroelectric switching of a two-dimensional metal.Nature2018;560:336-9

[10] Guan Z,Shen X.Recent progress in two-dimensional ferroelectric materials.Adv Elect Mater2020;6:1900818

[11] Li W,Li J.Phase transitions in 2D materials.Nat Rev Mater2021;6:829-46

[12] Bao Y,Liu Y.Gate-tunable in-plane ferroelectricity in few-layer SnS.Nano Lett2019;19:5109-17

[13] Fei R,Li J.Giant piezoelectricity of monolayer Group IV monochalcogenides: SnSe, SnS, GeSe, and GeS.Appl Phys Lett2015;107:173104

[14] Fei R,Yang L.Ferroelectricity and phase transitions in monolayer group-IV monochalcogenides.Phys Rev Lett2016;117:097601

[15] Mehboudi M,Yang Y.Structural phase transition and material properties of few-layer monochalcogenides.Phys Rev Lett2016;117:246802

[16] Wang H.Two-dimensional multiferroics in monolayer group IV monochalcogenides.2D Mater2017;4:015042

[17] Botu V,Chapman J.Machine learning force fields: construction, validation, and outlook.J Phys Chem C2017;121:511-22

[18] Botu V.Adaptive machine learning framework to accelerate ab initio molecular dynamics.Int J Quantum Chem2015;115:1074-83

[19] Zong H,Ding X,Lookman T.Developing an interatomic potential for martensitic phase transformations in zirconium by machine learning.npj Comput Mater2018;4:48

[20] Yang Y,Han CX.Taking materials dynamics to new extremes using machine learning interatomic potentials.J Mater Inf2021;1:10

[21] Botu V.Learning scheme to predict atomic forces and accelerate materials simulations.Phys Rev B2015;92:094306

[22] Hohenberg P.Inhomogeneous electron gas.Phys Rev1964;136:B864-71

[23] Kohn W.Self-consistent equations including exchange and correlation effects.Phys Rev1965;140:A1133-8

[24] Kresse G.Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set.Comput Mater Sci1996;6:15-50

[25] Kresse G.Ab initio molecular dynamics for liquid metals.Phys Rev B Condens Matter1993;47:558-61

[26] Perdew JP,Ernzerhof M.Generalized gradient approximation made simple.Phys Rev Lett1996;77:3865-8

[27] Becke AD.Density-functional exchange-energy approximation with correct asymptotic behavior.Phys Rev A1988;38:3098-100

[28] Langreth DC.Beyond the local-density approximation in calculations of ground-state electronic properties.Phys Rev B1983;28:1809-34

[29] Huan TD,Chapman J,Chen L.A universal strategy for the creation of machine learning-based atomistic force fields.npj Comput Mater2017;3:37

[30] Hofmann T,Smola AJ.Kernel methods in machine learning.Ann Statist2008;36:1171-220

[31] Müller KR,Rätsch G,Schölkopf B.An introduction to kernel-based learning algorithms.IEEE Trans Neural Netw2001;12:181-201

[32] Deringer VL.Machine learning based interatomic potential for amorphous carbon.Phys Rev B2017;95:094203

[33] Seko A,Tanaka I.First-principles interatomic potentials for ten elemental metals via compressed sensing.Phys Rev B2015;92:054113

[34] Pedregosa F,Gramfort A.Scikit-learn: machine learning in python.J Mach Learn Res2011;12:2825-30Available from: https://www.jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf?ref=https:/.[Last accessed on 9 Nov 2023]

[35] Nosé S.A unified formulation of the constant temperature molecular dynamics methods.J Chem Phys1984;81:511-9

[36] Hoover WG.Canonical dynamics: equilibrium phase-space distributions.Phys Rev A Gen Phys1985;31:1695-7

[37] Parrinello M.Polymorphic transitions in single crystals: a new molecular dynamics method.J Appl Phys1981;52:7182-90

[38] Plimpton S.Fast parallel algorithms for short-range molecular dynamics.J Comput Phys1995;117:1-19

[39] Li J.AtomEye: an efficient atomistic configuration viewer.Modelling Simul Mater Sci Eng2003;11:173

[40] Yang Y,Ding X.Size-dependent ferroic phase transformations in GeSe nanoribbons.Appl Phys Lett2022;121:122903

[41] Yang Y,Sun J.Rippling ferroic phase transition and domain switching in 2D materials.Adv Mater2021;33:2103469

[42] Falin A,Santos EJG.Mechanical properties of atomically thin boron nitride and the role of interlayer interactions.Nat Commun2017;8:15815 PMCID:PMC5489686

[43] Ahmed T,Mcdermitt C.Strength and toughness anisotropy in hexagonal boron nitride: an atomistic picture.J Appl Phys2018;124:185108