Abstract
Machine learning interatomic potentials (MLIPs) provide exceptional opportunities to accurately simulate atomistic systems and/or accelerate the evaluation of diverse physical properties. MLIPs moreover offer extraordinary capabilities to conduct first-principles multiscale modeling, enabling the modeling of nanostructured materials at continuum level, with quantum mechanics level of accuracy and affordable computational costs. In this chapter, we first briefly discuss conventional methods and MLIPs for studying the atomic interactions. Next, the basic concept of MLIPs, their training procedure, and technical challenges will be discussed. Later, with several examples, the bottlenecks of quantum mechanics and empirical interatomic potentials in the evaluation of materials and structural properties will be highlighted, and it will be shown that how MLIPs could efficiently address those issues. Last, the novel concept of MLIP-enabled first-principles multiscale modeling will be elaborated, and the practical prospect for the autonomous materials and structural design will be outlined.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arabha S, Aghbolagh ZS, Ghorbani K, Hatam-Lee M, Rajabpour A (2021) Recent advances in lattice thermal conductivity calculation using machine-learning interatomic potentials. J Appl Phys 130:210903. https://doi.org/10.1063/5.0069443
Arabha S, Rajabpour A (2021) Thermo-mechanical properties of nitrogenated holey graphene (C2N): a comparison of machine-learning-based and classical interatomic potentials. Int J Heat Mass Transf 178:121589
Artrith N, Morawietz T, Behler J (2011) High-dimensional neural-network potentials for multicomponent systems: applications to zinc oxide. Phys Rev B 83:153101. https://doi.org/10.1103/PhysRevB.83.153101
Artrith N, Urban A (2016) An implementation of artificial neural-network potentials for atomistic materials simulations: performance for TiO2. Comput Mater Sci 114:135–150. https://doi.org/10.1016/j.commatsci.2015.11.047
Bartók AP, Csányi G (2015) Gaussian approximation potentials: a brief tutorial introduction. Int J Quantum Chem 115:1051–1057. https://doi.org/10.1002/qua.24927
Bartók AP, Payne MC, Kondor R, Csányi G (2010) Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. Phys Rev Lett 104:136403
Behler J (2014) Representing potential energy surfaces by high-dimensional neural network potentials. J Phys Condens Matter 26:183001
Behler J (2015) Constructing high-dimensional neural network potentials: a tutorial review. Int J Quantum Chem 115:1032–1050. https://doi.org/10.1002/qua.24890
Behler J (2016) Perspective: machine learning potentials for atomistic simulations. J Chem Phys 145:170901. https://doi.org/10.1063/1.4966192
Behler J, Parrinello M (2007) Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys Rev Lett 98:146401. https://doi.org/10.1103/PhysRevLett.98.146401
Behler J, RuNNer: A program for constructing high-dimensional neural network potentials
Brenner DW, Shenderova OA, Harrison JA, Stuart SJ, Ni B, Sinnott SB (2002) A second-generation Reactive Empirical Bond Order (REBO) potential energy expression for hydrocarbons. J Phys Condens Matter. https://doi.org/10.1088/0953-8984/14/4/312
Brieuc F, Schran C, Forbert H, Marx D, RubNNet4MD: Ruhr-Universität Bochum neural networks for molecular dynamics simulations
Chakraborty P, Liu Y, Ma T, Guo X, Cao L, Hu R, Wang Y (2020) Quenching thermal transport in aperiodic superlattices: a molecular dynamics and machine learning study. ACS Appl Mater Interfaces 12:8795–8804
Chen H, Ortner C (207) QM/MM methods for crystalline defects. Part 2: consistent energy and force-mixing. Multiscale Model Simul 15:184–214. https://doi.org/10.1137/15M1041250
Chen H, Ortner C (2016) QM/MM methods for crystalline defects. Part 1: locality of the tight binding model. Multiscale Model Simul 14:232–264. https://doi.org/10.1137/15M1022628
Dong Y, Meng M, Groves MM, Zhang C, Lin J (2018) Thermal conductivities of two-dimensional graphitic carbon nitrides by molecule dynamics simulation. Int J Heat Mass Transf 123:738–746. https://doi.org/10.1016/j.ijheatmasstransfer.2018.03.017
Fan Z, Wang Y, Ying P, Song K, Wang J, Wang Y, Zeng Z, Xu K, Lindgren E, Rahm JM et al (2022) GPUMD: a package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations. J Chem Phys 157:114801. https://doi.org/10.1063/5.0106617
Fan Z, Zeng Z, Zhang C, Wang Y, Song K, Dong H, Chen Y, Ala-Nissila T (2021) Neuroevolution machine learning potentials: combining high accuracy and low cost in atomistic simulations and application to heat transport. Phys Rev B 104:104309
Fan Z, Pereira LFC, Hirvonen P, Ervasti MM, Elder KR, Donadio D, Ala-Nissila T, Harju A (2017) Thermal conductivity decomposition in two-dimensional materials: application to graphene. Phys Rev B 95. https://doi.org/10.1103/PhysRevB.95.144309
Gao Y, Wang H, Sun M, Ding Y, Zhang L, Li Q (2018) First-principles study of intrinsic phononic thermal transport in monolayer C3N. Phys E Low-Dimensional Syst Nanostruct 99:194–201. https://doi.org/10.1016/j.physe.2018.02.012
Grimme S, Antony J, Ehrlich S, Krieg H (2010) A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu. J Chem Phys 132:154104. https://doi.org/10.1063/1.3382344
Han D, Wang X, Ding W, Chen Y, Zhang J, Xin G, Cheng L (2019) Phonon thermal conduction in a graphene–C 3 N heterobilayer using molecular dynamics simulations. Nanotechnology 30:075403. https://doi.org/10.1088/1361-6528/aaf481
Hatam-Lee SM, Rajabpour A, Volz S (2020) Thermal conductivity of graphene polymorphs and compounds: from C3N to graphdiyne lattices. Carbon N Y 161:816–826. https://doi.org/10.1016/j.carbon.2020.02.007
He L, Guo S, Lei J, Sha Z, Liu Z (2014) The effect of stone–thrower–wales defects on mechanical properties of graphene sheets—a molecular dynamics study. Carbon N Y 75:124–132. https://doi.org/10.1016/j.carbon.2014.03.044
Hong Y, Ju MG, Zhang J, Zeng XC (2018a) Phonon thermal transport in a graphene/MoSe2 van Der Waals heterobilayer. Phys Chem Chem Phys 20:2637–2645. https://doi.org/10.1039/C7CP06874C
Hong Y, Zhang J, Zeng XC (2018b) Monolayer and bilayer polyaniline C3N: two-dimensional semiconductors with high thermal conductivity. Nanoscale 10:4301–4310. https://doi.org/10.1039/C7NR08458G
Hu R, Iwamoto S, Feng L, Ju S, Hu S, Ohnishi M, Nagai N, Hirakawa K, Shiomi J (2020) Machine-learning-optimized aperiodic superlattice minimizes coherent phonon heat conduction. Phys Rev X 10:21050
Jensen BD, Wise KE, Odegard GM (2015) Simulation of the elastic and ultimate tensile properties of diamond, graphene, carbon nanotubes, and amorphous carbon using a revised ReaxFF parametrization. J Phys Chem A 119:9710–9721. https://doi.org/10.1021/acs.jpca.5b05889
KInacI A, Haskins JB, Sevik C, ÇaǧIn T (2012) Thermal conductivity of BN-C nanostructures. Phys Rev B-Condens Matter Mater Phys 86:115410. https://doi.org/10.1103/PhysRevB.86.115410
Korotaev P, Novoselov I, Yanilkin A, Shapeev A (2019) Accessing thermal conductivity of complex compounds by machine learning interatomic potentials. Phys Rev B 100:144308. https://doi.org/10.1103/PhysRevB.100.144308
Kresse G, Furthmüller J (1996) Efficient iterative schemes for Ab initio total-energy calculations using a plane-wave basis set. Phys Rev B 54:11169–11186. https://doi.org/10.1103/PhysRevB.54.11169
Kumar S, Sharma S, Babar V, Schwingenschlögl U (2017) Ultralow lattice thermal conductivity in monolayer C3N as compared to graphene. J Mater Chem A 5:20407–20411. https://doi.org/10.1039/C7TA05872A
Lee K, Yoo D, Jeong W, Han S (2019) SIMPLE-NN: an efficient package for training and executing neural-network interatomic potentials. Comput Phys Commun 242:95–103. https://doi.org/10.1016/j.cpc.2019.04.014
Li W, Carrete J, Katcho NA, Mingo N (2014) ShengBTE: a solver of the boltzmann transport equation for phonons. Comput Phys Commun 185:1747–1758. https://doi.org/10.1016/j.cpc.2014.02.015
Lindsay B (2010) Optimized tersoff and brenner empirical potential parameters for lattice dynamics and phonon thermal transport in carbon nanotubes and graphene. Phys Rev B-Condens Matter Mater Phys 82:205441
Lindsay L, Broido DA (2010) Optimized tersoff and brenner empirical potential parameters for lattice dynamics and phonon thermal transport in carbon nanotubes and graphene. Phys Rev B-Condens Matter Mater Phys 81:205441. https://doi.org/10.1103/PhysRevB.81.205441
Liu Z, Yang X, Zhang B, Li W (2021) High thermal conductivity of wurtzite boron arsenide predicted by including four-phonon scattering with machine learning potential. ACS Appl Mater Interfaces. https://doi.org/10.1021/acsami.1c11595
Liu X, Hersam MC (2019) Borophene-graphene heterostructures. Sci Adv 5:eaax6444. https://doi.org/10.1126/sciadv.aax6444
Mortazavi B (2017) Ultra High stiffness and thermal conductivity of graphene like C<inf>3</Inf>N. Carbon N Y 118:25–34. https://doi.org/10.1016/j.carbon.2017.03.029
Mortazavi B (2021) Ultrahigh thermal conductivity and strength in direct-gap semiconducting graphene-like BC6N: a first-principles and classical investigation. Carbon N Y 182:373–383. https://doi.org/10.1016/j.carbon.2021.06.038
Mortazavi B, Fan Z, Pereira LFC, Harju A, Rabczuk T (2016) Amorphized graphene: a stiff material with low thermal conductivity. Carbon N. Y. 103:318–326. https://doi.org/10.1016/j.carbon.2016.03.007
Mortazavi B, Novikov IS, Podryabinkin EV, Roche S, Rabczuk T, Shapeev AV, Zhuang X (2020b) exploring phononic properties of two-dimensional materials using machine learning interatomic potentials. Appl Mater Today 20:100685. https://doi.org/10.1016/j.apmt.2020.100685
Mortazavi B, Novikov IS, Shapeev A (2022a) V A machine-learning-based investigation on the mechanical/failure response and thermal conductivity of semiconducting BC2N monolayers. Carbon N Y 188:431–441. https://doi.org/10.1016/j.carbon.2021.12.039
Mortazavi B, Podryabinkin EV, Novikov IS, Rabczuk T, Zhuang X, Shapeev A (2021a) V Accelerating first-principles estimation of thermal conductivity by machine-learning interatomic potentials: a MTP/ShengBTE solution. Comput Phys Commun 258:107583. https://doi.org/10.1016/j.cpc.2020.107583
Mortazavi B, Podryabinkin EV, Roche S, Rabczuk T, Zhuang X, Shapeev A (2020a) V Machine-learning interatomic potentials enable first-principles multiscale modeling of lattice thermal conductivity in graphene/borophene heterostructures. Mater. Horizons 7:2359–2367. https://doi.org/10.1039/D0MH00787K
Mortazavi B, Rabczuk T (2015) Multiscale modeling of heat conduction in graphene laminates. Carbon N Y 85:1–7. https://doi.org/10.1016/j.carbon.2014.12.046
Mortazavi B, Rémond Y, Ahzi S, Toniazzo V (2012) Thickness and chirality effects on tensile behavior of few-layer graphene by molecular dynamics simulations. Comput Mater Sci 53:298–302. https://doi.org/10.1016/j.commatsci.2011.08.018
Mortazavi B, Shahrokhi M, Shojaei F, Rabczuk T, Zhuang X, Shapeev A (2022c) V A first-principles and machine-learning investigation on the electronic, photocatalytic, mechanical and heat conduction properties of nanoporous C5N monolayers. Nanoscale 14:4324–4333. https://doi.org/10.1039/D1NR06449E
Mortazavi B, Shojaei F, Shapeev AV, Zhuang X (2022b) A combined first-principles and machine-learning investigation on the stability, electronic, optical, and mechanical properties of novel C6N7-based nanoporous carbon nitrides. Carbon N Y 194:230–239. https://doi.org/10.1016/j.carbon.2022.03.068
Mortazavi B, Silani M, Podryabinkin EV, Rabczuk T, Zhuang X, Shapeev A (2021b) V First-principles multiscale modeling of mechanical properties in graphene/borophene heterostructures empowered by machine-learning interatomic potentials. Adv Mater 33:2102807. https://doi.org/10.1002/adma.202102807
Ni Z, Bu H, Zou M, Yi H, Bi K, Chen Y (2010) Anisotropic mechanical properties of graphene sheets from molecular dynamics. Phys B Condens Matter 405:1301–1306. https://doi.org/10.1016/j.physb.2009.11.071
Novikov I, Gubaev K, Evgeny Podryabinkin AS (2021) The MLIP package: moment tensor potentials with mpi and active learning. Mach Learn Sci Technol 2:025002
Novikov I, Grabowski B, Körmann F, Shapeev A (2022) Magnetic moment tensor potentials for collinear spin-polarized materials reproduce different magnetic states of Bcc Fe. NPJ Comput Mater 8:13. https://doi.org/10.1038/s41524-022-00696-9
Ouyang Y, Yu C, Yan G, Chen J (2021) Machine learning approach for the prediction and optimization of thermal transport properties. Front Phys 16:1–16
Peng B, Mortazavi B, Zhang H, Shao H, Xu K, Li J, Ni G, Rabczuk T, Zhu H (2018) Tuning thermal transport in C3N monolayers by adding and removing carbon atoms. Phys Rev Appl 10:34046. https://doi.org/10.1103/PhysRevApplied.10.034046
Plimpton S (1995) Fast Parallel algorithms for short-range molecular dynamics. J Comput Phys 117:1–19. https://doi.org/10.1006/jcph.1995.1039
Podryabinkin EV, Kvashnin AG, Asgarpour M, Maslenikov II, Ovsyannikov DA, Sorokin PB, Popov MY, Shapeev A (2022) V Nanohardness from first principles with active learning on atomic environments. J Chem Theory Comput 18:1109–1121. https://doi.org/10.1021/acs.jctc.1c00783
Podryabinkin EV, Shapeev A (2017) V active learning of linearly parametrized interatomic potentials. Comput Mater Sci 140:171–180. https://doi.org/10.1016/j.commatsci.2017.08.031
Podryabinkin EV, Tikhonov EV, Shapeev AV, Oganov AR (2019) Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning. Phys Rev B 99:064114. https://doi.org/10.1103/PhysRevB.99.064114
Qin G, Qin Z, Wang H, Hu M (2018) On the diversity in the thermal transport properties of graphene: a first-principles-benchmark study testing different exchange-correlation functionals. Comput Mater Sci 151:153–159. https://doi.org/10.1016/j.commatsci.2018.05.007
Rowe P, Deringer VL, Gasparotto P, Csányi G, Michaelides A (2020) An accurate and transferable machine learning potential for carbon. J Chem Phys 153:34702. https://doi.org/10.1063/5.0005084
Schütt KT, Arbabzadah F, Chmiela S, Müller KR, Tkatchenko A (2017) Quantum-chemical insights from deep tensor neural networks. Nat Commun 8:13890. https://doi.org/10.1038/ncomms13890
Shapeev AV (2016) Moment tensor potentials: a class of systematically improvable interatomic potentials. Multiscale Model Simul 14:1153–1173. https://doi.org/10.1137/15M1054183
Shapeev A (2019) V Chapter 3 Applications of machine learning for representing interatomic interactions. In: Computational materials discovery; The royal society of chemistry, pp 66–86. ISBN 978-1-78262-961-0
Singraber A, Morawietz T, Behler J, Dellago C (2019) Parallel multistream training of high-dimensional neural network potentials. J Chem Theory Comput 15:3075–3092. https://doi.org/10.1021/acs.jctc.8b01092
Song J, Xu Z, He X, Bai Y, Miao L, Cai C, Wang R (2019) Thermal conductivity of two-dimensional BC 3: A comparative study with two-dimensional C 3 N. Phys Chem Chem Phys 21:12977–12985. https://doi.org/10.1039/C9CP01943J
Srinivasan SG, van Duin ACT, Ganesh P (2015) Development of a ReaxFF potential for carbon condensed phases and its application to the thermal fragmentation of a large fullerene. J Phys Chem A 119:571–580. https://doi.org/10.1021/jp510274e
Stuart SJ, Tutein AB, Harrison JA (2000) A reactive potential for hydrocarbons with intermolecular interactions. J Chem Phys 112:6472–6486. https://doi.org/10.1063/1.481208
Taheri A, Pisana S, Singh CV (2021) Importance of quadratic dispersion in acoustic flexural phonons for thermal transport of two-dimensional materials. Phys Rev B 103:235426. https://doi.org/10.1103/PhysRevB.103.235426
Taheri A, Da Silva C, Amon CH (2018) First-principles phonon thermal transport in graphene: effects of exchange-correlation and type of pseudopotential. J Appl Phys 123:215105. https://doi.org/10.1063/1.5027619
Tersoff J (1988) New empirical approach for the structure and energy of covalent systems. Phys Rev B 37:6991–7000. https://doi.org/10.1103/PhysRevB.37.6991
Tersoff J (1989) Modeling solid-state chemistry: interatomic potentials for multicomponent systems. Phys Rev B 39:5566–5568. https://doi.org/10.1103/PhysRevB.39.5566
Thomas JA, Iutzi RM, McGaughey AJH (2010) Thermal conductivity and phonon transport in empty and water-filled carbon nanotubes. Phys Rev B-Condens Matter Mater Phys 81:045413. https://doi.org/10.1103/PhysRevB.81.045413
Thompson AP, Swiler LP, Trott CR, Foiles SM, Tucker GJ (2015) Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. J Comput Phys 285:316–330
Wang H, Li Q, Pan H, Gao Y, Sun M (2019) Comparative investigation of the mechanical, electrical and thermal transport properties in graphene-like C3B and C3N. J Appl Phys 126:234302. https://doi.org/10.1063/1.5122678
Wang H, Qin G, Qin Z, Li G, Wang Q, Hu M (2018b) Lone-pair electrons do not necessarily lead to low lattice thermal conductivity: an exception of two-dimensional penta-CN2. J Phys Chem Lett 9:2474–2483. https://doi.org/10.1021/acs.jpclett.8b00820
Wang H, Zhang L, Han J, Weinan E (2018a) DeePMD-Kit: a deep learning package for many-body potential energy representation and molecular dynamics. Comput Phys Commun 228:178–184
Ward A (2009) Alistair first principles theory of the lattice thermal conductivity of semiconductors. PhDT
Wei Z, Ni Z, Bi K, Chen M, Chen Y (2011) In-plane lattice thermal conductivities of multilayer graphene films. Carbon N Y 49:2653–2658. https://doi.org/10.1016/j.carbon.2011.02.051
Yang X, Wu S, Xu J, Cao B, To AC (2018) Spurious heat conduction behavior of finite-size graphene nanoribbon under extreme uniaxial strain caused by the AIREBO potential. Phys E Low-Dimensional Syst Nanostruct 96:46–53. https://doi.org/10.1016/j.physe.2017.10.006
Yanxon H, Zagaceta D, Wood BC, Zhu Q (2020) Neural network potential from bispectrum components: a case study on crystalline silicon. J Chem Phys 153:54118. https://doi.org/10.1063/5.0014677
Yanxon H, Zagaceta D, Tang B, Matteson DS, Zhu Q (2021) PyXtal_FF: a python library for automated force field generation. 2:27001. https://doi.org/10.1088/2632-2153/abc940
Ying P, Dong H, Liang T, Fan Z, Zhong Z, Zhang J (2023) Atomistic Insights into the mechanical anisotropy and fragility of monolayer fullerene networks using quantum mechanical calculations and machine-learning molecular dynamics simulations. Extrem Mech Lett. https://doi.org/10.1016/j.eml.2022.101929
Zuo Y, Chen C, Li X, Deng Z, Chen Y, Behler J, Csányi G, Shapeev AV, Thompson AP, Wood MA et al (2020) Performance and cost assessment of machine learning interatomic potentials. J Phys Chem A 124:731–745. https://doi.org/10.1021/acs.jpca.9b08723
Acknowledgements
Author appreciates the funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122, Project ID 390833453)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Mortazavi, B. (2023). Machine Learning Interatomic Potentials: Keys to First-Principles Multiscale Modeling. In: Rabczuk, T., Bathe, KJ. (eds) Machine Learning in Modeling and Simulation. Computational Methods in Engineering & the Sciences. Springer, Cham. https://doi.org/10.1007/978-3-031-36644-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-36644-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36643-7
Online ISBN: 978-3-031-36644-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)