Volume 2 Issue 1
March  2022
Turn off MathJax
Article Contents
Juefan Wang, Abhishek A Panchal, Pieremanuele Canepa. Strategies for fitting accurate machine-learned inter-atomic potentials for solid electrolytes[J]. Materials Futures, 2023, 2(1): 015101. doi: 10.1088/2752-5724/acb506
Citation: Juefan Wang, Abhishek A Panchal, Pieremanuele Canepa. Strategies for fitting accurate machine-learned inter-atomic potentials for solid electrolytes[J]. Materials Futures, 2023, 2(1): 015101. doi: 10.1088/2752-5724/acb506
Paper •

Strategies for fitting accurate machine-learned inter-atomic potentials for solid electrolytes

© 2023 The Author(s). Published by IOP Publishing Ltd on behalf of the Songshan Lake Materials Laboratory
Materials Futures, Volume 2, Number 1
  • Received Date: 2022-11-27
  • Accepted Date: 2023-01-16
  • Publish Date: 2023-02-09
  • Ion transport in materials is routinely probed through several experimental techniques, which introduce variability in reported ionic diffusivities and conductivities. The computational prediction of ionic diffusivities and conductivities helps in identifying good ionic conductors, and suitable solid electrolytes (SEs), thus establishing firm structure-property relationships. Machine-learned potentials are an attractive strategy to extend the capabilities of accurate ab initio molecular dynamics (AIMD) to longer simulations for larger systems, enabling the study of ion transport at lower temperatures. However, machine-learned potentials being in their infancy, critical assessments of their predicting capabilities are rare. Here, we identified the main factors controlling the quality of a machine-learning potential based on the moment tensor potential formulation, when applied to the properties of ion transport in ionic conductors, such as SEs. Our results underline the importance of high-quality and diverse training sets required to fit moment tensor potentials. We highlight the importance of considering intrinsic defects which may occur in SEs. We demonstrate the limitations posed by short-timescale and high-temperature AIMD simulations to predict the room-temperature properties of materials.
  • loading
  • [1]
    Crabtree G 2019 The coming electric vehicle transformation Science 366 422–4
    Janek J and Zeier W G 2016 A solid future for battery development Nat. Energy 1 16141
    Famprikis T, Canepa P, Dawson J A, Islam M S and Masquelier C 2019 Fundamentals of inorganic solid-state electrolytes for batteries Nat. Mater. 18 1278–91
    Kamaya N et al 2011 A lithium superionic conductor Nat. Mater. 10 682–6
    Rayavarapu P R, Sharma N, Peterson V K and Adams S 2012 Variation in structure and Li+-ion migration in argyrodite-type Li6PS5X (X = Cl, Br, I) solid electrolytes J. Solid State Electrochem. 16 1807–13
    Kato Y, Hori S, Saito T, Suzuki K, Hirayama M, Mitsui A, Yonemura M, Iba H and Kanno R 2016 High-power all-solid-state batteries using sulfide superionic conductors Nat. Energy 1 16030
    Gao Y, Nolan A M, Du P, Wu Y, Yang C, Chen Q, Mo Y and Bo S-H 2020 Classical and emerging characterization techniques for investigation of ion transport mechanisms in crystalline fast ionic conductors Chem. Rev. 120 5954–6008
    Bachman J C et al 2016 Inorganic solid-state electrolytes for lithium batteries: mechanisms and properties governing ion conduction Chem. Rev. 116 140–62
    Rao R P and Adams S 2011 Studies of lithium argyrodite solid electrolytes for all-solid-state batteries: studies of lithium argyrodite solid electrolytes Phys. Status Solidi a 208 1804–7
    Tatsumisago M and Hayashi A 2012 Superionic glasses and glass–ceramics in the Li2S–P2S5 system for all-solid-state lithium secondary batteries Solid State Ion. 225 342–5
    Tatsumisago M, Nagao M and Hayashi A 2013 Recent development of sulfide solid electrolytes and interfacial modification for all-solid-state rechargeable lithium batteries J. Asian Ceram. Soc. 1 17–25
    Levi M D and Aurbach D 1997 Diffusion coefficients of lithium ions during intercalation into graphite derived from the simultaneous measurements and modeling of electrochemical impedance and potentiostatic intermittent titration characteristics of thin graphite electrodes J. Phys. Chem. B 101 4641–7
    Levi M D and Aurbach D 2012 Characterization of Materials ed E N Kaufmann (Hoboken, NJ: Wiley) p com125
    Tang K, Yu X, Sun J, Li H and Huang X 2011 Kinetic analysis on LiFePO4 thin films by CV, GITT and EIS Electrochim. Acta 56 4869–75
    Pecher O, Carretero-González J, Griffith K J and Grey C P 2017 Materials’ methods: NMR in battery research Chem. Mater. 29 213–42
    Tang W S, Unemoto A, Zhou W, Stavila V, Matsuo M, Wu H, Orimo S-I and Udovic T J 2015 Unparalleled lithium and sodium superionic conduction in solid electrolytes with large monovalent cage-like anions Energy Environ. Sci. 8 3637–45
    Dimitrievska M, Shea P, Kweon K E, Bercx M, Varley J B, Tang W S, Skripov A V, Stavila V, Udovic T J and Wood B C 2018 Carbon incorporation and anion dynamics as synergistic drivers for ultrafast diffusion in superionic LiCB11H12 and NaCB11H12 Adv. Energy Mater. 8 1703422
    Xie J, Kohno K, Matsumura T, Imanishi N, Hirano A, Takeda Y and Yamamoto O 2008 Li-ion diffusion kinetics in LiMn2O4 thin films prepared by pulsed laser deposition Electrochim. Acta 54 376–81
    Wen K, Xia M, Deng P, Lv W and He W 2019 A sandwich-structured double-battery device for direct evaluation of lithium diffusion coefficients and phase transition in electrodes of lithium ion batteries Chem. Eng. Sci. 200 80–86
    Ecker M, Tran T K D, Dechent P, Käbitz S, Warnecke A and Sauer D U 2015 Parameterization of a physico-chemical model of a lithium-ion battery: I. Determination of parameters J. Electrochem. Soc. 162 A1836–48
    Deng Z et al 2022 Fundamental investigations on the sodium-ion transport properties of mixed polyanion solid-state battery electrolytes Nat. Commun. 13 4470
    Zhu Z, Chu I-H, Deng Z and Ong S P 2015 Role of Na+ interstitials and dopants in enhancing the Na+ conductivity of the cubic Na3PS4 superionic conductor Chem. Mater. 27 8318–25
    Chu I-H, Nguyen H, Hy S, Lin Y-C, Wang Z, Xu Z, Deng Z, Meng Y S and Ong S P 2016 Insights into the performance limits of the Li7P3S11 superionic conductor: a combined first-principles and experimental study ACS Appl. Mater. Interfaces 8 7843–53
    de Klerk N J J, Rosło´n I and Wagemaker M 2016 Diffusion mechanism of Li argyrodite solid electrolytes for Li-ion batteries and prediction of optimized halogen doping: the effect of Li vacancies, halogens and halogen disorder Chem. Mater. 28 7955–63
    de Klerk N J J and Wagemaker M 2016 Diffusion mechanism of the sodium-ion solid electrolyte Na3PS4 and potential improvements of halogen doping Chem. Mater. 28 3122–30
    Deng Z, Zhu Z, Chu I-H and Ong S P 2017 Data-driven first-principles methods for the study and design of alkali superionic conductors Chem. Mater. 29 281–8
    Hynninen T, Musso T and Foster A S 2016 Limitations of reactive atomistic potentials in describing defect structures in oxides Modelling Simul. Mater. Sci. Eng. 24 035022
    Iype E, Hütter M, Jansen A P J, Nedea S V and Rindt C C M 2013 Parameterization of a reactive force field using a Monte Carlo algorithm J. Comput. Chem. 34 1143–54
    Trnka T, Tvaroˇska I and Kocˇa J 2018 Automated training of ReaxFF reactive force fields for energetics of enzymatic reactions J. Chem. Theory Comput. 14 291–302
    Mueller T, Hernandez A and Wang C 2020 Machine learning for interatomic potential models J. Chem. Phys. 152 050902
    Zuo Y et al 2020 Performance and cost assessment of machine learning interatomic potentials J. Phys. Chem. A 124 731–45
    Qi J, Banerjee S, Zuo Y, Chen C, Zhu Z, Holekevi Chandrappa M, Li X and Ong S 2021 Bridging the gap between simulated and experimental ionic conductivities in lithium superionic conductors Mater. Today Phys. 21 100463
    Novikov I S, Gubaev K, Podryabinkin E V and Shapeev A V 2021 The MLIP package: moment tensor potentials with MPI and active learning Mach. Learn.: Sci. Technol. 2 025002
    Friederich P, Häse F, Proppe J and Aspuru-Guzik A 2021 Machine-learned potentials for next-generation matter simulations Nat. Mater. 20 750–61
    Mishin Y 2021 Machine-learning interatomic potentials for materials science Acta Mater. 214 116980
    Miksch A M, Morawietz T, Kästner J, Urban A and Artrith N 2021 Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations Mach. Learn.: Sci. Technol. 2 031001
    Perdew J P, Burke K and Ernzerhof M 1996 Generalized gradient approximation made simple Phys. Rev. Lett. 77 3865–8
    Kraft M A, Culver S P, Calderon M, Böcher F, Krauskopf T, Senyshyn A, Dietrich C, Zevalkink A, Janek J and Zeier W G 2017 Influence of lattice polarizability on the ionic conductivity in the lithium superionic argyrodites Li6PS5 X (X = Cl, Br, I) J. Am. Chem. Soc. 139 10909–18
    Yu C, Ganapathy S, Hageman J, van Eijck L, van Eck E R H, Zhang L, Schwietert T, Basak S, Kelder E M and Wagemaker M 2018 Facile synthesis toward the optimal structure-conductivity characteristics of the argyrodite Li6PS5Cl solid-state electrolyte ACS Appl. Mater. Interfaces 10 33296–306
    Boulineau S, Courty M, Tarascon J-M and Viallet V 2012 Mechanochemical synthesis of Li-argyrodite Li6PS5X (X = Cl, Br, I) as sulfur-based solid electrolytes for all solid state batteries application Solid State Ion. 221 1–5
    Deiseroth H-J, Kong S-T, Eckert H, Vannahme J, Reiner C, Zaiß T and Schlosser M 2008 Li6PS5X: a class of crystalline Li-rich solids with an unusually high Li+ mobility Angew. Chem., Int. Ed. 47 755–8
    Blöchl P E 1994 Projector augmented-wave method Phys. Rev. B 50 17953–79
    Kresse G and Joubert D 1999 From ultrasoft pseudopotentials to the projector augmented-wave method Phys. Rev. B 59 1758–75
    Kresse G and Furthmüller J 1996 Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set Phys. Rev. B 54 11169–86
    Ong S P, Richards W D, Jain A, Hautier G, Kocher M, Cholia S, Gunter D, Chevrier V L, Persson K A and Ceder G 2013 Python materials genomics (pymatgen): a robust, open-source python library for materials analysis Comput. Mater. Sci. 68 314–9
    Nosé S 1984 A unified formulation of the constant temperature molecular dynamics methods J. Chem. Phys. 81 511–9
    Hoover W G 1985 Canonical dynamics: equilibrium phase-space distributions Phys. Rev. A 31 1695–7
    Perdew J P, Ruzsinszky A, Csonka G I, Vydrov O A, Scuseria G E, Constantin L A, Zhou X and Burke K 2008 Restoring the density-gradient expansion for exchange in solids and surfaces Phys. Rev. Lett. 100 136406
    Klimeˇs J, Bowler D R and Michaelides A 2010 Chemical accuracy for the van der Waals density functional J. Phys.: Condens. Matter 22 022201
    Sun J, Ruzsinszky A and Perdew J P 2015 Strongly constrained and appropriately normed semilocal density functional Phys. Rev. Lett. 115 036402
    Kitchaev D A, Peng H, Liu Y, Sun J, Perdew J P and Ceder G 2016 Energetics of MnO2 polymorphs in density functional theory Phys. Rev. B 93 045132
    Sai Gautam G and Carter E A 2018 Evaluating transition metal oxides within DFT-SCAN and SCAN + U frameworks for solar thermochemical applications Phys. Rev. Mater. 2 095401
    Devi R, Singh B, Canepa P and Sai Gautam G 2022 Effect of exchange-correlation functionals on the estimation of migration barriers in battery materials npj Comput. Mater. 8 160
    Peng H, Yang Z-H, Perdew J P and Sun J 2016 Versatile van der Waals density functional based on a meta-generalized gradient approximation Phys. Rev. X 6 041005
    Furness J W, Kaplan A D, Ning J, Perdew J P and Sun J 2020 Accurate and numerically efficient r2 SCAN meta-generalized gradient approximation J. Phys. Chem. Lett. 11 8208–15
    Plimpton S 1995 Fast parallel algorithms for short-range molecular dynamics J. Comput. Phys. 117 1–19
    Dickey J M and Paskin A 1969 Computer simulation of the lattice dynamics of solids Phys. Rev. 188 1407–18
    Ercolessi F and Adams J B 1994 Interatomic potentials from first-principles calculations: the force-matching method Europhys. Lett. 26 583
    Wang C, Aoyagi K, Wisesa P and Mueller T 2020 Lithium ion conduction in cathode coating materials from on-the-fly machine learning Chem. Mater. 32 3741–52
    Podryabinkin E V and Shapeev A V 2017 Active learning of linearly parametrized interatomic potentials Comput. Mater. Sci. 140 171–80
    Wang J, Panchal A A, Sai Gautam G and Canepa P 2022 The resistive nature of decomposing interfaces of solid electrolytes with alkali metal electrodes J. Mater. Chem. A 10 19732–42
    Famprikis T et al 2021 Insights into the rich polymorphism of the Na+ ion conductor Na3PS4 from the perspective of variable-temperature diffraction and spectroscopy Chem. Mater. 33 5652–67
    Krauskopf T, Culver S P and Zeier W G 2018 Local tetragonal structure of the cubic superionic conductor Na3PS4 Inorg. Chem. 57 4739–44
    Gorai P, Famprikis T, Singh B, Stevanovi´c V and Canepa P 2021 Devil is in the defects: electronic conductivity in solid electrolytes Chem. Mater. 33 7484–98
    Li Y, Canepa P and Gorai P 2022 Role of electronic passivation in stabilizing the lithium- LixPOyNz solid-electrolyte interphase PRX Energy 1 023004
    McCluskey M D and Haller E E 2018 Dopants and Defects in Semiconductors 0th edn (Boca Raton, FL: CRC Press)
    Galeener F L, Leadbetter A J and Stringfellow M W 1983 Comparison of the neutron, Raman and infrared vibrational spectra of vitreous SiO2, GeO2 and BeF2 Phys. Rev. B 27 1052–78
    Ding J 2022 Phonon anharmonicity and ionic diffusion in emergent energy materials PhD Thesis Duke University, Ann Arbor
    Van Hove L 1954 Correlations in space and time and born approximation scattering in systems of interacting particles Phys. Rev. 95 249–62
    Vineyard G H 1958 Scattering of slow neutrons by a liquid Phys. Rev. 110 999–1010
    Zhou L, Minafra N, Zeier W G and Nazar L F 2021 Innovative approaches to Li-argyrodite solid electrolytes for all-solid-state lithium batteries Acc. Chem. Res. 54 2717–28
  • 加载中



    Article Metrics

    Article Views(44) PDF downloads(42)
    Article Statistics
    Related articles from


    DownLoad:  Full-Size Img  PowerPoint