Machine learning descriptors for crystal materials: applications in Ni-rich layered cathode and lithium anode materials for high-energy-density lithium batteries

Abstract

Lithium batteries have revolutionized energy storage with their high energy density and long lifespan, but challenges such as energy density limitations, safety, and cost still need to be addressed. Crystalline materials, including Ni-rich cathodes and lithium anodes, play pivotal roles in the performance of high-energy-density lithium batteries. Understanding the micro-scale behavior and degradation mechanisms of these materials is crucial for improving macro-scale battery performance. Simulation methods, particularly machine learning (ML) techniques, have become indispensable tools in elucidating these intricate processes because of great efficiency and acceptable accuracy. ML methods depend on descriptors, which bridge the gap between crystal structures and input matrices of models. These descriptors encode essential atomic-level details in crystal structures, enabling predictions of material properties and behaviors relevant to lithium batteries. This paper reviews and discusses the diverse array of descriptors employed in the simulation of crystalline materials for lithium batteries with high energy density. Case studies highlight the effectiveness of different descriptors in simulating cathode behaviors such as Li/Ni disordering, screening of stable LiNi_0.8Co_0.1Mn_0.1O₂ (NMC811) configurations, and lithium deposition behaviors at the anode interface. The discussed descriptors can also be applied to other crystalline cathode, anode, and electrolyte materials in lithium batteries and advance the development of lithium batteries with superior energy density.

Keywords

Machine learning / crystal descriptors / high-energy-density lithium batteries / Ni-rich cathode / lithium anode

References

[1] Zheng Y,Ou J.A review of composite solid-state electrolytes for lithium batteries: fundamentals, key materials and advanced structures.Chem Soc Rev2020;49:8790-839

[2] Jiang Z,Yang Y.Machine-learning-revealed statistics of the particle-carbon/binder detachment in lithium-ion battery cathodes.Nat Commun2020;11:2310 PMCID:PMC7210251

[3] Wang C,Aykol M.Ionic conduction through reaction products at the electrolyte-electrode interface in all-solid-state Li⁺ batteries.ACS Appl Mater Interfaces2020;12:55510-9

[4] Gao YC,Chen X,Zhang R.Data-driven insight into the reductive stability of ion-solvent complexes in lithium battery electrolytes.J Am Chem Soc2023;145:23764-70

[5] Chen X,Shen X.Applying machine learning to rechargeable batteries: from the microscale to the macroscale.Angew Chem Int Ed Engl2021;60:24354-66

[6] Lombardo T,El-Bouysidy H.Artificial intelligence applied to battery research: hype or reality?.Chem Rev2022;122:10899-969 PMCID:PMC9227745

[7] Chen C,Ye W,Deng Z.A critical review of machine learning of energy materials.Adv Energy Mater2020;10:1903242

[8] Li S,Chen D,Nie Z.Encoding the atomic structure for machine learning in materials science.WIREs Comput Mol Sci2022;12:e1558

[9] Wang S,Liu J.Integrating crystal structure and numerical data for predictive models of lithium-ion battery materials: a modified crystal graph convolutional neural networks approach.J Energy Storage2024;80:110220

[10] Zhang Z,Li S,Chen M.Interpretable machine learning prediction of voltage and specific capacity for electrode materials.Adv Theor Simul2024;7:2400227

[11] Min K,Park K.Machine learning assisted optimization of electrochemical properties for Ni-rich cathode materials.Sci Rep2018;8:15778 PMCID:PMC6202356

[12] Saal JE,Aykol M,Wolverton C.Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD).JOM2013;65:1501-9

[13] Han T,Liu L,Wang L.Accuracy evaluation of different machine learning force field features.New J Phys2023;25:093007

[14] Batatia I,Chiang Y. A foundation model for atomistic materials chemistry. arXiv. [Preprint.] Mar 1, 2024 [accessed on 2024 Oct 21]. Available from: https://doi.org/10.48550/arXiv.2401.00096.

[15] Schütt KT,Kindermans PJ,Müller KR.SchNet - a deep learning architecture for molecules and materials.J Chem Phys2018;148:241722

[16] Xie T,Ganea OE,Jaakkola T. Crystal diffusion variational autoencoder for periodic material generation. arXiv. [Preprint.] Mar 14, 2022 [accessed on 2024 Oct 21]. Available from: https://doi.org/10.48550/arXiv.2110.06197.

[17] Cao Z,Lv J. Space group informed transformer for crystalline materials generation. arXiv. [Preprint.] Aug 16, 2024 [accessed on 2024 Oct 21]. Available from: https://doi.org/10.48550/arXiv.2403.15734.

[18] Gebauer NWA,Schütt KT. Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules. arXiv. [Preprint.] Jan 9, 2020 [accessed on 2024 Oct 21]. Available from: https://doi.org/10.48550/arXiv.1906.00957.

[19] Ward L,Choudhary A.A general-purpose machine learning framework for predicting properties of inorganic materials.npj Comput Mater2016;2:BFnpjcompumats201628

[20] Ong SP,Jain A.Python materials genomics (pymatgen): a robust, open-source python library for materials analysis.Comput Mater Sci2013;68:314-9

[21] Ward L,Faghaninia A.Matminer: an open source toolkit for materials data mining.Comput Mater Sci2018;152:60-9

[22] Himanen L,Morooka EV.DScribe: library of descriptors for machine learning in materials science.Comput Phys Commun2020;247:106949

[23] Laakso J,Homm H.Updates to the DScribe library: new descriptors and derivatives.J Chem Phys2023;158:234802

[24] Deml AM,Wolverton C.Predicting density functional theory total energies and enthalpies of formation of metal-nonmetal compounds by linear regression.Phys Rev B2016;93:085142

[25] Jha D,Paul A.ElemNet: deep learning the chemistry of materials from only elemental composition.Sci Rep2018;8:17593 PMCID:PMC6279928

[26] Leung K,Zavadil KR.Using atomic layer deposition to hinder solvent decomposition in lithium ion batteries: first-principles modeling and experimental studies.J Am Chem Soc2011;133:14741-54

[27] Yang S,Zhao J.Prediction on discharging properties of nickel–manganese materials for high-performance sodium-ion batteries via machine learning methods.Energy Technol2022;10:2200733

[28] Chen W,Yan D,Chen C.Machine learning and evolutionary prediction of superhard B-C-N compounds.npj Comput Mater2021;7:585

[29] Guo J,Pedersen K.Battery impedance spectrum prediction from partial charging voltage curve by machine learning.J Energy Chem2023;79:211-21

[30] Bartók AP,Csányi G.On representing chemical environments.Phys Rev B2013;87:184115

[31] Huo H.Unified representation of molecules and crystals for machine learning.Mach Learn Sci Technol2022;3:045017

[32] Novikov IS,Podryabinkin EV.The MLIP package: moment tensor potentials with MPI and active learning.Mach Learn Sci Technol2021;2:025002

[33] Shapeev AV.Moment tensor potentials: a class of systematically improvable interatomic potentials.Multiscale Model Sim2016;14:1153-73

[34] Drautz R.Atomic cluster expansion for accurate and transferable interatomic potentials.Phys Rev B2019;99:014104

[35] Bai X,Zhang Y.Dynamic stability of copper single-atom catalysts under working conditions.J Am Chem Soc2022;144:17140-8

[36] Chen C.A universal graph deep learning interatomic potential for the periodic table.Nat Comput Sci2022;2:718-28

[37] Chen C,Zuo Y,Ong SP.Graph networks as a universal machine learning framework for molecules and crystals.Chem Mater2019;31:3564-72

[38] Cheng J,Dong L.A geometric-information-enhanced crystal graph network for predicting properties of materials.Commun Mater2021;2:194

[39] Gong S,Xie T.Examining graph neural networks for crystal structures: Limitations and opportunities for capturing periodicity.Sci Adv2023;9:eadi3245 PMCID:PMC10637739

[40] Merchant A,Schoenholz SS,Cheon G.Scaling deep learning for materials discovery.Nature2023;624:80-5 PMCID:PMC10700131

[41] Du H,Zhang L.Rational design of deep learning networks based on a fusion strategy for improved material property predictions.J Chem Theory Comput2024;20:6756-71

[42] Cheng D,Han Q.ACGNet: an interpretable attention crystal graph neural network for accurate oxidation potential prediction.Electrochim Acta2024;473:143459

[43] Xie T.Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties.Phys Rev Lett2018;120:145301

[44] Louis SY,Nasiri A.Graph convolutional neural networks with global attention for improved materials property prediction.Phys Chem Chem Phys2020;22:18141-8

[45] Satorras VG,Welling M. E(n) equivariant graph neural networks. arXiv. [Preprint.] Feb 16, 2022 [accessed on 2024 Oct 21]. Available from: https://doi.org/10.48550/arXiv.2102.09844.

[46] Zhang D,Dai FZ,Zhang L. DPA-1: pretraining of attention-based deep potential model for molecular simulation. arXiv. [Preprint.] Sep 15, 2023 [accessed on 2024 Oct 21]. Available from: https://doi.org/10.48550/arXiv.2208.08236.

[47] Zhang D,Zhang X. DPA-2: towards a universal large atomic model for molecular and material simulation. arXiv. [Preprint.] Dec 24, 2023 [accessed on 2024 Oct 21]. Available from: https://arxiv.org/html/2312.15492v1.

[48] Chen C,Ye W,Ong SP.Learning properties of ordered and disordered materials from multi-fidelity data.Nat Comput Sci2021;1:46-53

[49] Chen C.AtomSets as a hierarchical transfer learning framework for small and large materials datasets.npj Comput Mater2021;7:639

[50] Li Y,Han Y.Local environment interaction-based machine learning framework for predicting molecular adsorption energy.J Mater Inf2024;4:4

[51] Zhao X.Origin of selective production of hydrogen peroxide by electrochemical oxygen reduction.J Am Chem Soc2021;9423-8

[52] Cao Z,Wang Y.MOFormer: self-supervised transformer model for metal-organic framework property prediction.J Am Chem Soc2023;145:2958-67 PMCID:PMC10041520

[53] Jain A,Hautier G.Commentary: the materials project: a materials genome approach to accelerating materials innovation.APL Mater2013;1:011002

[54] The Materials Project. Available from: https://www.Materialsproject.Org/. [Last accessed on 21 Oct 2024]

[55] Kirklin S,Meredig B.The open quantum materials database (OQMD): assessing the accuracy of DFT formation energies.npj Comput Mater2015;1:BFnpjcompumats201510

[56] Kim M,Gyu Park H,Min K.Maximizing the energy density and stability of Ni-rich layered cathode materials with multivalent dopants via machine learning.Chem Eng J2023;452:139254

[57] Lundberg S. A unified approach to interpreting model predictions. arXiv. [Preprint.] Nov 25, 2017 [accessed on 2024 Oct 22]. Available from: https://doi.org/10.48550/arXiv.1705.07874.

[58] Chen H,Lundberg SM.Algorithms to estimate Shapley value feature attributions.Nat Mach Intell2023;5:590-601

[59] Hu Y,Wen B.Grain boundary engineering in Nickel-rich cathode: a combination of high-throughput first-principles and interpretable machine learning study.Acta Mater2024;276:120144

[60] Jia Y,Fang C.Interpretable machine learning to accelerate the analysis of doping effect on Li/Ni exchange in Ni-rich layered oxide cathodes.J Phys Chem Lett2024;15:1765-73

[61] Dunn A,Ganose A,Jain A.Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm.npj Comput Mater2020;6:138

[62] MatBench. Available from: https://matbench.materialsproject.org/. [Last accessed on 22 Oct 2024]

[63] Behler J.Atom-centered symmetry functions for constructing high-dimensional neural network potentials.J Chem Phys2011;134:074106

[64] Valle M.Crystal fingerprint space - a novel paradigm for studying crystal-structure sets.Acta Crystallogr A2010;66:507-17

[65] Kim S,Jin T,Jung Y.A structure translation model for crystal compounds.npj Comput Mater2023;9:1094

[66] Isayev O,Toher C,Curtarolo S.Universal fragment descriptors for predicting properties of inorganic crystals.Nat Commun2017;8:15679 PMCID:PMC5465371

[67] Dinic F.Unconstrained machine learning screening for new Li-ion cathode materials enhanced by class balancing.Adv Theory Simul2023;6:2300081

[68] Gilmer J,Riley PF,Dahl GE. Neural message passing for Quantum chemistry. In. Proceedings of the 34th International Conference on Machine Learning; Sydney, Australia. 2017. pp. 1263-72. Available from: https://proceedings.mlr.press/v70/gilmer17a. [Last accessed on 22 Oct 2024]

[69] Jørgensen PB,Schmidt MN. Neural message passing with edge updates for predicting properties of molecules and materials. arXiv. [Preprint.] Jun 8, 2018 [accessed on 2024 Oct 22]. Available from: https://doi.org/10.48550/arXiv.1806.03146.

[70] He X,Zhu Z.Chemical and structural evolutions of Li–Mn-rich layered electrodes at different current densities.Energy Environ Sci2022;15:4137-47

[71] Choudhary K.Atomistic line graph neural network for improved materials property predictions.npj Comput Mater2021;7:650

[72] Wang H,Han J.DeePMD-kit: a deep learning package for many-body potential energy representation and molecular dynamics.Comput Phys Commun2018;228:178-84

[73] Zeng J,Lu D.DeePMD-kit v2: a software package for deep potential models.J Chem Phys2023;159:054801

[74] Jia W,Chen M,Lin L.Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning. In. SC20: International Conference for High Performance Computing, Networking, Storage and Analysis; 2020 Noc 09-19; Atlanta, USA. IEEE; 2020. pp. 1-14.

[75] Deng B,Jun K.CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling.Nat Mach Intell2023;5:1031-41

[76] Batatia I,Simm GNC,Csányi G. MACE: higher order equivariant message passing neural networks for fast and accurate force fields. arXiv. [Preprint.] Jan 26, 2023 [accessed on 2024 Oct 22]. Available from: https://doi.org/10.48550/arXiv.2206.07697.

[77] Genreith-Schriever AR,Phillips GS.Jahn-Teller distortions and phase transitions in LiNiO₂: insights from ab initio molecular dynamics and variable-temperature X-ray diffraction.Chem Mater2024;36:2289-303 PMCID:PMC10938510

[78] Chen L,Nie Z,Pan F.Generative models for inverse design of inorganic solid materials.J Mater Inf2021;1:4

[79] Ren Z,Noh J.An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties.Matter2022;5:314-35

[80] Zeni C,Zügner D. MatterGen: a generative model for inorganic materials design. arXiv. [Preprint.] Jan 29, 2024 [accessed on 2024 Oct 22]. Available from: https://doi.org/10.48550/arXiv.2312.03687.

[81] Myung S,Park K.Nickel-rich layered cathode materials for automotive lithium-ion batteries: achievements and perspectives.ACS Energy Lett2017;2:196-223

[82] MacNeil DD,Chen Z.A comparison of the electrode/electrolyte reaction at elevated temperatures for various Li-ion battery cathodes.J Power Sources2002;108:8-14

[83] Zhang J,Lei Y.Nickel-rich layered cathode LiNi_0.8Co_0.1Mn_0.1O₂ mediated by a selective lattice doping towards high-performance lithium ion battery.J Alloys Compd2023;957:170400

[84] Pechen LS,Medvedeva AE.Effect of dopants on the functional properties of lithium-rich cathode materials for lithium-ion batteries.Russ J Inorg Chem2021;66:777-88

[85] Shen Y,Zhang J.Sodium doping derived electromagnetic center of lithium layered oxide cathode materials with enhanced lithium storage.Nano Energy2022;94:106900

[86] Thackeray M,Bruce P.Lithium insertion into manganese spinels.Mater Res Bull1983;18:461-72

[87] Thackeray M,de Picciotto L,Goodenough J.Electrochemical extraction of lithium from LiMn₂O₄.Mater Res Bull1984;19:179-87

[88] Vanaphuti P,Ma L,Wang Y.Systematic study of different anion doping on the electrochemical performance of cobalt-free lithium–manganese-rich layered cathode.ACS Appl Energy Mater2020;3:4852-9

[89] Wang Y,Chen T,Zheng J.Factors that affect volume change during electrochemical cycling in cathode materials for lithium ion batteries.Phys Chem Chem Phys2022;24:2167-75

[90] Wang YY,Liu S,Ye SH.Elucidating the effect of the dopant ionic radius on the structure and electrochemical performance of Ni-rich layered oxides for lithium-ion batteries.ACS Appl Mater Interfaces2021;13:56233-41

[91] Yang W.Anion doping of LiNi_0.4Co_0.2Mn_0.4O₂ cathode material for lithium-ion batteries.Rare Metal Mat Eng2014;43:3133-7Available from: http://www.rmme.ac.cn/rmmeen/article/abstract/20141253. [Last accessed on 22 Oct 2024]

[92] McCalla E,Saubanère M.Visualization of O-O peroxo-like dimers in high-capacity layered oxides for Li-ion batteries.Science2015;350:1516-21

[93] Padhi AK,Goodenough JB.Phospho-olivines as positive-electrode materials for rechargeable lithium batteries.J Electrochem Soc1997;144:1188-94

[94] Shin Y.Surface morphology and surface stability against oxygen loss of the lithium-excess Li₂MnO₃ cathode material as a function of lithium concentration.ACS Appl Mater Interfaces2016;8:25595-602

[95] Wu Z,Zheng J.Prelithiation activates Li(Ni_0.5Mn_0.3Co_0.2)O₂ for high capacity and excellent cycling stability.Nano Lett2015;15:5590-6

[96] Yoon S,Lee J,Kim D.(In)Coherent-bond-networks in Ni-rich layered oxides for durable lithium-ion batteries.Chem Eng J2023;458:141472

[97] Zhang R,Zou P.Compositionally complex doping for zero-strain zero-cobalt layered cathodes.Nature2022;610:67-73

[98] Song Z,Yang H.Promoting high-voltage stability through local lattice distortion of halide solid electrolytes.Nat Commun2024;15:1481 PMCID:PMC10874449

[99] Wang T,Wu Y.Engineering a flexible and mechanically strong composite electrolyte for solid-state lithium batteries.J Energy Chem2020;46:187-90

[100] Wang Y,Ue M.Theoretical studies to understand surface chemistry on carbon anodes for lithium-ion batteries: reduction mechanisms of ethylene carbonate.J Am Chem Soc2001;123:11708-18

[101] Wu Q,Qi Y.Effect of the electric double layer (EDL) in multicomponent electrolyte reduction and solid electrolyte interphase (SEI) formation in lithium batteries.J Am Chem Soc2023;145:2473-84 PMCID:PMC9896563

[102] Yan C,Chen X.Regulating the inner Helmholtz plane for stable solid electrolyte interphase on lithium metal anodes.J Am Chem Soc2019;141:9422-9

[103] Duan J,Wang T.Shaping the contact between Li metal anode and solid-state electrolytes.Adv Funct Mater2020;30:1908701

[104] Tobishima S,Aoki M.Glyme-based nonaqueous electrolytes for rechargeable lithium cells.Electrochim Acta2004;49:979-87

[105] Ye Y,Liu J.Research progress of theoretical studies on polarons in cathode materials of lithium-ion batteries.Acta Phys Chim Sin2021;37:75-87

[106] Yin YC,Luo JD.A LaCl₃-based lithium superionic conductor compatible with lithium metal.Nature2023;616:77-83

[107] Yoshida K,Kazue Y.Oxidative-stability enhancement and charge transport mechanism in glyme-lithium salt equimolar complexes.J Am Chem Soc2011;133:13121-9

[108] Rubin M,Richardson T,von Rottkay K.Electrochromic lithium nickel oxide by pulsed laser deposition and sputtering.Sol Energ Mat Sol C1998;54:59-66

[109] Goodenough JB.Evolution of strategies for modern rechargeable batteries.Acc Chem Res2013;46:1053-61

[110] Xu Z,Song W.Sulfur-assisted surface modification of lithium-rich manganese-based oxide toward high anionic redox reversibility.Adv Mater2024;36:e2303612

[111] Yoshino A.The birth of the lithium-ion battery.Angew Chem Int Ed Engl2012;51:5798-800

[112] Zhang T,Tao Z.Understanding electrode materials of rechargeable lithium batteries via DFT calculations.Prog Nat Sci Mater2013;23:256-72

[113] Zheng J,Xin C.Role of superexchange interaction on tuning of Ni/Li disordering in layered Li(Ni_xMn_yCo_z)O₂.J Phys Chem Lett2017;8:5537-42

[114] Zheng J,Liu T.Ni/Li disordering in layered transition metal oxide: electrochemical impact, origin, and control.Acc Chem Res2019;52:2201-9

[115] Lai G,Fang C.A deep neural network interface potential for Li-Cu systems.Adv Mater Interfaces2022;9:2201346

[116] Lai G,Jiao J.The mechanism of external pressure suppressing dendrites growth in Li metal batteries.J Energy Chem2023;79:489-94

[117] Jiao J,Zhao L.Self-healing mechanism of lithium in lithium metal.Adv Sci2022;9:e2105574 PMCID:PMC9036043

[118] Lai G,Fang C.The mechanism of Li deposition on the Cu substrates in the anode-free Li metal batteries.Small2023;19:e2205416

[119] Lai G,Yao J,Ouyang C.Analysis of Li metal anode by machine learning potential.J Chin Ceram Soc2023;51:469-75

[120] Li S,Xie Y,Jia J.Developing high-performance lithium metal anode in liquid electrolytes: challenges and progress.Adv Mater2018;30:e1706375

[121] Wang T,Zhang B.A self-regulated gradient interphase for dendrite-free solid-state Li batteries.Energy Environ Sci2022;15:1325-33

[122] Wen J,Wang C.A tailored interface design for anode-free solid-state batteries.Adv Mater2024;36:e2307732

[123] Zunger A.Inverse design in search of materials with target functionalities.Nat Rev Chem2018;2:BFs415700180121

[124] Yang N,Zheng J.Independent regulation of the lithium-ion conductivity of LiF using elemental doping: a first-principles study.Phys Rev Mater2024;8:015403

[125] Jalem R,Qi J,Ong SP.Lithium dynamics at grain boundaries of β-Li₃PS₄ solid electrolyte.Energy Adv2023;2:2029-41