Predicting oxidation and spin states by high-dimensional neural networks: Applications to lithium manganese oxide spinels
Open accessAbstract
Lithium ion batteries often contain transition metal oxides such as LixMn2O4 (0 ≤ x ≤ 2). Depending on the Li content, different ratios of MnIII to MnIV ions are present. In combination with electron hopping, the Jahn–Teller distortions of the MnIIIO6 octahedra can give rise to complex phenomena such as structural transitions and conductance. While for small model systems oxidation and spin states can be determined using density functional theory (DFT), the investigation of dynamical phenomena by DFT is too demanding. Previously, we have shown that a high-dimensional neural network potential can extend molecular dynamics (MD) simulations of LixMn2O4 to nanosecond time scales, but these simulations did not provide information about the electronic structure. Here, we extend the use of neural networks to the prediction of atomic oxidation and spin states. The resulting high-dimensional neural network is able to predict the spins of the Mn ions with an error of only 0.03 ℏ. We find that the Mn eg electrons are correctly conserved and that the number of Jahn–Teller distorted MnIIIO6 octahedra is predicted precisely for different Li loadings. A charge ordering transition is observed between 280 K and 300 K, which matches resistivity measurements. Moreover, the activation energy of the electron hopping conduction above the phase transition is predicted to be 0.18 eV, deviating only 0.02 eV from experiment. This work demonstrates that machine learning is able to provide an accurate representation of both the geometric and the electronic structure dynamics of LixMn2O4 on time and length scales that are not accessible by ab initio MD.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Low-cost, topological, three-dimensional, one-hot chemical encoding, and geometric descriptors are often employed for this purpose in transition-metal chemistry.
“Low-cost, topological (5, 7, 32, 92-94), three-dimensional (95-100), one-hot chemical encoding (92, 101), and geometric (e.g., for MOF pores) (102-104) descriptors are often employed for this purpose in transition-metal chemistry.”
From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [96]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Projector augmented-wave method
Blöchl, P. E. (1994) · Physical Review B · doi:10.1103/physrevb.50.17953 · Cited by 92,732 · see citing works
Self-citationGrimme, S., Antony, J., Ehrlich, S., & Krieg, H. (2010) · The Journal of Chemical Physics · doi:10.1063/1.3382344 · Cited by 59,686 · see citing works
Fast Parallel Algorithms for Short-Range Molecular Dynamics
Plimpton, S. (1995) · Journal of Computational Physics · doi:10.1006/jcph.1995.1039 · Cited by 44,721 · cited 1× · see citing works
“Geometry optimizations and MD simulations driven by the HDNNP were performed using the Largescale Atomic/Molecular Massively Parallel Simulator (LAMMPS) (version from August 7, 2019) [73, 74].”
MethodA New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751 · cited 1× · see citing works
“The details of the training process [70, 71] including the description of the adapted weight initialization method [17, 72] are described in the Supporting Information.”
MethodEffect of the damping function in dispersion corrected density functional theory
Grimme, S., Ehrlich, S., & Goerigk, L. (2011) · Journal of Computational Chemistry · doi:10.1002/jcc.21759 · Cited by 28,221 · cited 1× · see citing works
“D3 dispersion corrections were applied using the DFT-D3 software (version from June 14, 2016) [67, 68].”
MethodCanonical dynamics: Equilibrium phase-space distributions
Hoover, W. G. (1985) · Physical Review A · doi:10.1103/physreva.31.1695 · Cited by 23,453 · cited 2× · see citing works
“The simulations were run in the isothermal-isobaric (NpT ) ensemble applying the Nosé-Hoover [76, 77] thermostat and barostat at a pressure of p = 1 bar.”
MethodMultilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 1× · see citing works
“The great advantage of neural networks is their ability to represent multidimensional real-valued functions with in principle arbitrary precision [61].”
BackgroundIssues and challenges facing rechargeable lithium batteries
Tarascon, J. ‐., & Armand, M. B. (2001) · Nature · doi:10.1038/35104644 · Cited by 21,210 · cited 1× · see citing works
“The identification of new battery materials with improved properties is a very active fields of research [1, 2].”
BackgroundVisualization and analysis of atomistic simulation data with OVITO–the Open Visualization Tool
Stukowski, A. (2009) · Modelling and Simulation in Materials Science and Engineering · doi:10.1088/0965-0393/18/1/015012 · Cited by 16,689 · see citing works
(2010) · Cited by 14,134 · see citing works
Challenges for Rechargeable Li Batteries
Goodenough, J. B., & Kim, Y. (2009) · Chemistry of Materials · doi:10.1021/cm901452z · Cited by 11,019 · see citing works
A molecular dynamics method for simulations in the canonical ensemble
Nosé, S. (1984) · Molecular Physics · doi:10.1080/00268978400101201 · Cited by 10,049 · see citing works
Li-ion battery materials: present and future
Nitta, N., Wu, F., Lee, J. T., & Yushin, G. N. (2014) · Materials Today · doi:10.1016/j.mattod.2014.10.040 · Cited by 7,421 · see citing works
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Behler, J., & Parrinello, M. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.146401 · Cited by 5,010 · see citing works
Self-citationStability of polyatomic molecules in degenerate electronic states - I—Orbital degeneracy
Jahn, H. A., & Teller, E. (1937) · Proceedings of the Royal Society of London A Mathematical and Physical Sciences · doi:10.1098/rspa.1937.0142 · Cited by 3,227 · see citing works
Wales, D. J., & Doye, J. P. K. (1997) · The Journal of Physical Chemistry A · doi:10.1021/jp970984n · Cited by 3,030 · see citing works
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
Rupp, M., Tkatchenko, A., Müller, K.-R., & von Lilienfeld, O. A. (2012) · Physical Review Letters · doi:10.1103/physrevlett.108.058301 · Cited by 2,312 · see citing works
Inverse molecular design using machine learning: Generative models for matter engineering
Sánchez-Lengeling, B., & Aspuru‐Guzik, A. (2018) · Science · doi:10.1126/science.aat2663 · Cited by 2,087 · see citing works
Lithium insertion into manganese spinels
Thackeray, M. M., David, W. I. F., Bruce, P. G., & Goodenough, J. B. (1983) · Materials Research Bulletin · doi:10.1016/0025-5408(83)90138-1 · Cited by 1,778 · cited 1× · see citing works
“An important example is the commercially used lithium manganese oxide spinel, LixMn2O4 with 0 ≤ x ≤ 2 [4, 5].”
MethodAtom-centered symmetry functions for constructing high-dimensional neural network potentials
Behler, J. (2011) · The Journal of Chemical Physics · doi:10.1063/1.3553717 · Cited by 1,621 · cited 1× · see citing works
“Therefore, the Cartesian coordinates are transformed to atom-centered symmetry functions (ACSFs) G [42], which meet all these requirements and describe the local chemical environments of each atom inside a cutoff radius Rc.”
MethodSelf-citationManganese oxides for lithium batteries
Thackeray, M. M. (1997) · Progress in Solid State Chemistry · doi:10.1016/s0079-6786(97)81003-5 · Cited by 1,479 · see citing works
Perspective: Machine learning potentials for atomistic simulations
Behler, J. (2016) · The Journal of Chemical Physics · doi:10.1063/1.4966192 · Cited by 1,435 · see citing works
Self-citationTheory of first-order phase transitions
Binder, K. (1987) · Reports on Progress in Physics · doi:10.1088/0034-4885/50/7/001 · Cited by 1,081 · cited 1× · see citing works
“This continuous change of the order parameter over a wider temperature range is expected because of finite size effects [82, 83].”
BackgroundMachine Learning Interatomic Potentials as Emerging Tools for Materials Science
Deringer, V. L., Caro, M. A., & Cśanyi, G. (2019) · Advanced Materials · doi:10.1002/adma.201902765 · Cited by 1,051 · see citing works
Crystal Distortion in Magnetic Compounds
Kanamori, J. (1960) · Journal of Applied Physics · doi:10.1063/1.1984590 · Cited by 982 · cited 1× · see citing works
“with the distances dx, dy, and dz of the opposite OO corners and the mean opposite O-O distance d [79].”
BackgroundMachine Learning for Molecular Simulation
Noé, F., Tkatchenko, A., Müller, K.-R., & Clementi, C. (2020) · Annual Review of Physical Chemistry · doi:10.1146/annurev-physchem-042018-052331 · Cited by 956 · see citing works
High-Resolution X-ray Emission and X-ray Absorption Spectroscopy
de Groot, F. M. F. (2001) · Chemical Reviews · doi:10.1021/cr9900681 · Cited by 882 · see citing works
Mills, G., & Jónsson, H. (1994) · Physical Review Letters · doi:10.1103/physrevlett.72.1124 · Cited by 872 · see citing works
Constructing high‐dimensional neural network potentials: A tutorial review
Behler, J. (2015) · International Journal of Quantum Chemistry · doi:10.1002/qua.24890 · Cited by 864 · cited 2× · see citing works
“The HDNN for the atomic spins as well as the HDNNP for the potential energy surface of LixMn2O4 were constructed using the RuNNer code (version from December 4, 2018 and August 22, 2019, respectively) [43, 62, 69].”
MethodSelf-citationMultiplet effects in X-ray spectroscopy
de Groot, F. M. F. (2004) · Coordination Chemistry Reviews · doi:10.1016/j.ccr.2004.03.018 · Cited by 799 · see citing works
Finite-size effects at temperature-driven first-order transitions
Challa, M. S. S., Landau, D. P., & Binder, K. (1986) · Physical review. B, Condensed matter · doi:10.1103/physrevb.34.1841 · Cited by 731 · see citing works
Behler, J. (2017) · Angewandte Chemie International Edition · doi:10.1002/anie.201703114 · Cited by 695 · cited 1× · see citing works
“The HDNN for the atomic spins as well as the HDNNP for the potential energy surface of LixMn2O4 were constructed using the RuNNer code (version from December 4, 2018 and August 22, 2019, respectively) [43, 62, 69].”
MethodSelf-citationMachine learning of molecular electronic properties in chemical compound space
Montavon, G., Rupp, M., Gobre, V., Vazquez-Mayagoitia, A., Hansen, K., Tkatchenko, A., Müller, K.-R., & von Lilienfeld, O. A. (2013) · New Journal of Physics · doi:10.1088/1367-2630/15/9/095003 · Cited by 631 · see citing works
Covalency competition dominates the water oxidation structure–activity relationship on spinel oxides
Sun, Y., Liao, H., Wang, J., Chen, B., Sun, S., Ong, S. J. H., Xi, S., Diao, C., Du, Y., Wang, J., et al. (2020) · Nature Catalysis · doi:10.1038/s41929-020-0465-6 · Cited by 611 · see citing works
Hautier, G., Fischer, C. C., Jain, A., Mueller, T., & Ceder, G. (2010) · Chemistry of Materials · doi:10.1021/cm100795d · Cited by 580 · see citing works
THE STEREOCHEMICAL MECHANISM OF THE COOPERATIVE EFFECTS IN HEMOGLOBIN REVISITED
Perutz, M. F., Wilkinson, A. J., Paoli, M., & Dodson, G. G. (1998) · Annual Review of Biophysics and Biomolecular Structure · doi:10.1146/annurev.biophys.27.1.1 · Cited by 562 · see citing works
Neural network models of potential energy surfaces
Blank, T. B., Brown, S. D., Calhoun, A. W., & Doren, D. J. (1995) · The Journal of Chemical Physics · doi:10.1063/1.469597 · Cited by 502 · cited 1× · see citing works
“The details of the training process [70, 71] including the description of the adapted weight initialization method [17, 72] are described in the Supporting Information.”
MethodHow van der Waals interactions determine the unique properties of water
Morawietz, T., Singraber, A., Dellago, C., & Behler, J. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1602375113 · Cited by 487 · see citing works
Self-citationSchütt, K. T., Gastegger, M., Tkatchenko, A., Müller, K. R., & Maurer, R. J. (2019) · Nature Communications · doi:10.1038/s41467-019-12875-2 · Cited by 476 · see citing works
High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide
Artrith, N., Morawietz, T., & Behler, J. (2011) · Physical Review B · doi:10.1103/physrevb.83.153101 · Cited by 411 · see citing works
Self-citationRodríguez-Carvajal, J., Rousse, G., Masquelier, C., & Hervieu, M. (1998) · Physical Review Letters · doi:10.1103/physrevlett.81.4660 · Cited by 332 · see citing works
Atomic-resolution imaging of oxidation states in manganites
Varela, M., Oxley, M. P., Luo, W., Tao, J., Watanabe, M., Lupini, A. R., Pantelides, S. T., & Pennycook, S. J. (2009) · Physical Review B · doi:10.1103/physrevb.79.085117 · Cited by 320 · see citing works
Ghasemi, S. A., Hofstetter, A., Saha, S., & Goedecker, S. (2015) · Physical Review B · doi:10.1103/physrevb.92.045131 · Cited by 293 · see citing works
Janet, J. P., & Kulik, H. J. (2017) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.7b08750 · Cited by 289 · see citing works
Behler, J., Martoňák, R., Donadio, D., & Parrinello, M. (2008) · Physical Review Letters · doi:10.1103/physrevlett.100.185501 · Cited by 235 · see citing works
Self-citationJahn–Teller distortion and electronic structure of LiMn2O4
Ouyang, C., Shi, S., & Lei, M. S. (2008) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2008.06.123 · Cited by 232 · see citing works
Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
Rupp, M., Ramakrishnan, R., & von Lilienfeld, O. A. (2015) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5b01456 · Cited by 211 · see citing works
Natarajan, S. K., & Behler, J. (2016) · Physical Chemistry Chemical Physics · doi:10.1039/c6cp05711j · Cited by 209 · see citing works
Self-citationJanet, J. P., Chan, L., & Kulik, H. J. (2018) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.8b00170 · Cited by 200 · see citing works
Janet, J. P., Ramesh, S., Duan, C., & Kulik, H. J. (2020) · ACS Central Science · doi:10.1021/acscentsci.0c00026 · Cited by 200 · see citing works
Predicting electronic structure properties of transition metal complexes with neural networks
Janet, J. P., & Kulik, H. J. (2017) · Chemical Science · doi:10.1039/c7sc01247k · Cited by 199 · see citing works
Ohzuku, T., Kitagawa, M., & Hirai, T. (1989) · Journal of The Electrochemical Society · doi:10.1149/1.2096421 · Cited by 197 · see citing works
Bisquert, J. (2008) · Physical Chemistry Chemical Physics · doi:10.1039/b719943k · Cited by 194 · see citing works
Morawietz, T., Sharma, V., & Behler, J. (2012) · The Journal of Chemical Physics · doi:10.1063/1.3682557 · Cited by 185 · see citing works
Self-citationBisquert, J. (2004) · The Journal of Physical Chemistry B · doi:10.1021/jp035397i · Cited by 170 · cited 1× · see citing works
“because the electron hopping occurs always to adjacent Mn sites with the nearest-neighbor Mn-Mn distance d [86].”
BackgroundPhases LixMnO2λ rattachees au type spinelle
Mosbah, A., VERBAERE, A., & Tournoux, M. (1983) · Materials Research Bulletin · doi:10.1016/0025-5408(83)90045-4 · Cited by 156 · see citing works
Verwey-Type Transition and Magnetic Properties of the LiMn2O4Spinels
Shimakawa, Y., Numata, T., & Tabuchi, J. (1997) · Journal of Solid State Chemistry · doi:10.1006/jssc.1997.7366 · Cited by 155 · see citing works
From Molecular Fragments to the Bulk: Development of a Neural Network Potential for MOF-5
Eckhoff, M., & Behler, J. (2019) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.8b01288 · Cited by 133 · see citing works
Self-citationArtrith, N., Hiller, B., & Behler, J. (2012) · physica status solidi (b) · doi:10.1002/pssb.201248370 · Cited by 129 · see citing works
Self-citationHigh-Dimensional Neural Network Potentials for Organic Reactions and an Improved Training Algorithm
Gastegger, M., & Marquetand, P. (2015) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5b00211 · Cited by 128 · see citing works
Electrodes for lithium batteries
Goodenough, J. B., Manthiram, A., & Wnętrzewski, B. (1993) · Journal of Power Sources · doi:10.1016/0378-7753(93)80124-8 · Cited by 115 · cited 1× · see citing works
“The activation energy for the eg electron migration is a consequence of the associated Jahn-Teller distortion of the MnO6 octahedra locally trapping the electrons [11, 12].”
BackgroundHellström, M., & Behler, J. (2016) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.6b01448 · Cited by 87 · see citing works
Self-citationSeeing Is Believing: Experimental Spin States from Machine Learning Model Structure Predictions
Taylor, M. G., Yang, T., Lin, S., Nandy, A., Janet, J. P., Duan, C., & Kulik, H. J. (2020) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.0c01458 · Cited by 81 · see citing works
Single Crystal X-ray Diffraction Study of the Spinel-type LiMn2O4
Akimoto, J., Takahashi, Y., Gotoh, Y., & Mizuta, S. (2000) · Chemistry of Materials · doi:10.1021/cm0003673 · Cited by 75 · see citing works
Zhang, S., Livi, K. J. T., Gaillot, A., Stone, A. T., & Veblen, D. R. (2010) · American Mineralogist · doi:10.2138/am.2010.3468 · Cited by 72 · see citing works
Houlding, S., Liem, S. Y., & Popelier, P. L. A. (2007) · International Journal of Quantum Chemistry · doi:10.1002/qua.21507 · Cited by 66 · see citing works
Electronic structure of Pr1−xCaxMnO3
Sotoudeh, M., Rajpurohit, S., Blöchl, P. E., Mierwaldt, D., Norpoth, J., Владимирович, Р. В., Mildner, S., Kressdorf, B., Ifland, B., & Jooß, C. (2017) · Physical review. B./Physical review. B · doi:10.1103/physrevb.95.235150 · Cited by 57 · see citing works
Self-citationKristallographische, elektronische und magnetische Eigenschaften des Spinells Li[Mn2]O4
Schutte, L. M., Colsmann, G., & Reuter, B. (1979) · Journal of Solid State Chemistry · doi:10.1016/0022-4596(79)90161-0 · Cited by 54 · see citing works
Machine-Learning Energy Gaps of Porphyrins with Molecular Graph Representations
Li, Z., Omidvar, N., Chin, W. S., Robb, E., Morris, A. J., Achenie, L. E. K., & Xin, H. (2018) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.8b02842 · Cited by 54 · see citing works
Eckhoff, M., Schönewald, F., Risch, M., Volkert, C. A., Blöchl, P. E., & Behler, J. (2020) · Physical review. B./Physical review. B · doi:10.1103/physrevb.102.174102 · Cited by 43 · see citing works
Self-citationLiMn2O4low-temperature phase: synchrotron and neutron diffraction study
Massarotti, V., Capsoni, D., Bini, M., Scardi, P., Leoni, M., Baron, V., & Berg, H. (1999) · Journal of Applied Crystallography · doi:10.1107/s0021889899011577 · Cited by 40 · see citing works
Electrical transport properties in LiMn2O4
Iguchi, E., Nakamura, N., & Aoki, A. (1998) · Philosophical Magazine B · doi:10.1080/13642819808206727 · Cited by 33 · cited 3× · see citing works
“This matches the experimental expectation [14] because for strongly correlated oxides this frequency is in the range from 10(13) to 10(14) s−1 [88].”
BackgroundMethodHybrid density functional theory benchmark study on lithium manganese oxides
Eckhoff, M., Blöchl, P. E., & Behler, J. (2020) · Physical review. B./Physical review. B · doi:10.1103/physrevb.101.205113 · Cited by 29 · see citing works
Self-citationSingle-crystal X-ray structure analysis of the low temperature form of LiMn2O4
Akimoto, J. (2004) · Solid State Ionics · doi:10.1016/j.ssi.2004.01.051 · Cited by 26 · cited 1× · see citing works
“The crystal structure of LixMn2O4 in the composition range 0 ≤ x ≤ 1 is a cubic spinel with space group Fd3m for temperatures above ∼ 290 K [10, 16].”
BackgroundPiszora, P. (2004) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2004.06.013 · Cited by 20 · see citing works
Takahashi, Y., Akimoto, J., Gotoh, Y., Dokko, K., Nishizawa, M., & Uchida, I. (2003) · Journal of the Physical Society of Japan · doi:10.1143/jpsj.72.1483 · Cited by 16 · see citing works
Schönewald, F., Eckhoff, M., Baumung, M., Risch, M., Blöchl, P. E., Behler, J., & Volkert, C. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.04217 · Cited by 4 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 7
- 9 H. A. Jahn and E. Teller, 'Stability of polyatomic molecules in degenerate electronic states,' Proc. Royal Soc. Lond. A 161 , 220235 (1937).
- 26 F. de Groot and A. Kotani, Core Level Spectroscopy of Solids (CRC Press, Boca Raton, 2008).
- 57 E. McCafferty, Introduction to Corrosion Science (Springer, New York, 2010).
- 80 H. J´ onsson, G. Mills, and K. W. Jacobsen, Classical and Quantum Dynamics in Condensed Phase Simulations (World Scientific, Singapore, 1998).
- 83 N. W. Ashcroft and N. D. Mermin, Solid State Physics (Saunders College, New York, 1976).
- 86 H. Mehrer, Diffusion in Solids (Springer, Berlin, 2007).
- 87 J. C. Phillips, Physics of HighT c Superconductors (Academic Press, San Diego, 1989).
Cited by
Sorted by citations
Four Generations of High-Dimensional Neural Network Potentials
Behler, J. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.0c00868 · Cited by 892 · see citing works
Self-citationNandy, A., Duan, C., Taylor, M. G., Liu, F., Steeves, A. H., & Kulik, H. J. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00347 · Cited by 358 · see citing works
Deep dive into machine learning density functional theory for materials science and chemistry
Fiedler, L., Shah, K., Bußmann, M., & Cangi, A. (2022) · Physical Review Materials · doi:10.1103/physrevmaterials.6.040301 · Cited by 117 · see citing works
Eckhoff, M., & Behler, J. (2021) · npj Computational Materials · doi:10.1038/s41524-021-00636-z · Cited by 91 · see citing works
Self-citationHow to train a neural network potential
Tokita, A. M., & Behler, J. (2023) · The Journal of Chemical Physics · doi:10.1063/5.0160326 · Cited by 82 · see citing works
Self-citationAccelerated Atomistic Modeling of Solid-State Battery Materials With Machine Learning
Guo, H., Wang, Q., Stuke, A., Urban, A., & Artrith, N. (2021) · Frontiers in Energy Research · doi:10.3389/fenrg.2021.695902 · Cited by 70 · see citing works
“Eckhoff et al. constructed an ANN potential for Li x Mn 2 O 4 with Jahn-Teller distortions that can predict a series of properties, including volume change, Li diffusion barrier, phonon frequencies ( Figure 4A ) (Eckhoff et al., 2020b), oxidation, and spin states (Eckhoff et al., 2020a).”
MethodMachine Learning for the Discovery, Design, and Engineering of Materials.
Duan, C., Nandy, A., & Kulik, H. J. (2022) · Annual Review of Chemical and Biomolecular Engineering · doi:10.1146/annurev-chembioeng-092320-120230 · Cited by 69 · see citing works
2023 roadmap for potassium-ion batteries
Xu, Y., Titirici, M., Chen, J., Corà, F., Cullen, P., Edge, J., Fan, K., Fan, L., Feng, J., Hosaka, T., et al. (2023) · Journal of Physics: Energy · doi:10.1088/2515-7655/acbf76 · Cited by 53 · see citing works
Chun, H., Lee, E., Nam, K., Jang, J., Kyoung, W., Noh, S. H., & Han, B. (2021) · Chem Catalysis · doi:10.1016/j.checat.2021.06.001 · Cited by 59 · see citing works
Insights into lithium manganese oxide–water interfaces using machine learning potentials
Eckhoff, M., & Behler, J. (2021) · The Journal of Chemical Physics · doi:10.1063/5.0073449 · Cited by 51 · see citing works
“41,64,65 The HDNNP and HDNNS were constructed using the RuNNer code (versions from October 19, 2020 and December 4, 2018, respectively).”
MethodSelf-citationLifelong Machine Learning Potentials
Eckhoff, M., & Reiher, M. (2023) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c00279 · Cited by 45 · see citing works
“This construction, however, leads to an unfavorable scaling in the number of descriptors with respect to the number of elements.”
BackgroundSelf-citationMachine Learning Interatomic Potentials for Heterogeneous Catalysis
Tang, D., Ketkaew, R., & Luber, S. (2024) · Chemistry - A European Journal · doi:10.1002/chem.202401148 · Cited by 50 · see citing works
Machine-learned interatomic potentials: Recent developments and prospective applications
Eyert, V., Wormald, J. L., Curtin, W. A., & Wimmer, E. (2023) · Journal of materials research/Pratt's guide to venture capital sources · doi:10.1557/s43578-023-01239-8 · Cited by 44 · see citing works
“This is different in the method proposed by Eckhoff and Behler [66, 67], which includes the full spin structure within each local atomic cluster.”
Kouhestani, H. S., Yi, X., Qi, G., Liu, X., Wang, R., Gao, Y., Yu, X. L., & Liu, L. (2022) · Energies · doi:10.3390/en15186599 · Cited by 36 · see citing works
Hwang, S., Jung, J., Hong, C., Jeong, W., Kang, S., & Han, S. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.3c06210 · Cited by 29 · see citing works
Karimi, E., Iglauer, S., & Azhar, M. R. (2025) · Advances in Colloid and Interface Science · doi:10.1016/j.cis.2025.103686 · Cited by 23 · see citing works
Machine Learning Potentials with the Iterative Boltzmann Inversion: Training to Experiment
Matin, S., Allen, A. E. A., Smith, J. S., Lubbers, N., Jadrich, R. B., Messerly, R. A., Nebgen, B. T., Li, Y. W., Tretiak, S., & Barros, K. M. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c01051 · Cited by 24 · see citing works
Machine learning for exploring small polaron configurational space
Birschitzky, V. C., Ellinger, F., Diebold, U., Reticcioli, M., & Franchini, C. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00805-8 · Cited by 22 · see citing works
Harper, D. R., Nandy, A., Arunachalam, N., Duan, C., Janet, J. P., & Kulik, H. J. (2022) · The Journal of Chemical Physics · doi:10.1063/5.0082964 · Cited by 22 · see citing works
Ab initio machine learning of phase space averages
Weinreich, J., Lemm, D., von Rudorff, G. F., & von Lilienfeld, O. A. (2022) · The Journal of Chemical Physics · doi:10.1063/5.0095674 · Cited by 18 · see citing works
Machine Learning Small Polaron Dynamics
Birschitzky, V. C., Leoni, L., Reticcioli, M., & Franchini, C. (2025) · Physical Review Letters · doi:10.1103/physrevlett.134.216301 · Cited by 17 · see citing works
van der Minne, E., Vensaus, P., Ratovskii, V., Hariharan, S., Behrends, J., Franchini, C., Fransson, J., Dhesi, S. S., Gunkel, F., Gossing, F., et al. (2025) · Advanced Energy Materials · doi:10.1002/aenm.202503556 · Cited by 16 · see citing works
Romano, S., de Hijes, P. M., Meier, M., Kresse, G., Franchini, C., & Christoph Dellago, A. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c01507 · Cited by 12 · see citing works
“We adopted the exponential atomic centered symmetry functions [48] already developed for bulk water in [49] and expanded it to account for the bulk magnetite and the interfacial regions [50].”
Nonclassical Nucleation of Zinc Oxide from a Physically Motivated Machine-Learning Approach
Goniakowski, J., Menon, S. K., Laurens, G., & Lam, J. (2022) · The Journal of Physical Chemistry C · doi:10.1021/acs.jpcc.2c06341 · Cited by 11 · see citing works
CoRe optimizer: an all-in-one solution for machine learning
Eckhoff, M., & Reiher, M. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad1f76 · Cited by 10 · see citing works
Self-citationMatin, S., Allen, A. E. A., Shinkle, E., Pachalieva, A. A., Craven, G. T., Nebgen, B. T., Smith, J. S., Messerly, R. A., Li, Y. W., Tretiak, S., et al. (2025) · Digital Discovery · doi:10.1039/d5dd00085h · Cited by 8 · see citing works
Ji, J., & Lee, B. (2022) · Journal of Power Sources · doi:10.1016/j.jpowsour.2022.231790 · Cited by 8 · see citing works
Jin, L., Ji, Y., Wang, H., Ding, L., & Li, Y. (2021) · Physical Chemistry Chemical Physics · doi:10.1039/d1cp02963k · Cited by 7 · see citing works
A high-dimensional neural network potential for Co3O4
Omranpour, A., & Behler, J. (2024) · Journal of Physics Condensed Matter · doi:10.1088/1361-648x/ad9f09 · Cited by 6 · see citing works
Self-citationAtomistic simulations of oxide–water interfaces using machine learning potentials
Elsner, J., Lausch, K. N., & Behler, J. (2025) · Chemical Physics Reviews · doi:10.1063/5.0268292 · Cited by 5 · see citing works
Self-citationModeling Single-Crystal Battery Materials: From Fundamental Understanding to Performance Evaluation
Yuan, S., Weitzner, S. E., Jeong, W., Zhang, S., Wang, B., Feng, L., Kaufman, J. L., Kim, K., Qi, Y., & Wan, L. F. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00360 · Cited by 5 · see citing works
A bin and hash method for analyzing reference data and descriptors in machine learning potentials
Paleico, M. L., & Behler, J. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abe663 · Cited by 5 · see citing works
Self-citationTeaching oxidation states to neural networks
Malica, C., & Marzari, N. (2025) · npj Computational Materials · doi:10.1038/s41524-025-01709-z · Cited by 4 · see citing works
“Furthermore, some models incorporate the concept of oxidation state through geometrical considerations 60 .”
Amorphous MoS2 from a machine learning inter-atomic potential
Kety, K., Tsogbadrakh, N., Nawaz, H., Rostami, S., & Seriani, N. (2024) · The Journal of Chemical Physics · doi:10.1063/5.0211841 · Cited by 3 · see citing works
Omranpour, A., & Behler, J. (2025) · ChemCatChem · doi:10.1002/cctc.202501321 · Cited by 2 · see citing works
Self-citationRinaldi, M., Kick, M., Reuter, K., & Carbogno, C. (2025) · Journal of Physics Materials · doi:10.1088/2515-7639/adeaec · Cited by 1 · see citing works
Hashimoto, S., & Watanabe, T. (2024) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ad29d0 · Cited by 1 · see citing works
CoRe Optimizer: An All-in-One Solution for Machine LearningPreprint
Eckhoff, M., & Reiher, M. (2023) · arXiv (Cornell University) · doi:10.3929/ethz-b-000658265 · Cited by 1 · see citing works
Self-citationLifelong Machine Learning PotentialsPreprint
Eckhoff, M., & Reiher, M. (2023) · arXiv (Cornell University) · doi:10.3929/ethz-b-000618133
Self-citationPhonon dispersion filter: A physics-inspired feature selection for machine learning potentials
Xu, T., Xue, Y., Park, H. S., & Jiang, J.-W. (2025) · Journal of Applied Physics · doi:10.1063/5.0253209
Accelerated discovery of stable spinels for energy applications using dense neural network approach
Bhaduri, R., Manasa, S., Karthik, M., & Sakthivel, S. (2026) · International Journal of Modern Physics B · doi:10.1142/s0217979226501249
Peng, T., Ma, M., Liu, S., He, J., Wang, Y., Yang, Y., Lu, Y., Luo, Y., & Sun, W. (2026) · Small · doi:10.1002/smll.73936
Lausch, K. N., Haouari, R. E., Schienbein, P., & Behler, J. (2026) · Angewandte Chemie · doi:10.1002/ange.3712910
Self-citationLausch, K. N., Haouari, R. E., Schienbein, P., & Behler, J. (2026) · Angewandte Chemie International Edition · doi:10.1002/anie.3712910
Self-citation
- Authors
- Eckhoff, M., Lausch, K. N., Blöchl, P. E., & Behler, J.
- Affiliations
- University of Göttingen (DE)
- Clausthal University of Technology (DE)
- Corresponding author
- Eckhoff, Marco
- Venue
- The Journal of Chemical Physics
- Publisher
- AIP Publishing
- Published
- 2020-10-23
- Volume
- 153
- Issue
- 16
- Pages
- 164107-164107
- ISSN
- 0021-9606 (ISSN-L)
- 1089-7690
- OpenAlex
- W3038488640
- Cited by
- 45
- References
- 77
- Citations by year
- 2026: 5 · 2025: 10 · 2024: 6 · 2023: 7 · 2022: 8 · 2021: 8 · 2020: 1
- FWCI
- 2.33
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- The Journal of Chemical Physics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Deutsche Forschungsgemeinschaft (217133147, 405832858, 329898176)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advancements in Battery Materials
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
- Keywords
- LiMn2O4, neural network potentials, Jahn-Teller distortion, charge ordering transition, hopping conduction, activation energy, electronic structure dynamics, spinel cathode, lithium-ion batteries
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
