GPUMDkit: A User-Friendly Toolkit for GPUMD and NEP

Abstract

Machine-learned interatomic potentials have revolutionized molecular dynamics simulations by providing quantum–mechanical accuracy at empirical–potential speeds. The graphics processing unit molecular dynamics (GPUMD) package, featuring the highly efficient neuroevolution potential (NEP) framework, has emerged as a powerful tool in this domain. However, the complexity of force field development, active learning, and trajectory post-processing often requires extensive manual scripting, imposing a steep learning curve on new users. To address this, we present GPUMDkit, a comprehensive and user-friendly toolkit that streamlines the entire simulation workflow for GPUMD and NEP. GPUMDkit integrates a suite of essential functionalities, including format conversion, structure sampling, property calculation, and data visualization, accessible through both interactive and command-line interfaces. Its modular, extensible architecture ensures accessibility for users of all experience levels while allowing seamless integration of new features. By automating complex tasks and enhancing productivity, GPUMDkit substantially lowers the barrier to using GPUMD and NEP programs. This article describes the program architecture and demonstrates its capabilities through practical applications.

References

[1] Z. Qi, X. Sun, Z. Sun, et al., “Interfacial Optimization for Aln/Diamond Heterostructures via Machine Learning Potential Molecular Dynamics Investigation of the Mechanical Properties,” ACS Applied Materials and Interfaces 16, no. 21 (2024): 27998–28007, https://doi.org/10.1021/acsami.4c06055.

[2] Y. Liu, H. Meng, Z. Zhu, H. Yu, L. Zhuang, and Y. Chu, “Predicting Mechanical and Thermal Properties of High-Entropy Ceramics via Transferable Machine-Learning-Potential-Based Molecular Dynamics,” Advanced Functional Materials 35, no. 16 (2025): 2418802, https://doi.org/10.1002/adfm.202418802.

[3] K. Xu, Y. Hao, T. Liang, et al., “Accurate Prediction of Heat Conductivity of Water by a Neuroevolution Potential,” Journal of Chemical Physics 158, no. 20 (2023): 204114, https://doi.org/10.1063/5.0147039.

[4] L. Yu, K. Dong, Q. Yang, et al., “Dynamic Mesophase Transition Induces Anomalous Suppressed and Anisotropic Phonon Thermal Transport,” npj Computational Materials 10, no. 1 (2024): 280, https://doi.org/10.1038/s41524-024-01442-z.

[5] P. Ying, W. Zhou, L. Svensson, et al., “Highly Efficient Path-Integral Molecular Dynamics Simulations With GPUMD Using Neuroevolution Potentials: Case Studies on Thermal Properties of Materials,” Journal of Chemical Physics 162, no. 6 (2025): 064109, https://doi.org/10.1063/5.0241006.

[6] E. Fransson, J. Wiktor, and P. Erhart, “Phase Transitions in Inorganic Halide Perovskites From Machine-Learned Potentials,” Journal of Physical Chemistry C 127, no. 28 (2023): 13773–13781, https://doi.org/10.1021/acs.jpcc.3c01542.

[7] Z. Yan and Y. Zhu, “Impact of Lithium Nonstoichiometry on Ionic Diffusion in Tetragonal Garnet-Type Li₇La₃Zr₂O₁₂,” Chemistry of Materials 36, no. 23 (2024): 11551–11557, https://doi.org/10.1021/acs.chemmater.4c02454.

[8] K. Li, B. Liu, J. Zhou, and Z. Sun, “Revealing the Crystallization Dynamics of Sb-Te Phase Change Materials by Large-Scale Simulations,” Journal of Materials Chemistry C 12, no. 11 (2024): 3897–3906, https://doi.org/10.1039/d3tc04586b.

[9] L. Zeng, J. Peng, J. Zhang, et al., “Molecular Dynamics Simulations of Electrochemical Interfaces,” Journal of Chemical Physics 159, no. 9 (2023): 091001, https://doi.org/10.1063/5.0160729.

[10] R. Zhao, S. Wang, Z. Kong, et al., “Development of a Neuroevolution Machine Learning Potential of Pd–Cu–Ni–P Alloys,” Materials and Design 231 (2023): 112012, https://doi.org/10.1016/j.matdes.2023.112012.

[11] Z. Zhao, M. Yi, W. Guo, and Z. Zhang, “General-Purpose Neural Network Potential for Ti–Al–Nb Alloys towards Large-Scale Molecular Dynamics With Ab Initio Accuracy,” Physical Review B: Condensed Matter 110, no. 18 (2024): 184115, https://doi.org/10.1103/physrevb.110.184115.

[12] J. Behler and M. Parrinello, “Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces,” Physical Review Letters 98, no. 14 (2007): 146401, https://doi.org/10.1103/physrevlett.98.146401.

[13] A. P. Bartók, M. C. Payne, R. Kondor, and G. Csányi, “Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, Without the Electrons,” Physical Review Letters 104, no. 13 (2010): 136403, https://doi.org/10.1103/physrevlett.104.136403.

[14] I. S. Novikov, K. Gubaev, E. V. Podryabinkin, and A. V. Shapeev, “The Mlip Package: Moment Tensor Potentials With mpi and Active Learning,” Machine Learning: Science and Technology 2 (2020): 025002, https://doi.org/10.1088/2632-2153/abc9fe.

[15] L. Zhang, J. Han, H. Wang, R. Car, and W. E , “Deep Potential Molecular Dynamics: A Scalable Model With the Accuracy of Quantum Mechanics,” Physical Review Letters 120, no. 14 (2018): 143001, https://doi.org/10.1103/physrevlett.120.143001.

[16] S. Batzner, A. Musaelian, L. Sun, et al., “E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials,” Nature Communications 13, no. 1 (2022): 2453, https://doi.org/10.1038/s41467-022-29939-5.

[17] I. Batatia, D. P. Kovacs, G. N. C. Simm, C. Ortner, and G. Csanyi, “MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields,” in Advances in Neural Information Processing Systems, ed. A. H. Oh, A. Agarwal, D. Belgrave, and K. Cho (2022)

[18] I. Batatia, S. Batzner, D. P. Kovács, et al., “The Design Space of e (3)-Equivariant Atom-Centred Interatomic Potentials,” Nature Machine Intelligence 7, no. 1 (2025): 56–67, https://doi.org/10.1038/s42256-024-00956-x.

[19] Z. Fan, Z. Zeng, C. Zhang, et al., “Neuroevolution Machine Learning Potentials: Combining High Accuracy and Low Cost in Atomistic Simulations and Application to Heat Transport,” Physical Review B: Condensed Matter 104, no. 10 (2021): 104309, https://doi.org/10.1103/physrevb.104.104309.

[20] T. Schaul, T. Glasmachers, and J. Schmidhuber, “High Dimensions and Heavy Tails for Natural Evolution Strategies,” in Booktitle Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, (2011), 845–852, https://doi.org/10.1145/2001576.2001692.

[21] H. Dong, Y. Shi, P. Ying, et al., “Molecular Dynamics Simulations of Heat Transport Using Machine-Learned Potentials: A Mini-Review and Tutorial on GPUMD With Neuroevolution Potentials,” Journal of Applied Physics 135, no. 16 (2024): 161101, https://doi.org/10.1063/5.0200833.

[22] J. Liu, J. Byggmästar, Z. Fan, P. Qian, and Y. Su, “Large-scale Machine-Learning Molecular Dynamics Simulation of Primary Radiation Damage in Tungsten,” Physical Review B: Condensed Matter 108, no. 5 (2023): 054312, https://doi.org/10.1103/physrevb.108.054312.

[23] T. Liang, K. Xu, E. Lindgren, et al., “NEP89: Universal Neuroevolution Potential for Inorganic and Organic Materials Across 89 Elements,” arXiv (2025), https://doi.org/10.48550/arXiv.2504.21286.

[24] K. Xu, H. Bu, S. Pan, et al., “GPUMD 4.0: A High-Performance Molecular Dynamics Package for Versatile Materials Simulations With Machine-Learned Potentials,” Materials Genome Engineering Advances 3, no. 3 (2025): e70028, https://doi.org/10.1002/mgea.70028.

[25] C. Chen, Y. Li, R. Zhao, et al., “NepTrain and NepTrainKit: Automated Active Learning and Visualization Toolkit for Neuroevolution Potentials,” Computer Physics Communications 317 (2025): 109859, https://doi.org/10.1016/j.cpc.2025.109859.

[26] E. Lindgren, M. Rahm, E. Fransson, et al., “Calorine: A python Package for Constructing and Sampling Neuroevolution Potential Models,” Journal of Open Source Software 9, no. 95 (2024): 6264, https://doi.org/10.21105/joss.06264.

[27] T. Liang, W. Jiang, K. Xu, et al., “PYSED: A Tool for Extracting Kinetic-Energy-Weighted Phonon Dispersion and Lifetime From Molecular Dynamics Simulations,” Journal of Applied Physics 138, no. 7 (2025): 075101, https://doi.org/10.1063/5.0278798.

[28] Z. Fan, W. Chen, V. Vierimaa, and A. Harju, “Efficient Molecular Dynamics Simulations With Many-Body Potentials on Graphics Processing Units,” Computer Physics Communications 218 (2017): 10–16, https://doi.org/10.1016/j.cpc.2017.05.003.

[29] J. E. Lennard-Jones, “Cohesion,” Proceedings of the Physical Society 43, no. 5 (1931): 461–482, https://doi.org/10.1088/0959-5309/43/5/301.

[30] M. S. Daw and M. I. Baskes, “Embedded-atom Method: Derivation and Application to Impurities, Surfaces, and Other Defects in Metals,” Physical Review B: Condensed Matter 29, no. 12 (1984): 6443–6453, https://doi.org/10.1103/physrevb.29.6443.

[31] J. Tersoff, “Empirical Interatomic Potential for Carbon, With Applications to Amorphous Carbon,” Physical Review Letters 61, no. 25 (1988): 2879–2882, https://doi.org/10.1103/physrevlett.61.2879.

[32] J. Brorsson, A. Hashemi, Z. Fan, et al., “Efficient Calculation of the Lattice Thermal Conductivity by Atomistic Simulations With ab Initio Accuracy,” Advanced Theory and Simulations 5, no. 2 (2022): 2100217, https://doi.org/10.1002/adts.202100217.

[33] J. Zeng, D. Zhang, D. Lu, et al., “DeePMD-kit v2: A Software Package for Deep Potential Models,” Journal of Chemical Physics 159, no. 5 (2023): 054801, https://doi.org/10.1063/5.0155600.

[34] K. Song, R. Zhao, J. Liu, et al., “General-Purpose Machine-Learned Potential for 16 Elemental Metals and Their Alloys,” Nature Communications 15, no. 1 (2024): 10208, https://doi.org/10.1038/s41467-024-54554-x.

[35] H. Bu, W. Jiang, P. Ying, T. Liang, Z. Fan, and W. Ouyang, “Modular Hybrid Machine Learning and Physics-Based Potentials for Scalable modeling of van der waals heterostructures,” Journal of the Mechanics and Physics of Solids 210 (2026): 106540, https://doi.org/10.1016/j.jmps.2026.106540.

[36] W. Jiang, T. Liang, H. Bu, J. Xu, and W. Ouyang, “Moiré-Driven Interfacial Thermal Transport in Twisted Transition Metal Dichalcogenides,” ACS Nano 19, no. 17 (2025): 16287–16296, https://doi.org/10.1021/acsnano.4c12148.

[37] P. Ying and Z. Fan, “Combining the D3 Dispersion Correction With the Neuroevolution Machine-Learned Potential,” Journal of Physics: Condensed Matter 36, no. 12 (2024): 125901, https://doi.org/10.1088/1361-648x/ad1278.

[38] Z. Fan, “Improving the Accuracy of the Neuroevolution Machine Learning Potential for Multi-Component Systems,” Journal of Physics: Condensed Matter 34, no. 12 (2022): 125902, https://doi.org/10.1088/1361-648x/ac462b.

[39] Z. Fan, Y. Wang, P. Ying, et al., “GPUMD: A Package for Constructing Accurate Machine-Learned Potentials and Performing Highly Efficient Atomistic Simulations,” Journal of Chemical Physics 157, no. 11 (2022): 114801, https://doi.org/10.1063/5.0106617.

[40] R. Drautz, “Atomic Cluster Expansion for Accurate and Transferable Interatomic Potentials,” Physical Review B: Condensed Matter 99, no. 1 (2019): 014104, https://doi.org/10.1103/physrevb.99.014104.

[41] A. H. Larsen, J. J. Mortensen, J. Blomqvist, et al., “The Atomic Simulation Environment—A Python Library for Working With Atoms,” Journal of Physics: Condensed Matter 29, no. 27 (2017): 273002, https://doi.org/10.1088/1361-648X/aa680e.

[42] J. Zeng, X. Peng, Y.-B. Zhuang, et al., “Dpdata: A Scalable python Toolkit for Atomistic Machine Learning Data Sets,” Journal of Chemical Information and Modeling 65, no. 21 (2025): 11497–11504, https://doi.org/10.1021/acs.jcim.5c01767.

[43] S. P. Ong, W. D. Richards, A. Jain, et al., “Python Materials Genomics (Pymatgen): A Robust, Open-Source Python Library for Materials Analysis,” Computational Materials Science 68 (2013): 314–319, https://doi.org/10.1016/j.commatsci.2012.10.028.

[44] V. Wang, N. Xu, J.-C. Liu, G. Tang, and W.-T. Geng, “VASPKIT: A User-Friendly Interface Facilitating High-Throughput Computing and Analysis Using vasp Code,” Computer Physics Communications 267 (2021): 108033, https://doi.org/10.1016/j.cpc.2021.108033.

[45] W.-T. Geng, Y.-C. Liu, N. Xu, G. Tang, Y. Kawazoe, and V. Wang, “Empowering Materials Science With VASPKIT: A Toolkit for Enhanced Simulation and Analysis,” Nature Protocols 20, no. 11 (2025): 3143–3169, https://doi.org/10.1038/s41596-025-01160-w.

[46] W. Yi, G. Tang, X. Chen, B. Yang, and X. Liu, “Qvasp: A Flexible Toolkit for vasp Users in Materials Simulations,” Computer Physics Communications 257 (2020): 107535, https://doi.org/10.1016/j.cpc.2020.107535.

[47] G. Kresse and J. Hafner, “Ab Initio Molecular-Dynamics Simulation of the Liquid-Metal–Amorphous-Semiconductor Transition in Germanium,” Physical Review B: Condensed Matter 49, no. 20 (1994): 14251–14269, https://doi.org/10.1103/physrevb.49.14251.

[48] G. Kresse and J. Furthmüller, “Efficient Iterative Schemes for Ab Initio Total-Energy Calculations Using a Plane-Wave Basis Set,” Physical Review B: Condensed Matter 54, no. 16 (1996): 11169–11186, https://doi.org/10.1103/physrevb.54.11169.

[49] T. D. Kühne, M. Iannuzzi, M. Del Ben, et al., “CP2K: An Electronic Structure and Molecular Dynamics Software Package-Quickstep: Efficient and Accurate Electronic Structure Calculations,” Journal of Chemical Physics 152, no. 19 (2020): 194103, https://doi.org/10.1063/5.0007045.

[50] W. Zhou, D. Zheng, Q. Liu, et al., “ABACUS: An Electronic Structure Analysis Package for the AI Era,” arXiv (2025), https://doi.org/10.48550/arXiv.2501.08697.

[51] A. P. Thompson, H. M. Aktulga, R. Berger, et al., “Lammps-a Flexible Simulation Tool for Particle-Based Materials Modeling at the Atomic, Meso, and Continuum Scales,” Computer Physics Communications 271 (2022): 108171, https://doi.org/10.1016/j.cpc.2021.108171.

[52] F. Han, Y. Zhu, X. He, Y. Mo, and C. Wang, “Electrochemical Stability of Li₁₀GeP₂S₁₂ and Li₇La₃Zr₂O₁₂ Solid Electrolytes,” Advanced Energy Materials 6 (2016): 1501590, https://doi.org/10.1002/aenm.201501590.

[53] Z. Yan, Z. Fan, and Y. Zhu, “Improving Robustness and Training Efficiency of Machine-Learned Potentials by Incorporating Short-Range Empirical Potentials,” Journal of Chemical Information and Modeling 66, no. 3 (2026): 1406–1413, https://doi.org/10.1021/acs.jcim.5c02335.

[54] Y. Chen, E. Rangasamy, C. R. dela Cruz, C. Liang, and K. An, “A Study of Suppressed Formation of Low-Conductivity Phases in Doped Li₇La₃Zr₂O₁₂ Garnets by In Situ Neutron Diffraction,” Journal of Materials Chemistry A 3, no. 45 (2015): 22868–22876, https://doi.org/10.1039/c5ta04902d.

[55] S. Wang, Y. Liu, and Y. Mo, “Frustration in Super-Ionic Conductors Unraveled by the Density of Atomistic States,” Angewandte Chemie International Edition 62, no. 15 (2023): e202215544, https://doi.org/10.1002/ange.202215544.

[56] M. E. Lines and A. M. Glass, noop Principles and Applications of Ferroelectrics and Related Materials (publisher Clarendon Press, 1977), https://doi.org/10.1093/acprof:oso/9780198507789.001.0001.

[57] D. Damjanovic, P. Muralt, and N. Setter, “Ferroelectric Sensors, Noop,” IEEE Sensors Journal 1, no. 3 (2001): 191–206, https://doi.org/10.1109/jsen.2001.954832.

[58] V. Garcia and M. Bibes, “Ferroelectric Tunnel Junctions for Information Storage and Processing,” Nature Communications 5, no. 1 (2014): 4289, https://doi.org/10.1038/ncomms5289.

[59] F. Li, B. Wang, X. Gao, D. Damjanovic, L.-Q. Chen, and S. Zhang, “Ferroelectric Materials Toward Next-Generation Electromechanical Technologies,” Science 389, no. 6755 (2025): eadn4926, https://doi.org/10.1126/science.adn4926.

[60] G. Shirane and S. Hoshino, “On the Phase Transition in Lead Titanate,” Journal of the Physical Society of Japan 6, no. 4 (1951): 265–270, https://doi.org/10.1143/jpsj.6.265.

[61] R. Xu, J. Huang, E. S. Barnard, et al., “Strain-Induced Room-Temperature Ferroelectricity in SrTiO₃ Membranes,” Nature Communications 11, no. 1 (2020): 3141, https://doi.org/10.1038/s41467-020-16912-3.

[62] X. Li, T. Qiu, J. Zhang, et al., “Terahertz Field–Induced Ferroelectricity in Quantum Paraelectric SrTiO₃,” Science 364, no. 6445 (2019): 1079–1082, https://doi.org/10.1126/science.aaw4913.

[63] Y. Tang, Y. Zhu, X. Ma, et al., “Observation of a Periodic Array of Flux-Closure Quadrants in Strained Ferroelectric PbTiO₃ Films,” Science 348, no. 6234 (2015): 547–551, https://doi.org/10.1126/science.1259869.

[64] A. K. Yadav, C. T. Nelson, S. L. Hsu, et al., “Observation of Polar Vortices in Oxide Superlattices,” Nature 530, no. 7589 (2016): 198–201, https://doi.org/10.1038/nature16463.

[65] S. Das, Y. L. Tang, Z. Hong, et al., “Observation of Room-Temperature Polar Skyrmions,” Nature 568, no. 7752 (2019): 368–372, https://doi.org/10.1038/s41586-019-1092-8.

[66] J. Yang and S. Liu, “Topological Phase Transitions in Perovskite Superlattices Driven by Temperature, Electric Field, and Doping,” Physical Review B: Condensed Matter 110, no. 21 (2024): 214112, https://doi.org/10.1103/physrevb.110.214112.

[67] J. Wu, J. Yang, L. Ma, L. Zhang, and S. Liu, “Modular Development of Deep Potential for Complex Solid Solutions,” Physical Review B: Condensed Matter 107, no. 14 (2023): 144102, https://doi.org/10.1103/physrevb.107.144102.

[68] Y. Qi, S. Liu, I. Grinberg, and A. M. Rappe, “Atomistic Description for Temperature-Driven Phase Transitions in BaTiO₃,” Physical Review B: Condensed Matter 94, no. 13 (2016): 134308, https://doi.org/10.1103/physrevb.94.134308.

[69] H. Wu, R. He, Y. Lu, and Z. Zhong, “Large-scale Atomistic Simulation of Quantum Effects in SrTiO₃ From First Principles,” Physical Review B: Condensed Matter 106, no. 22 (2022): 224102, https://doi.org/10.1103/physrevb.106.224102.

[70] S. Liu and R. E. Cohen, “Origin of Stationary Domain Wall Enhanced Ferroelectric Susceptibility,” Physical Review B: Condensed Matter 95, no. 9 (2017): 094102, https://doi.org/10.1103/physrevb.95.094102.

[71] D. J. Evans, “Homogeneous NEMD Algorithm for Thermal Conductivity—Application of Non-Canonical Linear Response Theory,” Physics Letters A 91, no. 9 (1982): 457–460, https://doi.org/10.1016/0375-9601(82)90748-4.

[72] Z. Fan, H. Dong, A. Harju, and T. Ala-Nissila, “Homogeneous Nonequilibrium Molecular Dynamics Method for Heat Transport and Spectral Decomposition With Many-Body Potentials,” Physical Review B: Condensed Matter 99, no. 6 (2019): 064308, https://doi.org/10.1103/physrevb.99.064308.

Rights & permissions

2026 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.