Data and models supporting "qNEP: A highly efficient neuroevolution potential with dynamic charges for large-scale atomistic simulations" doi-10-5281-zenodo-18335947-0 https://doi.org/10.5281/zenodo.18335947 Swedish National Data Service Svensk nationell datatjänst Landing page Data and models supporting "qNEP: A highly efficient neuroevolution potential with dynamic charges for large-scale atomistic simulations" doi-10-5281-zenodo-18335947-0 https://doi.org/10.5281/zenodo.18335947 Fan, Zheyong Tang, Benrui Berger, Esmée Berger, Ethan Fransson, Erik Xu, Ke Yang, Zihang Liu, Zhoulin Song, Zichen Dong, Haikuan Chen, Shunda Li, Lei Wang, Ziliang Zhu, Yizhou Wiktor, Julia Erhart, Paul Swedish National Data Service Svensk nationell datatjänst Landing page This record contains models based on the neuroevolution potential (NEP) approach, charge unaware (conventional) NEP models (nep-*.txt) and charge-aware qNEP models (qnep-*.txt). It also contains the respective reference datasets used for training and validation of these models (references-*.txt). When using any of these models make sure to cite both the original publication for these models as well as, where applicable, the source publications for the reference data (see below). Sources of reference datasets Water models The reference data for the energies, forces, and virials are from Ke Xu, Yongchao Hao, Ting Liang, Penghua Ying, Jianbin Xu, Jianyang Wu, and Zheyong FanThe Journal of Chemical Physics 158, 204114 (2023)Accurate Prediction of Heat Conductivity of Water by a Neuroevolution Potentialdoi: 10.1063/5.0147039 The reference data for the Born effective charges are from Zheyong Fan, Benrui Tang, Esmée Berger, Ethan Berger, Erik Fransson, Ke Xu, Zihan Yan, Zhoulin Liu, Zichen Song, Haikuan Dong, Shunda Chen, Ziliang Wang, Lei Li, Yizhou Zhu, Julia Wiktor, and Paul ErhartqNEP: A highly efficient neuroevolution potential with dynamic charges for large-scale atomistic simulationsdoi: https://doi.org/10.48550/arXiv.2601.19034 The original structures were generated in Linfeng Zhang, Han Wang, Roberto Car, and Weinan EPhysical Review Letters 126, 236001 (2021)Phase Diagram of a Deep Potential Water Modeldoi: 10.1103/PhysRevLett.126.236001 Li7La3Zr2O12 garnet models The reference data are from Zihan Yan and Yizhou ZhuChemistry of Materials 36, 11551 (2024)Impact of lithium nonstoichiometry on ionic diffusion in tetragonal garnet-type Li7La3Zr2O12doi: 10.1021/acs.chemmater.4c02454 BaTiO3 models The reference data are from Zheyong Fan, Benrui Tang, Esmée Berger, Ethan Berger, Erik Fransson, Ke Xu, Zihan Yan, Zhoulin Liu, Zichen Song, Haikuan Dong, Shunda Chen, Ziliang Wang, Lei Li, Yizhou Zhu, Julia Wiktor, and Paul ErhartqNEP: A highly efficient neuroevolution potential with dynamic charges for large-scale atomistic simulationsdoi: https://doi.org/10.48550/arXiv.2601.19034 MgOH models The reference data are from Z. Liu, J. Sha, G.-L. Song, Z. Wang, and Y. ZhangChemical Engineering Journal 516, 163578 (2025)Understanding magnesium dissolution through machine learning molecular dynamicsdoi: 10.1016/j.cej.2025.163578 Access to data through an external actor. Data are freely accessible. Åtkomst till data via extern aktör. Data är fritt tillgängliga. openAccess