DFT datasets for training machine-learning potential to model Cl-doped lithium borosilicate glasses using DeePMD

Li diffusion in oxygen-chlorine mixed anion borosilicate glasses using

a machine-learning simulation

Shingo Urata, Noriyoshi Kayaba

DFT_Data_for_Cl-doped_LBSCl_glass.zip inlucudes atom configurations, energies, forces, box size, atom types, atom kinds, and virial in coord.raw, energy.raw, force.raw, type.raw, type_map.raw, and virial.raw, respectively. 

All DFT data were evaluated using PBE with a cutoff energy of 600 eV by VASP.

The other detasets are available from https://doi.org/10.5281/zenodo.10577559

LBSCl_DMD_model.pb is force field developed using DeePMD-kit.

LBSCl_DMD_model_c.pb.zip is the compressed version of LBSCl_DMD_model.pb.

基于机器学习模拟的氧氯混合阴离子硼硅酸盐玻璃中的锂扩散研究

浦田真吾（Shingo Urata）、萱场纪德（Noriyoshi Kayaba）

文件DFT_Data_for_Cl-doped_LBSCl_glass.zip 包含原子构型、能量、作用力、模拟盒子尺寸、原子类型、原子种类以及维里张量，上述数据分别存储于coord.raw、energy.raw、force.raw、type.raw、type_map.raw与virial.raw文件中。

所有密度泛函理论（Density Functional Theory, DFT）数据均由VASP软件采用PBE泛函、600 eV截断能计算得到。

其余数据集可通过链接 https://doi.org/10.5281/zenodo.10577559 获取。

LBSCl_DMD_model.pb 为基于DeePMD-kit开发的原子力场文件。

LBSCl_DMD_model_c.pb.zip 为LBSCl_DMD_model.pb 的压缩打包版本。