Training datasets for AIMNet2 machine-learned neural network potential

The datasets contain molecular structures and the properties computed with B97-3c (GGA DFT) or wB97M-def2-TZVPP (range-separated hybrid DFT) methods. Each data file contains about 20M structures. DFT calculation performed with ORCA 5.0.3 software. Properties include energy, forces, atomic charges, and molecular dipole and quadrupole moments.

本数据集包含分子结构，以及采用B97-3c（广义梯度近似密度泛函理论（GGA DFT））或wB97M-def2-TZVPP（范围分离杂化密度泛函理论（range-separated hybrid DFT））方法计算得到的分子性质。每个数据文件包含约2000万个分子结构。所有密度泛函理论计算均通过ORCA 5.0.3软件完成。所涵盖的分子性质包括能量、原子受力、原子电荷以及分子偶极矩和四极矩。