Published May 17, 2022 | Version v1
Dataset Open

Dataset for deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation

Creators

Description

Dataset files of atomic structures and Hamiltonian matrices of graphene, MoS2, bilayer graphene and bilayer bismuthene.

Please note that the DFT results in this dataset were calculated using OpenMX. This means that if you want to use a DeepH model trained on this dataset to calculate properties, you need to use the overlap calculated using OpenMX. The orbital information required for overlap calculations can be found in the paper.

Files

graphene_dataset.zip

Files (25.8 GB)

Name Size Download all
md5:348c21faacdc62433dd8f01994824916
1.8 GB Preview Download
md5:a5dd04b1141eb9f3763d06d100c6bf48
3.8 GB Preview Download
md5:eb70f5e7ed2b10df5eba1ca4021c2f99
18.0 GB Preview Download
md5:402ad6daf0522ca7355eae069e116752
2.2 GB Preview Download