Skip to content

Model for mbj_bandgap

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the bandgap (at the meta-GGA TBmBJ functional level of theory) using the JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures. Here we use mean absolute error (MAE) to compare models with respect to DFT (meta-GGA TBmBJ) accuracy.


Reference(s): https://doi.org/10.1103/PhysRevMaterials.2.083801, https://github.com/divelab/AIRS/tree/main/OpenMat/PotNet, https://www.nature.com/articles/s41524-021-00650-1, https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://hackingmaterials.lbl.gov/matminer/, https://github.com/aimat-lab/gcnn_keras, https://arxiv.org/abs/2405.03680, https://doi.org/10.48550/arXiv.2305.11842, https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.120.145301, https://www.nature.com/articles/s41524-020-00440-1

Model benchmarks

Model nameDataset MAE Team name Dataset size Date submitted Notes
kgcnn_cgcnndft_3d0.3261kgcnn1816709-26-2023CSV, JSON, run.sh, Info
kgcnn_schnetdft_3d0.3289kgcnn1816709-26-2023CSV, JSON, run.sh, Info
kgcnn_coGNdft_3d0.264kgcnn1816705-06-2023CSV, JSON, run.sh, Info
matminer_lgbmdft_3d0.3909Matminer1816701-14-2023CSV, JSON, run.sh, Info
atomgpt_modeldft_3d0.3188AtomGPT1816705-23-2024CSV, JSON, run.sh, Info
alignn_modeldft_3d0.3104ALIGNN1816701-14-2023CSV, JSON, run.sh, Info
kgcnn_megnetdft_3d0.297kgcnn1816705-06-2023CSV, JSON, run.sh, Info
cfid_chemdft_3d0.6206JARVIS1816701-14-2023CSV, JSON, run.sh, Info
matminer_rfdft_3d0.3516UofT1816705-22-2023CSV, JSON, run.sh, Info
cfiddft_3d0.5313JARVIS1816701-14-2023CSV, JSON, run.sh, Info
matminer_xgboostdft_3d0.3392UofT1816705-22-2023CSV, JSON, run.sh, Info
kgcnn_dimenetPPdft_3d0.4764kgcnn1816705-06-2023CSV, JSON, run.sh, Info
cgcnn_modeldft_3d0.4067CGCNN1816701-14-2023CSV, JSON, run.sh, Info
kgcnn_coNGNdft_3d0.2719kgcnn1816705-06-2023CSV, JSON, run.sh, Info
potnetdft_3d0.2707DIVE@TAMU1816706-02-2023CSV, JSON, run.sh, Info