Skip to content

Model for exfoliation_energy

  • Description: This is a benchmark to evaluate how accurately an AI model can predict the energy above the exfoliation energy (isolating a monolayer from a layered structure) 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 accuracy.


Reference(s): https://doi.org/10.1103/PhysRevMaterials.2.083801, https://www.nature.com/articles/s41524-021-00650-1, https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://github.com/YKQ98/Matformer, https://hackingmaterials.lbl.gov/matminer/, https://github.com/aimat-lab/gcnn_keras, 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_3d45.7621kgcnn81209-26-2023CSV, JSON, run.sh, Info
kgcnn_schnetdft_3d48.3027kgcnn81209-26-2023CSV, JSON, run.sh, Info
kgcnn_coGNdft_3d47.6979kgcnn81205-06-2023CSV, JSON, run.sh, Info
matminer_lgbmdft_3d49.5104Matminer81201-14-2023CSV, JSON, run.sh, Info
alignn_modeldft_3d52.7033ALIGNN81201-14-2023CSV, JSON, run.sh, Info
kgcnn_megnetdft_3d68.2435kgcnn81205-06-2023CSV, JSON, run.sh, Info
cfid_chemdft_3d63.769JARVIS81201-14-2023CSV, JSON, run.sh, Info
matminer_rfdft_3d42.7554UofT81205-22-2023CSV, JSON, run.sh, Info
cfiddft_3d62.1169JARVIS81201-14-2023CSV, JSON, run.sh, Info
matminer_xgboostdft_3d40.887UofT81205-22-2023CSV, JSON, run.sh, Info
matformerdft_3d51.661JARVIS81201-14-2023CSV, JSON, run.sh, Info
kgcnn_dimenetPPdft_3d46.1517kgcnn81205-06-2023CSV, JSON, run.sh, Info
cgcnn_modeldft_3d52.7033CGCNN81201-14-2023CSV, JSON, run.sh, Info
kgcnn_coNGNdft_3d46.272kgcnn81205-06-2023CSV, JSON, run.sh, Info