Model for ALIGNN-FF energy¶
- Description: This is an AI benchmark to evaluate how accurately a machine learning force-field (MLFF) can predict the total energy using the relaxation trajectories (energy and forces of intermediate steps) of the JARVIS-DFT (dft_3d) dataset, calculated with the OPTB88vdw density functional. The dataset contains different types of chemical formula and atomic structures. Here we use mean absolute error (MAE) to compare MLFFs with respect to DFT (OPT) accuracy.
Reference(s): https://pubs.rsc.org/en/content/articlehtml/2023/dd/d2dd00096b, https://doi.org/10.1039/D2DD00096B
Model benchmarks
Model name | Dataset | Accuracy | Team name | Dataset size | Date submitted | Notes |
---|---|---|---|---|---|---|
alignnff_pretrained_wt0.1 | alignn_ff_db | 0.0342 | JARVIS | 307111 | 01-14-2023 | CSV, JSON, run.sh, Info |
alignnff_pretrained_wt0.5 | alignn_ff_db | 0.0443 | JARVIS | 307111 | 01-14-2023 | CSV, JSON, run.sh, Info |
alignnff_pretrained_wt1 | alignn_ff_db | 0.0509 | JARVIS | 307111 | 01-14-2023 | CSV, JSON, run.sh, Info |
alignnff_pretrained_wt10 | alignn_ff_db | 0.0973 | JARVIS | 307111 | 01-14-2023 | CSV, JSON, run.sh, Info |