Model for mbj_bandgap¶
- Description: This is a benchmark to evaluate how accurately an AI model can classify a material as a semiconductor/insulator vs. metal based on the band gap computed with the TBmBJ meta-GGA density functional using the JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures. Here we use accuracy of classification (ACC) to compare models with respect to DFT accuracy.
Reference(s): https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://www.nature.com/articles/s41524-020-00440-1, https://www.nature.com/articles/s41524-021-00650-1, https://doi.org/10.48550/arXiv.2305.11842
Model benchmarks
| Model name | Dataset | ACC | Team name | Dataset size | Date submitted | Notes |
|---|---|---|---|---|---|---|
| matminer_rf | dft_3d | 0.9328 | UofT | 18167 | 05-22-2023 | CSV, JSON, run.sh, Info |
| alignn_model | dft_3d | 0.9229 | ALIGNN | 18167 | 01-14-2023 | CSV, JSON, run.sh, Info |
| matminer_xgboost | dft_3d | 0.9399 | UofT | 18167 | 05-22-2023 | CSV, JSON, run.sh, Info |