Model for indir_gap¶
- Description: This is a benchmark to evaluate how accurately an AI model can predict the indirect bandgap using the JARVIS Three-Body Tight Binding dataset computed with Quantum Espresso (this data has been used to fit tight binding parameters for the entire periodic table). The dataset contains 65 different elements and their binary combinations. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://journals.aps.org/prmaterials/abstract/10.1103/PhysRevMaterials.7.044603, https://jarvis.nist.gov/jarvisqetb/, https://github.com/usnistgov/tb3py
Reference(s): https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://doi.org/10.1103/PhysRevMaterials.7.044603, https://github.com/aimat-lab/gcnn_keras, https://www.nature.com/articles/s41524-021-00650-1
Model benchmarks
| Model name | Dataset | MAE | Team name | Dataset size | Date submitted | Notes |
|---|---|---|---|---|---|---|
| matminer_rf | qe_tb | 0.0278 | UofT | 829574 | 05-22-2023 | CSV, JSON, run.sh, Info |
| alignn_model | qe_tb | 0.1167 | ALIGNN | 829574 | 01-14-2023 | CSV, JSON, run.sh, Info |
| matminer_xgboost | qe_tb | 0.0351 | UofT | 829574 | 05-22-2023 | CSV, JSON, run.sh, Info |
| kgcnn_coGN | qe_tb | 0.0474 | kgcnn | 829574 | 05-06-2023 | CSV, JSON, run.sh, Info |
| kgcnn_schnet | qe_tb | 0.11 | kgcnn | 829574 | 09-26-2023 | CSV, JSON, run.sh, Info |