Model for void_fraction¶
- Description: This is a benchmark to evaluate how accurately an AI model can predict the void fraction using the hMOF dataset. The dataset contains different types of hypothetical metal organic frameworks. Here we use mean absolute error (MAE) to compare models with respect to DFT accuracy. External links: https://pubs.acs.org/doi/10.1021/acs.jced.2c00583
Reference(s): https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://www.nature.com/articles/s41524-021-00650-1, https://doi.org/10.1021/acs.jced.2c00583
Model benchmarks
| Model name | Dataset | MAE | Team name | Dataset size | Date submitted | Notes |
|---|---|---|---|---|---|---|
| matminer_rf | hmof | 0.0216 | UofT | 137651 | 05-22-2023 | CSV, JSON, run.sh, Info |
| alignn_model | hmof | 0.0174 | ALIGNN | 137651 | 01-14-2023 | CSV, JSON, run.sh, Info |
| matminer_xgboost | hmof | 0.0186 | UofT | 137651 | 05-22-2023 | CSV, JSON, run.sh, Info |