Model for dfpt_piezo_max_dielectric¶
- Description: This is a benchmark to evaluate how accurately an AI model can predict the maximum piezoelectric coefficient 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/10.48550/arXiv.2305.11842, https://github.com/aimat-lab/gcnn_keras, https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.120.145301, 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
Model benchmarks
| Model name | Dataset | MAE | Team name | Dataset size | Date submitted | Notes |
|---|---|---|---|---|---|---|
| kgcnn_cgcnn | dft_3d | 30.9607 | kgcnn | 4704 | 09-26-2023 | CSV, JSON, run.sh, Info |
| kgcnn_coNGN | dft_3d | 25.5553 | kgcnn | 4704 | 05-06-2023 | CSV, JSON, run.sh, Info |
| alignn_model | dft_3d | 28.1514 | ALIGNN | 4704 | 01-14-2023 | CSV, JSON, run.sh, Info |
| matminer_xgboost | dft_3d | 36.6913 | UofT | 4704 | 05-22-2023 | CSV, JSON, run.sh, Info |
| kgcnn_megnet | dft_3d | 30.1911 | kgcnn | 4704 | 05-06-2023 | CSV, JSON, run.sh, Info |
| cgcnn_model | dft_3d | 32.5589 | CGCNN | 4704 | 01-14-2023 | CSV, JSON, run.sh, Info |
| matminer_rf | dft_3d | 36.7249 | UofT | 4704 | 05-22-2023 | CSV, JSON, run.sh, Info |
| kgcnn_coGN | dft_3d | 30.2923 | kgcnn | 4704 | 05-06-2023 | CSV, JSON, run.sh, Info |
| kgcnn_dimenetPP | dft_3d | 30.3358 | kgcnn | 4704 | 05-06-2023 | CSV, JSON, run.sh, Info |
| kgcnn_schnet | dft_3d | 26.5276 | kgcnn | 4704 | 09-26-2023 | CSV, JSON, run.sh, Info |