Skip to content

Model for p-Seebeck

  • Description: This is a benchmark to evaluate how accurately an AI model can classify a material as a thermoeletric based on the p-doped Seebeck Coefficient (computed with DFT and BoltzTrap) from 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://doi.org/10.48550/arXiv.2305.11842, https://www.nature.com/articles/s41524-021-00650-1, https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://www.nature.com/articles/s41524-020-00440-1

Model benchmarks

Model nameDataset ACC Team name Dataset size Date submitted Notes
alignn_modeldft_3d0.9259ALIGNN2321001-14-2023CSV, JSON, run.sh, Info
matminer_rfdft_3d0.9237UofT2321005-22-2023CSV, JSON, run.sh, Info
matminer_xgboostdft_3d0.9332UofT2321005-22-2023CSV, JSON, run.sh, Info