Skip to content

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://doi.org/10.1103/PhysRevMaterials.7.044603, https://www.nature.com/articles/s41524-023-01012-9;https://hackingmaterials.lbl.gov/matminer, https://www.nature.com/articles/s41524-021-00650-1, https://github.com/aimat-lab/gcnn_keras

Model benchmarks

Model name Dataset MAE Team name Dataset size Date submitted Notes
kgcnn_schnetqe_tb0.11kgcnn82957409-26-2023CSV, JSON, run.sh, Info
kgcnn_coGNqe_tb0.0474kgcnn82957405-06-2023CSV, JSON, run.sh, Info
alignn_modelqe_tb0.1167ALIGNN82957401-14-2023CSV, JSON, run.sh, Info
matminer_rfqe_tb0.0278UofT82957405-22-2023CSV, JSON, run.sh, Info
matminer_xgboostqe_tb0.0351UofT82957405-22-2023CSV, JSON, run.sh, Info