Skip to content

Model for bandgap_JVASP_8169_GaN

  • Description: This is a benchmark to evaluate how accurately an ES model can predict the bandgap of GaN (JVASP-8169), experimental results are used as a ground truth for comparison and the mean absolute error (MAE) with respect to the experimental value is used as an accuracy metric


Reference(s): https://www.nature.com/articles/s41524-020-00440-1, https://wiki.fysik.dtu.dk/gpaw/tutorialsexercises/tutorialsexercises.html, https://pubs.acs.org/doi/abs/10.1021/acs.chemmater.9b02166, https://doi.org/10.48550/arXiv.2305.11842, https://aflow.org/, https://materialsproject.org/, https://github.com/usnistgov/ThreeBodyTB.jl/

Model benchmarks

Model name Dataset MAE Team name Dataset size Date submitted Notes
vasp_tbmbjdft_3d0.377JARVIS101-14-2023CSV, JSON, run.sh, Info, JVASP-8169
vasp_pbe_aflowdft_3d1.71AFLOW101-14-2023CSV, JSON, run.sh, Info, JVASP-8169
vasp_pbe_mpdft_3d1.71MP101-14-2023CSV, JSON, run.sh, Info, JVASP-8169
gpaw_pbedft_3d1.3525GPAW101-14-2023CSV, JSON, run.sh, Info, JVASP-8169
gpaw_gllbscdft_3d0.1977GPAW101-14-2023CSV, JSON, run.sh, Info, JVASP-8169
tb3_modelsdft_3d1.1479TB3103-29-2023CSV, JSON, run.sh, Info, JVASP-8169
gpaw_ldadft_3d1.3287GPAW101-14-2023CSV, JSON, run.sh, Info, JVASP-8169
vasp_optb88vdwdft_3d1.494JARVIS101-14-2023CSV, JSON, run.sh, Info, JVASP-8169