Skip to content

Model for Li FF stresses

  • Description: This is an AI benchmark to evaluate how accurately a machine learning force-field (MLFF) can predict the stresses of Li using the relaxation trajectories (energy and forces of intermediate steps) of the mlearn dataset, calculated with the PBE density functional. The dataset contains different types of chemical formula and atomic structures. Here we use multi-mean absolute error (multi-MAE) to compare MLFFs with respect to DFT (PBE) accuracy. External links: https://github.com/materialsvirtuallab/mlearn


Reference(s): https://github.com/usnistgov/chipsff, https://doi.org/10.1021/acs.jpca.9b08723

Model benchmarks

Model nameDataset Accuracy Team name Dataset size Date submitted Notes
mlearn_analysis_Li_macemlearnall_Li0.23755626474658392JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_chgnetmlearnall_Li0.27162847497123155JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_eqV2_31M_omat_mp_salexmlearnall_Li0.1904206900846113JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_eqV2_31M_omatmlearnall_Li0.19740889417628812JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_eqV2_153M_omatmlearnall_Li0.20645194169057218JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_eqV2_86M_omatmlearnall_Li0.2007639140113057JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_mace-alexandriamlearnall_Li0.6710063720243422JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_matgl-directmlearnall_Li0.3803296603329105JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_orb-v2mlearnall_Li0.23257791508971778JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_eqV2_86M_omat_mp_salexmlearnall_Li0.206764221132883JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_matglmlearnall_Li0.45284366654352015JARVIS27011-22-2024CSV, JSON, run.sh, Info
mlearn_analysis_Li_sevennetmlearnall_Li0.22860574442191778JARVIS27011-22-2024CSV, JSON, run.sh, Info