Predicts the DFT formation energy per atom from the JARVIS-DFT optB88vdW dataset.
NEMAD Tc bias correction, ALIGNN formation energy ranking, and ±0.25 eV/atom uncertainty propagation for all 6 GGen Heusler anchors.
50+ pretrained graph neural network models for predicting materials properties from a CIF file. Covers energetics, band gaps, mechanical properties, thermoelectrics, superconductivity, catalysis, MOFs, and more.