Predicts the superconducting critical temperature Tc.
Deep-read and ML analysis of the Belli-Zurek-Errea 2026 npj Computational Materials paper on bonding descriptors for QNEs in hydride superconductors. Ran Tc, Debye, and DOS predictions on 6 hydride systems (4 SB, 2 AB). ML fails to capture QNE direction; the paper's S_a descriptor fills the gap.
A practical analysis of how AI models like ALIGNN are transforming materials discovery, with a focus on superconductivity research.
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.