Answers are grounded in this paper and cite their sources.
Accurate prediction of molecular structure, energetics, and reactivity requires quantum chemistry methods that remain too costly for large-scale and high-throughput modeling. Semi-empirical tight-binding approaches are much faster, but their largely element-fixed parameters under-resolve local chemical-environment effects, limiting accuracy. We introduce a neural-network extension of extended-tight binding that learns bounded, environment-dependent shifts to Hamiltonian parameters, increasing chemical adaptivity while preserving self-consistency, charge and spin treatment, and correct long-range behavior. We show that, across benchmarks spanning main-group thermochemistry, noncovalent interactions, molecular forces, vibrational spectra and supramolecular complexes, this approach achieves density functional theory accuracy at near tight-binding cost. On the GMTKN55, the weighted mean absolute error decreases from 25.0 to 3.78 kcal/mol relative to GFN2-xTB; molecular force errors are lowest on eight of ten rMD17 molecules and improve by 10–40% relative to leading machine-learned interatomic potentials; and vibrational frequency errors decrease from 200.6 to 12.7 cm−1, with runtime increasing by less than 20%. This work introduces a paradigm where neural networks predict parameters of a quantum semi-empirical Hamiltonian rather than energies directly, achieving DFT accuracy for relative energies, forces, vibrations, and geometries at semi-empirical cost.
No takes yet. Share an insight, caveat, or question.
Xia et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: