Machine-Learning Adaptivity, DFT-Level Accuracy, and Semi-Empirical Quantum-Chemistry Speed with Neural-Network Extended Tight-Binding

Le résumé fourni par la source

Fast, general, and interpretable quantum accuracy remains challenging. We introduce Neural‑Network Extended Tight‑Binding (NN‑xTB), a Hamiltonian‑preserving scheme that augments the explicit GFN2‑xTB operator with small, bounded, environment‑dependent shifts to a compact set of physically interpretable parameters predicted by an E(3)‑equivariant encoder. NN‑xTB confines learning to atom/shell local parameters and to a few global scalings, enhancing local chemical adaptivity while preserving analytic long‑range limits, native charge and spin treatment, and self‑consistency, and ensuring that all observables are derived from a single adapted electronic state. Across complementary benchmarks, NN‑xTB attains DFT‑like accuracy at near‑xTB cost. On GMTKN55 it achieves a WTMAD‑2 of 5.6 kcal/mol (versus 25.0 kcal/mol for GFN2‑xTB and 9.3 kcal/mol for g‑xTB). Relative to strong equivariant Machine Learned Interatomic Potentials (MLIPs), NN‑xTB yields the lowest force MAE on 8/10 molecules for the rMD17 dataset and delivers 10–40% RMSE reductions on large subsets of MACEOFF23 and SPICE. Under temperature shift on the 3BPA dataset, errors remain substantially below competing MLIPs up to 1200 K, indicating stronger out‑of‑distribution generalization. On VQM24, the vibrational‑frequency MAE drops from 200.6 (GFN2‑xTB) to 12.7 cm^{-1} (>90% reduction). The neural component adds <20% wall‑time overhead, preserving the throughput that motivates semi‑empirical quantum methods. By adapting the Hamiltonian rather than directly regressing energies or forces, NN-xTB bridges much of the accuracy gap to DFT while retaining interpretability, correct asymptotics, and robustness, offering a practical route to quantum-accurate molecular simulation and modeling at scale.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.