AI and the World's Hard Problems · Chemistry & materials · arXiv · 2026-10-22
A Combined Tight Binding with Machine Learning Potential Model for Magnesium Compounds
The authors present DFTB+MACE, a model for magnesium-based systems that combines density functional tight binding with the machine learning interatomic potential MACE, replacing the conventional repulsive pair potential with a many-body MACE potential trained on DFT-DFTB energy and force differences. They apply it to structural relaxation of MgO-CO2 adsorption systems, molecular dynamics of water clusters, and phonon spectra of stable fcc-MgO and metastable bcc-MgO. The model improves accuracy over pair-potential DFTB at only moderate extra cost and provides electronic structures that most machine learning potentials cannot.