Localized Coulomb Descriptors for the Gaussian Approximation Potential

We introduce a novel class of localized atomic environment representation functions, based upon the global Coulomb matrix, which have dimensionality either quadratic or linear in the number of atoms in the local atomic environment. By combining these functions with the Gaussian approximation potential approach, we present LC-GAP, a new system for generating atomic potentials through machine learning (ML). Tests on the QM7, QM7b and GDB9 biomolecular datasets demonstrate that potentials created with LC-GAP can successfully predict atomization energies for molecules larger than those used for training to chemical accuracy, and can (in the case of QM7b) also be used to predict a range of other atomic properties with accuracy in line with the recent literature.