Abstract
The development of first-principles-quality reactive atomistic potentials for organic-inorganic hybrid materials is still a substantial challenge because of the very different physics of the atomic interactions – from covalent via ionic bonding to dispersion – that have to be described in an accurate and balanced way. In this work we use a prototypical metal-organic-framework – MOF-5 – as a benchmark case to investigate the applicability of high-dimensional neural network potentials (HDNNP) to this type of materials. In HDNNPs, which belong to the class of machine learning potentials, the energy is constructed as a sum of environment-dependent atomic energy contributions. We demonstrate that using this approach it is possible to obtain a high-quality potential for the periodic MOF-5 crystal using density functional theory (DFT) reference calculations of small molecular fragments only. The resulting HDNNP, which has a root mean square error (RMSE) of 1.6 meV/atom for the energies of molecular fragments not included in the training set, is able to provide the equilibrium lattice constant of the bulk MOF-5 structure with an error of about 0.1% compared to DFT, and also the negative thermal expansion behaviour is accurately predicted. The total energy RMSE of periodic structures, which are completely absent in the training set, is about 6.5 meV/atom, with errors of energy differences in the order of 2 meV/atom. We show that, in contrast to energy differences, achieving a high accuracy for total energies requires a careful variation of the stoichiometries of the training structures to avoid energy offsets, as atomic energies are no physical observables. The forces, which have an RMSE of about 94 meV/a0 for the molecular fragments and 130 meV/a0 for bulk structures not included in the training set, are insensitive to such offsets. Therefore, forces, which are the relevant properties for molecular dynamics simulations, provide a realistic estimate of the accuracy of atomistic potentials.
Funding Information
  • Deutsche Forschungsgemeinschaft (Be3264/11-2, BE3264/12-1)

This publication has 89 references indexed in Scilit: