Global exploration of the energy landscape of solids on the ab initio level

Predicting which crystalline modifications can be present in a chemical system requires the global exploration of its energy landscape. Due to the large computational effort involved, in the past this search for sufficiently stable minima has been performed employing a variety of empirical potentials and cost functions followed by a local optimization on the ab initio level. However, this entails the risk of overlooking important modifications that are not modeled accurately using empirical potentials. In order to overcome this critical limitation, we develop an approach to employ ab initio energy functions during the global optimization phase of the structure prediction. As an example, we perform a global exploration of the landscape of LiF on the ab initio level and show that the relevant crystalline modifications are found during the search.