Structure prediction of two-dimensional materials based on neural network-driven evolutionary technique

We present a simple yet effective method for structure prediction of two-dimensional structures. The method is based on a combination of neural networks and evolutionary techniques. It allows finding pristine 2D structures as well as structures grown on a substrate. Conducted tests show, that the method is efficient and the calculations, based only on the information of stoichiometry, can lead to stable structures. Since the algorithm is able to address structures on a given substrate, it can be useful from the experimental point of view.