Machine learning scheme for fast extraction of chemically interpretable interatomic potentials

We present a new method for a fast, unbiased and accurate representation of interatomic interactions. It is a combination of an artificial neural network and our new approach for pair potential reconstruction. The potential reconstruction method is simple and computationally cheap and gives rich information about interactions in crystals. This method can be combined with structure prediction and molecular dynamics simulations, providing accuracy similar to ab initio methods, but at a small fraction of the cost. We present applications to real systems and discuss the insight provided by our method.