Mordechai Kornbluth

Feb 3, 2023 | nature.com | Simon Batzner |Anders F Johansson |Mordechai Kornbluth |Cameron J. Owen

AbstractA simultaneously accurate and computationally efficient parametrization of the potential energy surface of molecules and materials is a long-standing goal in the natural sciences. While atom-centered message passing neural networks (MPNNs) have shown remarkable accuracy, their information propagation has limited the accessible length-scales. Local methods, conversely, scale to large simulations but have suffered from inferior accuracy.