One endeavour of modern physical chemistry is to use bottom-up approaches to design materials and drugs with desired properties. Here we introduce an atomistic structure learning algorithm (ASLA) that utilizes a convolutional neural network to build 2D compounds and layered structures atom by atom. The algorithm takes no prior data or knowledge on atomic interactions but inquires a first-principles quantum mechanical program for physical properties. Using reinforcement learning, the algorithm accumulates knowledge of chemical compound space for a given number and type of atoms and stores this in the neural network, ultimately learning the blueprint for the optimal structural arrangement of the atoms for a given target property. ASLA is demonstrated to work on diverse problems, including grain boundaries in graphene sheets, organic compound formation and a surface oxide structure. This approach to structure prediction is a first step toward direct manipulation of atoms with artificially intelligent first principles computer codes.
@article{arxiv.1902.10501,
title = {Atomistic structure learning},
author = {Mathias S. Jørgensen and Henrik L. Mortensen and Søren A. Meldgaard and Esben L. Kolsbjerg and Thomas L. Jacobsen and Knud H. Sørensen and Bjørk Hammer},
journal= {arXiv preprint arXiv:1902.10501},
year = {2019}
}