Atomistic structure learning

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

DOI

One endeavor 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 structures and planar compounds atom by atom. The algorithm takes no prior data or knowledge on atomic interactions but inquires a first-principles quantum mechanical program for thermodynamical stability. 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. ASLA is demonstrated to work on diverse problems, including grain boundaries in graphene sheets, organic compound formation, and a surface oxide structure. (C) 2019 Author(s).

Original languageEnglish
Article number054111
JournalJournal of Chemical Physics
Volume151
Issue5
Number of pages11
ISSN0021-9606
DOIs
Publication statusPublished - Aug 2019

    Research areas

  • DESIGN, AG(111), OXYGEN, GAME, GO

See relations at Aarhus University Citationformats

ID: 163177546