Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks.

Journal: Journal of chemical information and modeling
Published Date:

Abstract

Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated, unsupervised method for connecting scientific literature to inorganic synthesis insights. Starting from the natural language text, we apply word embeddings from language models, which are fed into a named entity recognition model, upon which a conditional variational autoencoder is trained to generate syntheses for any inorganic materials of interest. We show the potential of this technique by predicting precursors for two perovskite materials, using only training data published over a decade prior to their first reported syntheses. We demonstrate that the model learns representations of materials corresponding to synthesis-related properties and that the model's behavior complements the existing thermodynamic knowledge. Finally, we apply the model to perform synthesizability screening for proposed novel perovskite compounds.

Authors

  • Edward Kim
    Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
  • Zach Jensen
    Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
  • Alexander van Grootel
    Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
  • Kevin Huang
    Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
  • Matthew Staib
    Department of EECS and CSAIL, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
  • Sheshera Mysore
    College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts 01003, United States.
  • Haw-Shiuan Chang
    College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts 01003, United States.
  • Emma Strubell
    College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts 01003, United States.
  • Andrew McCallum
    College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts 01003, United States.
  • Stefanie Jegelka
    Department of EECS and CSAIL, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
  • Elsa Olivetti
    Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.