Universal fragment descriptors for predicting properties of inorganic crystals

Although historically materials discovery has been driven by a laborious trial-and-error process, knowledge-driven materials design can now be enabled by the rational combination of Machine Learning methods and materials databases. Here, data from the AFLOW repository for ab initio calculations is combined with Quantitative Materials Structure-Property Relationship models to predict important properties: metal/insulator classification, band gap energy, bulk/shear moduli, Debye temperature and heat capacities. The prediction's accuracy compares well with the quality of the training data for virtually any stoichiometric inorganic crystalline material, reciprocating the available thermomechanical experimental…

• NS
  National Science Foundation

  Awards: DGF-1106401, 1106401, 1053575, DE-AC02-05CH11231
• UD
  U.S. Department of Defense

  Awards: DE-AC02-05CH11231, N00014-13-1-0635
• UD
  U.S. Department of Energy

  Awards: -AC02-05CH11231, ACI-1053575, 05CH11231, AC02-05CH11231, DE-AC02, DE-AC02-05CH11231, DE-AC02-
• OO
  Office of Naval Research

  Awards: N00014-16-1-2311, N00014-13-1-0635, DE-AC02-05CH11231, N00014-13-1-0028, N00014-13-1-0030, N00014
• DO
  Division of Materials Research

  Awards: 1106401, 110088