Recommender System of Successful Processing Conditions for New Compounds Based on a Parallel Experimental Data Set

We propose a machine-learning method to recommend successful processing conditions for new compounds on the basis of parallel experiments. Initially, an experimental database was constructed for 67 pseudobinary oxides registered in the Inorganic Crystal Structure Database (ICSD) by parallel experiments using 23 starting materials and 23 cation mixing ratios. Precursor powders were obtained by four synthesis methods (solid-state reaction, polymerized complex, cyclic ether sol–gel, and spray coprecipitation), which were fired at five different temperatures. This resulted in 1648 unique chemical synthesis conditions and database entries. The reactants were characterized sequentially using powder X-ray diffraction equipment with an automatic sample exchanger. The synthesis results were rated as a score, which was placed into a fifth-order tensor with 243 340 elements. The Tucker decomposition method was used to predict yet-to-be-rated scores for unexperimented processing conditions. Good predictive performance of the present model was demonstrated by cross validation. It was further evaluated by examining the presence of highly rated compositions in another database, ICDD-PDF (International Center for Diffraction Data-Powder Diffraction File). Successful processing conditions for unexperimented compositions were found to be well recommended.