Experimental Ni3TeO6 synthesis condition exploration accelerated by active learning

Abstract

Material synthesis is time- and chemicals-consuming due to the traditional (“brute force”) methodology. For instance, Ni3TeO6 (NTO) is a multiferroic material relevant in different applications. Herein, we used an active learning scheme to explore the different phases obtained using a complex hydrothermal synthesis procedure instead of a solid-state methodology. Different from conventional ML prediction requiring a large dataset, we show that with only 9 data points obtained through experimental endeavor, 87% of the experimental condition space is predicted. The predicted phase configuration is verified with the sample in a new synthetic work. Beside exploring the NTO species, scheme developed herein constitute a powerful tool for experimental condition optimization.