Machine-Learning-Based phase diagram construction for high-throughput batch experiments

To know phase diagrams is a time saving approach for developing novel materials. efficiently construct diagrams, machine learning technique was developed using uncertainty sampling, which called as PDC (Phase Diagram Construction) package [K. Terayama et al. Phys. Rev. Mater. 3, 033802 (2019).]. In this method, the most uncertain point in diagram suggested next experimental condition. However, owing to recent progress lab automation techniques and robotics, high-throughput batch experiments can be performed. benefit from such nature, multiple conditions must selected simultaneously effectively technique. study, we consider some strategies do so, their performances were compared when exploring ternary isothermal sections (two-dimensional) temperature-dependent (three-dimensional). We show that even if suggestions are explored several instead of one at time, performance did not change drastically. Thus, conclude with suitable expected play an active role next-generation automated material development.