Download file (800 KB)
Download as zip (679 KB)

Collection

Citation

Description:

Machine learning methods are increasingly used in experimental design in phase diagram determination. Some methods perform batch design, where multiple points are sampled from the design space. In this case, it is essential to diversify samples to avoid performing almost identical experiments, and control the diversity level appropriately. Manual diversity control is unintuitive and may require additional trial-and-error in prior to the experiments are started. We propose a Bayesian model called determinantal point process for phase diagram construction (DPP-PDC) that can perform batch design and automatic diversity control simultaneously. Central to this model is the uncertainty-weighted determinantal point process that samples a set of points with high uncertainty under diversity control. Experiments with Cu-Mg-Zn ternary system demonstrate that DPP-PDC can actively control the sample diversity to achieve high efficiency.

Rights:

• https://creativecommons.org/licenses/by-nc/3.0/
  

Keyword: phase diagram, machine learning

Date published: 2026-02-16

Publisher: Royal Society of Chemistry (RSC)

Journal:

• Digital Discovery (ISSN: 2635098X) vol. 5 issue. 3 p. 1252-1256

Funding:

• Core Research for Evolutional Science and Technology JPMJCR21O2
• Exploratory Research for Advanced Technology JPMJER1903
• Japan Society for the Promotion of Science 25K01492

Manuscript type: Publisher's version (Version of record)

MDR DOI:

First published URL: https://doi.org/10.1039/d5dd00486a

Related item:

Other identifier(s):

Contact agent:

Updated at: 2026-04-01 14:33:21 +0900

Published on MDR: 2026-04-01 16:26:11 +0900