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

コレクション

引用

説明:

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.

権利情報:

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

キーワード: phase diagram, machine learning

刊行年月日: 2026-02-16

出版者: Royal Society of Chemistry (RSC)

掲載誌:

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

研究助成金:

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

原稿種別: 出版者版 (Version of record)

MDR DOI:

公開URL: https://doi.org/10.1039/d5dd00486a

関連資料:

その他の識別子:

連絡先:

更新時刻: 2026-04-01 14:33:21 +0900

MDRでの公開時刻: 2026-04-01 16:26:11 +0900