Interpretable decision tree-assisted optimization of PLD growth of EuBa2Cu3O7-δ films
Understanding the process-performance relationship is of fundamental importance for optimizing functional properties and guiding material design. However, establishing this relationship remains highly challenging because the processing parameters define a high-dimensional feature space, interact with one another, and often exhibit non-monotonic effects on material properties. Here, we propose a novel decision-tree splitting strategy that integrates an interval-splitting scheme and parameter linear correlations to address non-monotonic and strongly coupled problems and apply it to the growth of EuBa 2 Cu 3 O 7- δ superconducting films by pulsed laser deposition. Using experimental data for training, the proposed model identifies oxygen pressure ( P O2 ) as the key parameter in determining film performance and classifies the preparation process into high-performance and low-performance modes. Electron microscopy reveals that the primary difference between these two modes lies in their influence on the morphology of rare-earth oxide precipitated phases in the films, which in turn affects the critical current density ( J c ) of the films under magnetic fields. These results demonstrate that the proposed strategy provides an interpretable and effective approach to reveal non-monotonic process–performance relationships and guide the optimization of EuBa 2 Cu 3 O 7- δ film growth.
Authors
- Dongliang Gong (ORCID: https://orcid.org/0000-0003-1804-7811)
- Guangyao Lin
- Yue Gong (ORCID: https://orcid.org/0000-0002-5764-3117)
- Kai Wang (ORCID: https://orcid.org/0000-0001-8836-1553)
- Yanwei Ma (ORCID: https://orcid.org/0000-0002-7131-0888)
- Ziheng Guo
- Penghong Hu (ORCID: https://orcid.org/0009-0002-4884-6294)
- Xinyue Xia (ORCID: https://orcid.org/0009-0002-4081-9208)
- Liangkang Chen
- Dongliang Wang
- Zhongtang Xu
- Minghui Tang
Institutions
- Chinese Academy of Sciences (CN)
- Institute of Electrical Engineering (CN)
- National Center for Nanoscience and Technology (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Journal
- NPG Asia Materials
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1038/s41427-026-00686-z
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Chinese Academy of Sciences
- Beijing Municipal Science and Technology Commission