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

Institutions

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

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Interpretable decision tree-assisted optimization of PLD growth of EuBa2Cu3O7-δ films

Dongliang Gong, Guangyao Lin, Yue Gong, Kai Wang et al.
2 links
NPG Asia Materials
Machine Learning in Materials Science
article

Interpretable decision tree-assisted optimization of PLD growth of EuBa2Cu3O7-δ films

Dongliang Gong, Guangyao Lin, Yue Gong, Kai Wang, Yanwei Ma, Ziheng Guo, Penghong Hu, Xinyue Xia, Liangkang Chen, Dongliang Wang, Zhongtang Xu, Minghui Tang
article en

Abstract

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.

NPG Asia Materials
Chinese Academy of Sciences (CN), Institute of Electrical Engineering (CN), National Center for Nanoscience and Technology (CN), University of Chinese Academy of Sciences (CN)
National Natural Science Foundation of China, Chinese Academy of Sciences, Beijing Municipal Science and Technology Commission
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon