Scholarlink

<p>ABN<sub>3</sub>-type nitride perovskites offer a rich platform for multifunctional materials but remain synthetically elusive. Here, we develop a machine learning (ML)-guided framework to expand the library of nitride perovskites and identify multiferroic candidates. By integrating positive-unlabeled (PU) learning with crystal graph convolutional neural networks (CGCNN), we screen 1465 ABN<sub>3</sub> compositions and predict 96 synthesizable compounds. Further symmetry and magnetic filtering yield 4 altermagnetic ferroelectric (AM-FE) perovskites. Among them, CeCrN<sub>3</sub> emerges as a promising candidate, exhibiting a bandgap of 0.30 eV, a spontaneous polarization of 0.59 μC/cm<sup>2</sup>, a high Curie temperature of 650 K, and a low polarization switching barrier of 53 meV, as confirmed by density functional theory (DFT) calculations. In addition, CeCrN<sub>3</sub> demonstrates a pronounced bulk photovoltaic effect (BPVE), with the shift current reaching 44 μA/V<sup>2</sup> and an injection current reaching 2.4 × 10<sup>9 </sup>A/V<sup>2</sup>, both of which reverse upon FE switching. These findings not only advance the understanding of nitride perovskites but also provides a validated ML-DFT framework to guide experimental efforts in realizing novel functional materials.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PU-learning-guided discovery of synthesizable multiferroic nitride perovskites with altermagnetic order

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月28日

查看全文
  • Tao Wang,
  • Jianwei Li,
  • Bin Wang,
  • Hao Jin

摘要

ABN3-type nitride perovskites offer a rich platform for multifunctional materials but remain synthetically elusive. Here, we develop a machine learning (ML)-guided framework to expand the library of nitride perovskites and identify multiferroic candidates. By integrating positive-unlabeled (PU) learning with crystal graph convolutional neural networks (CGCNN), we screen 1465 ABN3 compositions and predict 96 synthesizable compounds. Further symmetry and magnetic filtering yield 4 altermagnetic ferroelectric (AM-FE) perovskites. Among them, CeCrN3 emerges as a promising candidate, exhibiting a bandgap of 0.30 eV, a spontaneous polarization of 0.59 μC/cm2, a high Curie temperature of 650 K, and a low polarization switching barrier of 53 meV, as confirmed by density functional theory (DFT) calculations. In addition, CeCrN3 demonstrates a pronounced bulk photovoltaic effect (BPVE), with the shift current reaching 44 μA/V2 and an injection current reaching 2.4 × 109 A/V2, both of which reverse upon FE switching. These findings not only advance the understanding of nitride perovskites but also provides a validated ML-DFT framework to guide experimental efforts in realizing novel functional materials.