Xia Weiyi, Tee Wei-Shen, Canfield Paul, Flint Rebecca, Wang Cai-Zhuang
Ames National Laboratory, U.S. Department of Energy, Iowa State University, Ames, Iowa 50011, United States.
Department of Physics and Astronomy, Iowa State University, Ames, Iowa 50011, United States.
Inorg Chem. 2025 May 26;64(20):10161-10169. doi: 10.1021/acs.inorgchem.5c00899. Epub 2025 May 9.
Cerium-based intermetallics have garnered significant research attention as potential new permanent magnets. In this study, we explore the compositional and structural landscape of Ce-Co-Cu ternary compounds using a machine learning (ML)-guided framework integrated with first-principles calculations. We employ a crystal graph convolutional neural network (CGCNN), which enables efficient screening for promising candidates, significantly accelerating the material discovery process. With this approach, we predict five stable compounds, CeCoCu, CeCoCu, CeCoCu, CeCoCu, and CeCoCu, with formation energies below the convex hull, along with hundreds of low-energy (possibly metastable) Ce-Co-Cu ternary compounds. First-principles calculations reveal that several structures are both energetically and dynamically stable. Notably, two Co-rich low-energy compounds, CeCoCu and CeCoCu, are predicted to have high magnetizations.
铈基金属间化合物作为潜在的新型永磁体已引起了大量的研究关注。在本研究中，我们使用与第一性原理计算相结合的机器学习（ML）引导框架，探索Ce-Co-Cu三元化合物的成分和结构情况。我们采用了晶体图卷积神经网络（CGCNN），它能够有效地筛选出有前景的候选物，显著加速材料发现过程。通过这种方法，我们预测了五种形成能低于凸包的稳定化合物，即CeCoCu、CeCoCu、CeCoCu、CeCoCu和CeCoCu，以及数百种低能量（可能是亚稳的）Ce-Co-Cu三元化合物。第一性原理计算表明，几种结构在能量和动力学上都是稳定的。值得注意的是，预测两种富钴低能量化合物CeCoCu和CeCoCu具有高磁化强度。
