Exploring diamondlike lattice thermal conductivity crystals via feature-based transfer learning
Exploring diamondlike lattice thermal conductivity crystals via feature-based transfer learning
复制标题
DOI：
10.1103/physrevmaterials.5.053801
复制
发表时间：
2019-09
影响因子：
3.4
通讯作者：
S. Ju;Ryo Yoshida;Chang Liu;Stephen Wu;K. Hongo;T. Tadano;J. Shiomi
中科院分区：
文献类型：
--
作者：
S. Ju;Ryo Yoshida;Chang Liu;Stephen Wu;K. Hongo;T. Tadano;J. Shiomi
超高晶格热导率材料在电子和光学器件的热管理中起着至关重要的作用，因此具有重要的意义。使用机器学习的模型可以搜索具有出色的高阶性能的材料，如导热系数。然而，缺乏足够的数据来训练模型是一个严重的障碍。在这里，我们表明，当适当地选择大数据中可用的低阶特征属性并将其应用于迁移学习时，大数据可以补充小数据以实现准确的预测。利用神经网络直接建立晶体信息与导热系数之间的联系，通过传递通过特征属性的预训练模型获得的描述符。成功的迁移学习显示了外推预测的能力，并揭示了晶格非谐性的描述符。转移学习被用来筛选60000多种化合物，以识别可以作为钻石替代品的新晶体。尽管榜单上的大多数材料都是超硬材料，但我们发现，超硬性质并不一定会导致高的晶格热导率。高硬度意味着在线性色散区声子的弹性常数和群速度较高，但晶格热导率还受声子弛豫时间等其他重要因素的影响。此外，平均或最大偶极极化率和范德华半径是也可以定性地与非谐性相关的主要描述符。
Ultrahigh lattice thermal conductivity materials hold great importance since they play a critical role in the thermal management of electronic and optical devices. Models using machine learning can search for materials with outstanding higher-order properties like thermal conductivity. However, the lack of sufficient data to train a model is a serious hurdle. Herein we show that big data can complement small data for accurate predictions when lower-order feature properties available in big data are selected properly and applied to transfer learning. The connection between the crystal information and thermal conductivity is directly built with a neural network by transferring descriptors acquired through a pre-trained model for the feature property. Successful transfer learning shows the ability of extrapolative prediction and reveals descriptors for lattice anharmonicity. Transfer learning is employed to screen over 60000 compounds to identify novel crystals that can serve as alternatives to diamond. Even though most materials in the top list are superhard materials, we reveal that superhard property do not necessarily lead to high lattice thermal conductivity. Large hardness means high elastic constants and group velocity of phonons in the linear dispersion regime, but the lattice thermal conductivity is determined also by other important factor such as the phonon relaxation time. What’s more, the average or maximum dipole polarizability and the van der Waals radius are revealed to be the leading descriptors among those that can also be qualitatively related to anharmonicity.