npj: 机器学习—界面热阻的预测

来源：知社学术圈

来自日本物质材料研究所的华人科学家徐一斌女士领导的团队，通过进一步考虑基于化学、物理和材料特性的界面条件，使用机器学习对界面热阻作了精确的预测，其预测结果的相关系数R高达0.96。他们将描述符分为三种符集：性能描述符、化合物描述符和过程描述符。在80,282种材料体系中，界面热阻预测准确度最高的前100名中，三种模型中至少有两个模型重复预测了25种材料体系的结果。25种材料体系有两个主要组：Bi /氧化物和AsI3 /碲化物或碘化物。其中，Bi / Si实现了0.16  Wm−1K−1的超低导热率。所预测的高界面热阻材料，被证明是绝热或热电应用的潜在候选者。通过限制新材料的搜索空间，如高温环境的高熔点，界面热阻预测模型还可扩展到更具体的热需求。该策略可以加速热利用的新材料开发。

该文近期发表于npj Computational Materials 5: 56 (2019)，英文标题与摘要如下，点击左下角“阅读原文”可以自由获取论文PDF。

Predicting interfacial thermal resistance by machine learning 

Yen-Ju Wu, Lei Fang & Yibin Xu 

Various factors affect the interfacial thermal resistance (ITR) between two materials, making ITR prediction a high-dimensional mathematical problem. Machine learning is a cost-effective method to address this. Here, we report ITR predictive models based on experimental data. The physical, chemical, and material properties of ITR are categorized into three sets of descriptors, and three algorithms are used for the models. hose descriptors assist the models in reducing the mismatch between predicted and experimental values and reaching high predictive performance of 96%. Over 80,000 material systems composed of 293 materials were inputs for predictions. Among the top-100 high-ITR predictions by the three different algorithms, 25 material systems are repeatedly predicted by at least two algorithm. One of the 25 material systems, Bi/Si achieved the ultra-low thermal conductivity in our previous work. We believe that the predicted high-ITR material systems are potential candidates for thermoelectric applications. This study proposed a strategy for material exploration for thermal management by means of machine learning.