Ab initio phonon transport across grain boundaries in graphene using machine learning based on small dataset
Ab initio phonon transport across grain boundaries in graphene using machine learning based on small dataset
复制标题
DOI：
10.1103/physrevmaterials.6.044004
复制
发表时间：
2019-08
影响因子：
3.4
通讯作者：
A. Hashemi;Ruiqiang Guo;K. Esfarjani;Sangyeop Lee
中科院分区：
文献类型：
--
作者：
A. Hashemi;Ruiqiang Guo;K. Esfarjani;Sangyeop Lee
建立晶界的结构-性能关系是开发下一代功能材料的关键，但由于其极大的构型空间而受到严重阻碍。具有低计算成本和高预测能力的原子模拟是强烈期望的，但是使用经验原子间相互作用势和密度泛函理论的常规模拟分别遭受缺乏预测能力和高计算成本。最近出现了一种机器学习原子间势（MLIP），但通常需要大量的训练数据集，这使得它成为一种不太可行的方法。在这里，我们证明了用合理设计的小训练数据集训练的MLIP可以以负担得起的计算成本以从头算的准确性预测石墨烯中跨GB的热输运。特别是，我们采用了一种基于结构单元模型的合理方法来找到一小部分可以代表整个配置空间的GB，从而可以作为MLIP的具有成本效益的训练数据集。发现仅5个GB足以代表石墨烯GB的整个构型空间。使用原子绿色函数方法和MLIP，我们揭示了石墨烯的结构-热阻关系并不遵循大位错密度导致较大热阻的共识。事实上，在室温下，热阻几乎与位错密度无关，并且在亚室温下，当位错密度较小时，热阻较高。我们解释了这种有趣的行为与附近的GB屈曲引起的弯曲声子模式的强烈散射。我们的工作表明，机器学习技术结合传统智慧（例如，结构单元模型）可以将最近成功的从头算热输运模拟（其主要限于单晶）扩展到具有GB的复杂但实际上重要的多晶。
Establishing the structure-property relationship for grain boundaries (GBs) is critical for developing next generation functional materials, but has been severely hampered due to its extremely large configurational space. Atomistic simulations with low computational cost and high predictive power are strongly desirable, but the conventional simulations using empirical interatomic potentials and density functional theory suffer from the lack of predictive power and high computational cost, respectively. A machine learning interatomic potential (MLIP) recently emerged but often requires an extensive size of the training dataset, making it a less feasible approach. Here we demonstrate that an MLIP trained with a rationally designed small training dataset can predict thermal transport across GBs in graphene with ab initio accuracy at an affordable computational cost. In particular, we employed a rational approach based on the structural unit model to find a small set of GBs that can represent the entire configurational space and thus can serve as a cost-effective training dataset for the MLIP. Only 5 GBs were found to be enough to represent the entire configurational space of graphene GBs. Using the atomistic Green’s function approach and the MLIP, we revealed that the structure-thermal resistance relation in graphene does not follow the common understanding that large dislocation density causes larger thermal resistance. In fact, thermal resistance is nearly independent of dislocation density at room temperature and is higher when the dislocation density is small at sub-room temperature. We explain this intriguing behavior with the buckling near a GB causing a strong scattering of flexural phonon modes. Our work shows that a machine learning technique combined with conventional wisdom (e.g., structural unit model) can extend the recent success of ab initio thermal transport simulation, which has been mostly limited to single crystals, to complex yet practically important polycrystals with GBs.