Machine Learning-Assisted Exploration of Thermally Conductive Polymers Based on High-Throughput Molecular Dynamics Simulations
Machine Learning-Assisted Exploration of Thermally Conductive Polymers Based on High-Throughput Molecular Dynamics Simulations
复制标题
DOI：
10.1016/j.mtphys.2022.100850
复制
发表时间：
2021-09
影响因子：
11.5
通讯作者：
Ruimin Ma;Hanfeng Zhang;Jiaxin Xu;Luning Sun;Y. Hayashi;R. Yoshida;J. Shiomi;Jian-Xun Wang
中科院分区：
文献类型：
--
作者：
Ruimin Ma;Hanfeng Zhang;Jiaxin Xu;Luning Sun;Y. Hayashi;R. Yoshida;J. Shiomi;Jian-Xun Wang
寻找具有更高导热性的无定形聚合物是很重要的，因为它们在传热很重要的广泛应用中无处不在。随着材料信息学的最新进展，机器学习方法越来越多地被用于寻找或设计具有所需特性的材料。然而，使用机器学习寻找导热聚合物的努力有限，主要是由于缺乏具有合理数据量的聚合物热导率数据库。在这项工作中，我们将联合收割机高通量分子动力学（MD）模拟和机器学习相结合，以探索具有相对较高热导率（>0.300 W/m-K）的聚合物-这是一个统计上重要的阈值，因为大多数纯聚合物在正常条件下的热导率低于该值。我们首先从现有的PoLyInfo数据库中随机选择365种聚合物，并使用MD模拟计算它们的热导率。然后使用这些数据来训练机器学习回归模型以量化结构-热导率关系，该关系进一步用于筛选PoLyInfo数据库中热导率>0.300 W/m-K的聚合物候选物。最终确定了121种MD计算的热导率高于此阈值的聚合物。在不同的模拟条件下，选择具有宽范围热导率值的聚合物进行重新计算，并且发现热导率高于0.300 W/m-K的那些聚合物大多被计算以保持高于该阈值的值，尽管精确值有波动。考虑到MD计算的TC中观察到的不确定性，我们还构建了一个贝叶斯神经网络来评估认知和任意预测的不确定性，其中使用最先进的近似贝叶斯推理算法进行可扩展的训练。这项工作的策略和结果可能有助于自动化的高导热性聚合物的设计。
Finding amorphous polymers with higher thermal conductivity is important, as they are ubiquitous in a wide range of applications where heat transfer is important. With recent progress in material informatics, machine learning approaches have been increasingly adopted for finding or designing materials with desired properties. However, limited effort has been put on finding thermally conductive polymers using machine learning, mainly due to the lack of polymer thermal conductivity databases with reasonable data volume. In this work, we combine high-throughput molecular dynamics (MD) simulations and machine learning to explore polymers with relatively high thermal conductivity (>0.300 W/m-K) – a statistically important threshold as most neat polymers have thermal conductivity lower than this value under normal conditions. We first randomly select 365 polymers from the existing PoLyInfo database and calculate their thermal conductivity using MD simulations. The data are then employed to train a machine learning regression model to quantify the structure-thermal conductivity relation, which is further leveraged to screen polymer candidates in the PoLyInfo database with thermal conductivity >0.300 W/m-K. 121 polymers with MD-calculated thermal conductivity above this threshold are eventually identified. Polymers with a wide range of thermal conductivity values are selected for re-calculation under different simulation conditions, and those polymers found with thermal conductivity above 0.300 W/m-K are mostly calculated to maintain values above this threshold despite fluctuation in the exact values. Given the observed uncertainties in the MD-calculated TC, we have also constructed a Bayesian neural network to evaluate the epistemic and aleatoric prediction uncertainties, where a state-of-the-art approximate Bayesian inference algorithm is used for scalable training. The strategy and results from this work may contribute to automating the design of polymers with high thermal conductivity.