Machine learning-assisted exploration of thermally conductive polymers based on high-throughput molecular dynamics simulations. (November 2022)

• Record Type: Journal Article
• Authors: Ma, Ruimin; Zhang, Hanfeng; Xu, Jiaxin; Sun, Luning; Hayashi, Yoshihiro; Yoshida, Ryo; Shiomi, Junichiro; Wang, Jian-xun; Luo, Tengfei
• Is Part Of: Materials today physics. Volume 28(2022)
• Publication Date: 2022-11
• Subjects: Amorphous polymer -- Thermal conductivity -- Molecular dynamics -- Machine learning -- Chemical structure; TC thermal conductivity -- MD molecular dynamics -- RF random forests -- BNN Bayesian neural network -- NEMD non-equilibrium molecular dynamics; Materials science -- Periodicals; Physics -- Periodicals; Electronic journals; 530.41
• DOI: 10.1016/j.mtphys.2022.100850
• Languages: English
• ISSNs: 2542-5293

Abstract

Abstract: 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. Graphical abstract: Image 1 Highlights: High-throughput molecular dynamics combined with machine learning to explore high thermal conductivity amorphous polymers. Machine learning helps increase the population of high thermal conductivity amorphous polymers. Uncertainties from molecular dynamics simulations are investigated. Bayesian neural networks predict and quantify the uncertainty on thermal conductivity prediction using machine learning.