Unlocking enhanced thermal conductivity in polymer blends through active learning

Article Properties
Abstract
Cite
Xu, Jiaxin, and Tengfei Luo. “Unlocking Enhanced Thermal Conductivity in Polymer Blends through Active Learning”. Npj Computational Materials, vol. 10, no. 1, 2024, https://doi.org/10.1038/s41524-024-01261-2.
Xu, J., & Luo, T. (2024). Unlocking enhanced thermal conductivity in polymer blends through active learning. Npj Computational Materials, 10(1). https://doi.org/10.1038/s41524-024-01261-2
Xu J, Luo T. Unlocking enhanced thermal conductivity in polymer blends through active learning. npj Computational Materials. 2024;10(1).
Journal Categories
Science
Chemistry
Science
Chemistry
Physical and theoretical chemistry
Science
Mathematics
Instruments and machines
Electronic computers
Computer science
Computer software
Technology
Chemical technology
Technology
Electrical engineering
Electronics
Nuclear engineering
Materials of engineering and construction
Mechanics of materials
Description

Can machine learning help us discover better materials? This study employs a combination of high-throughput molecular dynamics (MD) simulation and active learning (AL) to identify polymer blends with enhanced thermal conductivity (TC) compared to their single-component counterparts. Researchers initially determined the TC of approximately 600 amorphous single-component polymers and 200 blends via MD simulations. They identified the optimal representation method for polymer blends and utilized an AL framework to explore the TC of roughly 550,000 unlabeled blends. This framework proved highly effective in accelerating the discovery of high-performance polymer blends for thermal transport. The Rg improvement and the indirect contribution from H-bond interaction contribute to TC enhancement through an odds ratio calculation. This work highlights the potential of AL to efficiently navigate the vast chemical space of polymer blends. It also provides valuable insights into the relationship between TC, radius of gyration, and hydrogen bonding, advancing our understanding of thermal transport mechanisms in amorphous polymer blends. Ultimately, this approach accelerates the design and development of advanced polymeric materials for various applications.

Published in npj Computational Materials, this study is highly relevant to the journal's focus. It combines computational materials science with machine learning to discover polymer blends with enhanced thermal conductivity, a key area of interest for researchers in this field.

Refrences
Refrences Analysis
The category Science: Chemistry 44 is the most frequently represented among the references in this article. It primarily includes studies from Physical Chemistry Chemical Physics The chart below illustrates the number of referenced publications per year.
Refrences used by this article by year