Deep learning reveals key predictors of thermal conductivity in covalent organic frameworks

TL;DR

This study uses deep learning and molecular dynamics to identify dangling molecular branches as key predictors of thermal conductivity in covalent organic frameworks, revealing how structural features influence heat transfer.

Contribution

It introduces an attention-based machine learning model and the dangling mass ratio (DMR) as novel predictors for thermal conductivity in COFs.

Findings

Dangling branches significantly reduce thermal conductivity.

Attention model accurately predicts thermal properties.

Molecular dynamics confirms vibrational mismatches due to dangling branches.

Abstract

The thermal conductivity of covalent organic frameworks (COFs), an emerging class of nanoporous polymeric materials, is crucial for many applications, yet the link between their structure and thermal properties remains poorly understood. Analysis of a dataset containing over 2,400 COFs reveals that conventional features such as density, pore size, void fraction, and surface area do not reliably predict thermal conductivity. To address this, an attention-based machine learning model was trained, accurately predicting thermal conductivities even for structures outside the training set. The attention mechanism was then utilized to investigate the model's success. The analysis identified dangling molecular branches as a key predictor of thermal conductivity, leading us to define the dangling mass ratio (DMR), a descriptor that quantifies the fraction of atomic mass in dangling branches relative to the total COF mass. Feature importance assessments on regression models confirm the significance of DMR in predicting thermal conductivity. These findings indicate that COFs with dangling functional groups exhibit lower thermal transfer capabilities. Molecular dynamics simulations support this observation, revealing significant mismatches in the vibrational density of states due to the presence of dangling branches.