Accelerating the Discovery of Materials with Expected Thermal Conductivity via a Synergistic Strategy of DFT and Interpretable Deep Learning

TL;DR

This paper presents an interpretable deep learning framework combined with DFT and MD to rapidly predict lattice thermal conductivity, enabling accelerated discovery of thermal materials while providing insights into phonon transport mechanisms.

Contribution

The study introduces a novel interpretable deep learning approach for LTC prediction that balances accuracy and interpretability, bridging a key gap in AI-driven material discovery.

Findings

Successfully identified four promising thermal conductors/insulators.

Provided new insights into phonon thermal transport mechanisms.

Set a new benchmark for interpretable AI in material science.

Abstract

Lattice thermal conductivity (LTC) is a critical parameter for thermal transport properties, playing a pivotal role in advancing thermoelectric materials and thermal management technologies. Traditional computational methods, such as Density Functional Theory (DFT) and Molecular Dynamics (MD), are resource-intensive, limiting their applicability for high-throughput LTC prediction. While AI-driven approaches have made significant strides in material science, the trade-off between accuracy and interpretability remains a major bottleneck. In this study, we introduce an interpretable deep learning framework that enables rapid and accurate LTC prediction, effectively bridging the gap between interpretability and precision. Leveraging this framework, we identify and validate four promising thermal conductors/insulators using DFT and MD. Moreover, by combining sensitivity analysis with DFT calculations, we uncover novel insights into phonon thermal transport mechanisms, providing a deeper understanding of the underlying physics. This work not only accelerates the discovery of thermal materials but also sets a new benchmark for interpretable AI in material science.