Machine Learning and First-Principles Predictions of Materials with Low Lattice Thermal Conductivity

TL;DR

This study combines machine learning and density functional theory to identify materials with low lattice thermal conductivity and high thermoelectric efficiency, discovering promising cadmium-based compounds for thermal management and thermoelectric applications.

Contribution

The paper introduces a combined ML and DFT approach to predict low $_L$ materials and identifies new cadmium compounds with potential thermoelectric performance.

Findings

Several Cd compounds predicted to have $_L < 1.0$ W/mK.

Certain compounds like K$_2$CdPb$ and K$_2$CdSn$ show $ZT$ > 1.0.

ML models effectively screen for low thermal conductivity materials.

Abstract

We perform machine learning (ML) simulations and density functional theory (DFT) calculations to search for materials with low lattice thermal conductivity, $\kappa_L$. Several cadmium (Cd) compounds containing elements from the alkali-metal and carbon groups including A$_2$CdX (A = Li, Na, and K; X = Pb, Sn, and Ge) are predicted by our ML models to exhibit very low $\kappa_L$ values ($< 1.0 $ W/mK), rendering these materials suitable for potential thermal management and insulation applications. Further DFT calculations of electronic and transport properties indicate that the figure of merit, $ZT$, for thermoelectric performance can exceed 1.0 in compounds such as K$_2$CdPb, K$_2$CdSn, and K$_2$CdGe, which are thereby also promising thermoelectric materials.