An iterative machine learning approach for discovering unexpected thermal conductivity enhancement in aperiodic superlattices

TL;DR

This paper presents an adaptive machine learning method that iteratively discovers unexpected thermal conductivity enhancements in aperiodic superlattices, revealing new physics beyond conventional expectations.

Contribution

The study introduces a novel iterative ML-accelerated search process that identifies exceptional aperiodic superlattices with enhanced thermal conductivity, surpassing prior methods limited to known physics.

Findings

ML can discover unexpected thermal conductivity enhancement in aperiodic superlattices.

Iterative training improves CNN prediction accuracy for rare structures.

Enhanced structures show increased coherent phonon contribution.

Abstract

While machine learning (ML) has shown increasing effectiveness in optimizing materials properties under known physics, its application in challenging conventional wisdom and discovering new physics still remains challenging due to its interpolative nature. In this work, we demonstrate the potential of using ML for such applications by implementing an adaptive ML-accelerated search process that can discover unexpected lattice thermal conductivity ($\kappa_l$) enhancement instead of reduction in aperiodic superlattices (SLs) as compared to periodic superlattices. We use non-equilibrium molecular dynamics (NEMD) simulations for high-fidelity calculations of $\kappa_l$ for a small fraction of SLs in the search space, along with a convolutional neural network (CNN) which can rapidly predict $\kappa_l$ for a large number of structures. To ensure accurate prediction by the CNN for the target unknown structures, we iteratively identify aperiodic SLs containing structural features which lead to locally enhanced thermal transport, and include them as additional training data for the CNN in each iteration. As a result, our CNN can accurately predict the high $\kappa_l$ of aperiodic SLs that are absent from the initial training dataset, which allows us to identify the previously unseen exceptional structures. The identified RML structures exhibit increased coherent phonon contribution to thermal conductivity owing to the presence of closely spaced interfaces. Our work describes a general purpose machine learning approach for identifying low-probability-of-occurrence exceptional solutions within an extremely large subspace and discovering the underlying physics.