Genetic algorithm-driven discovery of unexpected thermal conductivity enhancement by disorder

Discovering exceptions has been a major route for advancing sciences but a challenging and risky process. Machine learning has shown effectiveness in high throughput search of materials and nanostructures, but using it to discover exceptions has been out of the norm. Here we demonstrate the use of genetic algorithm to discover unexpected thermal conductivity enhancement in disordered nanoporous graphene as compared to periodic nanoporous graphene. Recent studies have concluded that random pores in nanoporous graphene lead to reduced thermal conductivity than periodic pores, due to phonon Anderson localization. This work, however, aims to challenge this accepted knowledge by searching for exceptions. A manual search was first shown to be expensive and unsuccessful. An efficient "two-step" search process coupled with genetic algorithm was then designed, and unexpected thermal conductivity enhancement was successfully discovered in certain structures with random pores, at a fraction of the computational cost of the manual search. Through structural analysis, we proposed that such unusual enhancement is due to the effect of shape factor and channel factor dominating over that of the phonon localization. Our work not only provides insights in thermal transport in disordered materials but also demonstrates the effectiveness of machine learning to discover small probability events and the intriguing physics behind.