Discovering new photovoltaics using optimal transport theory

TL;DR

This paper introduces a novel application of optimal transport theory, specifically the Fused Gromov-Wasserstein metric, to identify new photovoltaic materials by comparing structural and compositional similarities with minimal training.

Contribution

The study adapts the FGW metric for crystalline materials and demonstrates its effectiveness in discovering new high-efficiency photovoltaic candidates with minimal training data.

Findings

FGW is competitive with large neural network embeddings.

Seven new high-efficiency photovoltaic candidates identified.

Cs$_5$Sb$_8$ predicted to be thermodynamically stable.

Abstract

Searching by chemical and structural analogy is one of the most commonly used and successful approaches to materials discovery. However, formulating this task for algorithmic implementation raises the question of how we define similar materials. Methods have been proposed for searching materials space using vectors based on chemical composition and functional fragments in the material. Descriptors for structural similarity have also been proposed. However, the question of how to incorporate and balance structural and compositional similarity measures in a single metric remains open. Here, we adapt methods developed for calculating distances between undirected graphs and apply them to crystalline materials similarity. The Fused Gromov-Wasserstein (FGW) metric uses optimal transport theory to map between two graphs considering a balance of the graph structure and the information present at the nodes of the graph (atoms in crystals). We apply the method to exploring new photovoltaic materials. We demonstrate that FGW is competitive with embeddings from an equivariant graph neural network, trained on $> 10^6$ materials, despite minimal training. We then apply FGW to a discovery campaign to identify materials from the Materials Project database that have not previously been explored as photovoltaics, but have similarities to known high-efficiency materials. After validating predictions with hybrid density functional theory, we identify seven previously unexplored high-efficiency photovoltaic absorber candidates, including Cs$_5$Sb$_8$, which is found to have a predicted SLME of $> 30\%$ and to be thermodynamically stable. The FGW approach demonstrates the power of strong inductive biases for developing metrics for materials exploration with minimal training data.