Interpretable discovery of new semiconductors with machine learning

TL;DR

This paper introduces DARWIN, an evolutionary algorithm coupled with machine learning surrogate models, to efficiently discover new stable semiconductors with targeted properties, providing interpretable design rules and experimental validation.

Contribution

It presents DARWIN, a novel search strategy combining ML models and evolutionary algorithms for discovering semiconductors, with interpretable rules and experimental validation.

Findings

DARWIN efficiently searches large materials spaces for target properties.

Electronegativity difference predicts ternary structural stability.

Synthesized materials are stable, direct bandgap UV emitters.

Abstract

Machine learning models of materials$^{1-5}$ accelerate discovery compared to ab initio methods: deep learning models now reproduce density functional theory (DFT)-calculated results at one hundred thousandths of the cost of DFT$^{6}$. To provide guidance in experimental materials synthesis, these need to be coupled with an accurate yet effective search algorithm and training data consistent with experimental observations. Here we report an evolutionary algorithm powered search which uses machine-learned surrogate models trained on high-throughput hybrid functional DFT data benchmarked against experimental bandgaps: Deep Adaptive Regressive Weighted Intelligent Network (DARWIN). The strategy enables efficient search over the materials space of ~10$^8$ ternaries and 10$^{11}$ quaternaries$^{7}$ for candidates with target properties. It provides interpretable design rules, such as our finding that the difference in the electronegativity between the halide and B-site cation being a strong predictor of ternary structural stability. As an example, when we seek UV emission, DARWIN predicts K$_2$CuX$_3$ (X = Cl, Br) as a promising materials family, based on its electronegativity difference. We synthesized and found these materials to be stable, direct bandgap UV emitters. The approach also allows knowledge distillation for use by humans.