Opportunities for machine learning to accelerate halide-perovskite commercialization and scale-up

Abstract

While halide perovskites attract significant academic attention, examples of industrial production at scale are still sparse. In this perspective, we review practical challenges hindering the commercialization of halide perovskites and discuss how machine-learning (ML) tools could help: (1) active-learning algorithms that blend institutional knowledge and human expertise could help stabilize and rapidly update baseline manufacturing processes, (2) computer-imaging methods with ML-based classification tools could help narrow the performance gap between large- and small-area devices, and (3) inference methods could help accelerate root-cause analysis by reconciling multiple data streams and simulations, focusing research efforts on the highest-probability areas. We conclude that to tackle many of these challenges, incremental—not radical—adaptations of existing ML methods are needed. We propose how industry-academic partnerships could help adapt “ready-now” ML tools to specific industry needs, further improve process control by revealing underlying mechanisms, and develop “gamechanger” discovery-oriented algorithms to better navigate the vast spaces of materials choices. While halide perovskites attract significant academic attention, examples of industrial production at scale are still sparse. In this perspective, we review practical challenges hindering the commercialization of halide perovskites and discuss how machine-learning (ML) tools could help: (1) active-learning algorithms that blend institutional knowledge and human expertise could help stabilize and rapidly update baseline manufacturing processes, (2) computer-imaging methods with ML-based classification tools could help narrow the performance gap between large- and small-area devices, and (3) inference methods could help accelerate root-cause analysis by reconciling multiple data streams and simulations, focusing research efforts on the highest-probability areas. We conclude that to tackle many of these challenges, incremental—not radical—adaptations of existing ML methods are needed. We propose how industry-academic partnerships could help adapt “ready-now” ML tools to specific industry needs, further improve process control by revealing underlying mechanisms, and develop “gamechanger” discovery-oriented algorithms to better navigate the vast spaces of materials choices.