From Literature to Lab: Closed-Loop Advancement of Perovskite Solar Cells via Domain Knowledge Guided LLM

TL;DR

This paper presents PVK-LLM, a domain-knowledge-guided framework that enhances large language models to efficiently design high-performance perovskite solar cells through hierarchical Bayesian optimization and experimental validation.

Contribution

It introduces a novel domain-knowledge integration method for LLMs, enabling efficient high-dimensional material design and achieving near-record efficiency in real-world experiments.

Findings

Achieved a PCE of over 26.0% with a new four-component recipe.

Successfully integrated domain knowledge into LLM for material design.

Demonstrated effective navigation of high-dimensional design space.

Abstract

Perovskite solar cells (PSCs) have been considered as a next-generation disruptive photovoltaic technology, yet their advancement is constrained by the complexity of perovskite recipe with high-dimensional material and process design space. Despite the impressive general reasoning of Large Language Models (LLMs), they struggle with two limitations for application in PSCs: an inability to align general semantics with the perovskite domain knowledge, and an inefficiency in navigating high-dimensional perovskite material and recipe design spaces. To address these limitations, we introduce a domain-knowledge-guided framework PVK-LLM, a specialized model to serve as an expert to bridge general semantics with perovskite domain knowledge. By integrating this domain knowledge into a hierarchical Bayesian Optimization workflow, our approach efficiently navigates the high-dimension design space on a solar cell simulator platform. The domain knowledge resolves cold-start problems while dynamically adapting to simulator feedback. Moreover, in an individual wet-lab experiment aimed at maximizing power conversion efficiency (PCE), our framework autonomously proposes a novel synergistic four-component recipe comprising specialized organic passivation recipe (3MTPAI, PDAI2, EDAI2, and PipDI) which has not been reported in existing literature. This AI-designed recipe effectively achieves a champion PCE value of over 26.0 %, approaching world records achieved through extensive expert trial-and-error. Our approach can effectively enable LLM comprehend the domain knowledge, which can efficiently navigate in a high-dimensional, capable to accelerate the advancement in real-world perovskite as well as other material science development.