Transfer learning discovery of molecular modulators for perovskite solar cells

2025-10-31

AI Summary

Molecular modulator screening for perovskite solar cells (PSCs) faces challenges including vast chemical space, high experimental costs, and limitations of quantitative structure–property relationship (QSPR) models—namely, small-sample constraints and poor interpretability. Method: We propose a cheminformatics transfer learning framework based on a pretrained deep neural network, integrating multimodal molecular representations, transfer learning, and explainable AI (XAI) techniques to enable high-accuracy prediction of molecular modulation effects with only limited labeled data. Contribution/Results: Through systematic benchmarking and high-throughput virtual screening across >79,000 commercially available molecules, our approach identifies highly effective modulators. Experimental validation achieves a certified power conversion efficiency (PCE) of 26.91%. This work establishes a generalizable, data-efficient paradigm for accelerated PSC material discovery.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The discovery of effective molecular modulators is essential for advancing perovskite solar cells (PSCs), but the research process is hindered by the vastness of chemical space and the time-consuming and expensive trial-and-error experimental screening. Concurrently, machine learning (ML) offers significant potential for accelerating materials discovery. However, applying ML to PSCs remains a major challenge due to data scarcity and limitations of traditional quantitative structure-property relationship (QSPR) models. Here, we apply a chemical informed transfer learning framework based on pre-trained deep neural networks, which achieves high accuracy in predicting the molecular modulator's effect on the power conversion efficiency (PCE) of PSCs. This framework is established through systematical benchmarking of diverse molecular representations, enabling lowcost and high-throughput virtual screening over 79,043 commercially available molecules. Furthermore, we leverage interpretability techniques to visualize the learned chemical representation and experimentally characterize the resulting modulator-perovskite interactions. The top molecular modulators identified by the framework are subsequently validated experimentally, delivering a remarkably improved champion PCE of 26.91% in PSCs.

Problem

• Accelerating molecular modulator discovery for perovskite solar cells
• Overcoming data scarcity in machine learning for materials science
• Enabling high-throughput virtual screening of commercial molecules

Innovation

• Transfer learning framework predicts molecular modulator effects
• Virtual screening of 79,043 molecules using deep neural networks
• Interpretability techniques visualize chemical representations and interactions