Graph Neural Network-Assisted Machine Learning for High-Throughput Buried Interfacial Materials Screening in Antisolvent-Free Perovskite Solar Cells
Authors:
- 1 July 2026
- journal article
- Published by American Chemical Society (ACS) in ACS Applied Materials & Interfaces
- Vol. 18 (27) , 38190-38202
Abstract
Numerous interfacial materials have been explored for efficient perovskite solar cells (PSCs). The identification of optimal candidates from the vast chemical space remains a difficult and costly task. Artificial intelligence (AI)-assisted materials screening has emerged as a convenient route to benefit and promote the pace of PSC research. Here, we propose a two-step cascade screening strategy that integrates a contrastive learning-based graph neural network (CLGNN) with a gradient boosting decision tree regressor (GBDTR) to balance high-throughput and predictive accuracy. Among them, CLGNN is a graph contrastive learning model trained on large-scale unlabeled molecular graph topologies, whereas GBDTR is a supervised regression model trained on a manually curated and labeled database. Using CLGNN, we screened one million molecules on a graphics processing unit (GPU) and shortlisted 128 candidates within 10 min. This step substantially reduced the number of molecules requiring subsequent density functional theory (DFT) calculations and experimental validation. We then developed and evaluated multiple regression models based on multidimensional physicochemical descriptors to accurately predict device performance. Two effective buried-interface modifiers, 4,4'-iminodibenzoic acid (4,4'-IDA) and 4,4'-biphenyldicarboxylic acid (4,4'-BA), were selected, which delivered a high-power conversion efficiency of 26.10% with an open-circuit voltage (VOC) of 1.184 V and a fill factor (FF) of 86.05% using antisolvent-free processing. This work exemplifies an efficient route for scalable and rapid exploration of new materials for PSCs.Keywords
Funding Information
- Guangdong Provincial Pearl River Talents Program (2021ZT09L400)
- National Natural Science Foundation of China (52072284)
- National Natural Science Foundation of China (52302195)
This publication has 64 references indexed in Scilit:
- Self‐Assembled Monolayers in p–i–n Perovskite Solar Cells: Molecular Design, Interfacial Engineering, and Machine Learning–Accelerated Material DiscoveryAdvanced Materials, 2026
- Enhancing Open‐Circuit Voltage and Fill Factor in Sn‐Based Perovskite Solar Cells: Challenges and Opportunities for Sustainable PhotovoltaicsSusmat, 2025
- Data‐Driven Molecular Encoding for Efficient Screening of Organic Additives in Perovskite Solar CellsAdvanced Functional Materials, 2025
- Viologen as an Electrolyte Additive for Extreme Fast Charging of Lithium‐Ion BatteriesBattery Energy, 2025
- Machine Learning for Screening Small Molecules as Passivation Materials for Enhanced Perovskite Solar CellsAdvanced Functional Materials, 2024
- Co‐Self‐Assembled Monolayers Modified NiOx for Stable Inverted Perovskite Solar CellsAdvanced Materials, 2024
- A Universal Strategy of Perovskite Ink ‐ Substrate Interaction to Overcome the Poor Wettability of a Self‐Assembled Monolayer for Reproducible Perovskite Solar CellsAdvanced Functional Materials, 2023
- Artificial Intelligence and Advanced MaterialsAdvanced Materials, 2023
- Deep Learning for Additive Screening in Perovskite Light‐Emitting DiodesAngewandte Chemie International Edition, 2022
- A Critical Review of Machine Learning of Energy MaterialsAdvanced Energy Materials, 2020