Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Balanced Molecular Interactions with Mild Dipole Moment for Intermediate Suppressing in High Performance Antisolvent-Free Regular α-FAPbI<sub>3</sub> Solar Cells.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Oxidation-Retarded AgNWs/IZO Composite Electrodes for Highly Efficient and Stable Semitransparent Perovskite Solar Cells.

ACS applied materials & interfaces·2026
Same author

Transient Interphase Assisted Crystallization of Antisolvent-Free Perovskite for Enhanced Device Performance.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Multiple-Site Interface Modification with 3,4,5-Trifluorobenzoic Acid for Efficient and Stable Perovskite Solar Cells.

ChemSusChem·2026
Same author

The analysis of postoperative wound healing, infection risk prediction, and nursing intervention strategies for elderly patients with lung cancer.

BMC geriatrics·2025
Same author

Additive with Multinary Interactions to Perovskite Precursor Species for Catalyzed Crystallization of Antisolvent-Free α-FAPbI<sub>3</sub> Solar Cells.

Advanced materials (Deerfield Beach, Fla.)·2025

Related Experiment Video

Updated: Jul 2, 2026

Using Neutron Spin Echo Resolved Grazing Incidence Scattering to Investigate Organic Solar Cell Materials
06:05

Using Neutron Spin Echo Resolved Grazing Incidence Scattering to Investigate Organic Solar Cell Materials

Published on: January 15, 2014

Graph Neural Network-Assisted Machine Learning for High-Throughput Buried Interfacial Materials Screening in

Guodong Liu1, Kaixin Liu1, Haoyu Cai2

  • 1School of Automobile Engineering, Wuhan University of Technology, Wuhan 430070, P. R. China.

ACS Applied Materials & Interfaces
|July 1, 2026
PubMed
Summary
This summary is machine-generated.

Artificial intelligence accelerates perovskite solar cell (PSC) development by screening one million molecules rapidly. This AI approach identified new interface materials, achieving a 26.10% power conversion efficiency for efficient PSCs.

Keywords:
antisolvent-freegraph neural networksinterface passivationmachine learningscreeningsmall molecule

More Related Videos

Printing Fabrication of Bulk Heterojunction Solar Cells and In Situ Morphology Characterization
07:32

Printing Fabrication of Bulk Heterojunction Solar Cells and In Situ Morphology Characterization

Published on: January 29, 2017

Flash Infrared Annealing for Perovskite Solar Cell Processing
05:15

Flash Infrared Annealing for Perovskite Solar Cell Processing

Published on: February 3, 2021

Related Experiment Videos

Last Updated: Jul 2, 2026

Using Neutron Spin Echo Resolved Grazing Incidence Scattering to Investigate Organic Solar Cell Materials
06:05

Using Neutron Spin Echo Resolved Grazing Incidence Scattering to Investigate Organic Solar Cell Materials

Published on: January 15, 2014

Printing Fabrication of Bulk Heterojunction Solar Cells and In Situ Morphology Characterization
07:32

Printing Fabrication of Bulk Heterojunction Solar Cells and In Situ Morphology Characterization

Published on: January 29, 2017

Flash Infrared Annealing for Perovskite Solar Cell Processing
05:15

Flash Infrared Annealing for Perovskite Solar Cell Processing

Published on: February 3, 2021

Area of Science:

  • Materials Science
  • Renewable Energy
  • Artificial Intelligence

Background:

  • Perovskite solar cells (PSCs) require efficient interfacial materials for optimal performance.
  • Identifying suitable materials from vast chemical spaces is challenging and time-consuming.
  • Artificial intelligence (AI) offers a promising solution for accelerated materials discovery.

Purpose of the Study:

  • To develop an efficient AI-driven strategy for screening interfacial materials for PSCs.
  • To balance high-throughput screening with accurate predictive performance.
  • To identify novel interface modifiers for enhanced PSC efficiency.

Main Methods:

  • A two-step cascade screening strategy integrating a contrastive learning-based graph neural network (CLGNN) and a gradient boosting decision tree regressor (GBDTR).
  • CLGNN trained on unlabeled molecular graphs for rapid initial screening of one million molecules.
  • GBDTR trained on labeled data for accurate prediction of device performance using physicochemical descriptors.

Main Results:

  • CLGNN screened one million molecules in 10 minutes, identifying 128 candidates.
  • Two effective buried-interface modifiers, 4,4'-iminodibenzoic acid (4,4'-IDA) and 4,4'-biphenyldicarboxylic acid (4,4'-BA), were selected.
  • PSCs utilizing these modifiers achieved a high power conversion efficiency of 26.10% with excellent open-circuit voltage (1.184 V) and fill factor (86.05%) via antisolvent-free processing.

Conclusions:

  • The proposed AI-assisted cascade screening strategy significantly accelerates the discovery of high-performance materials for PSCs.
  • This approach reduces the need for extensive computational and experimental validation.
  • Demonstrates a scalable and rapid route for exploring new materials crucial for advancing PSC technology.