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

Scanning Electron Microscopy01:07

Scanning Electron Microscopy

A scanning electron microscope (SEM) is used to study the surface features of a sample by using an electron beam that scans the sample surface in a two-dimensional manner. Typically, areas between ~1 centimeter to 5 micrometers in width can be imaged. SEM can be used to image bacteria, viruses, tissues as well as larger samples like insects. Conventional SEM gives a magnification ranging from 20X to 30,000X and spatial resolution of 50 to 100 nanometers.
Fundamental Principles
Accelerated...
Self-Evaluation Maintenance Model01:29

Self-Evaluation Maintenance Model

The Self-Evaluation Maintenance (SEM) model offers a psychological framework to understand how individuals’ self-esteem is influenced by the achievements of others, particularly those with whom they share close personal bonds. The SEM model operates when personal rather than social identity guides individuals. Central to this model is the notion that individuals have an inherent desire to preserve a favorable self-image, which is continuously shaped by interpersonal comparisons and...

You might also read

Related Articles

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

Sort by
Same author

Federated microservices architecture with blockchain for privacy-preserving and scalable healthcare analytics.

Scientific reports·2026
Same author

Unravelling amino acid-graphene interactions: insights from polarizable force field simulations.

Nanoscale·2025
Same author

Modelling of queuing systems using blockchain based on Markov process for smart healthcare systems.

Scientific reports·2025
Same author

Multi-Modal Graph Neural Networks for Colposcopy Data Classification and Visualization.

Cancers·2025
Same author

Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation.

Cancers·2025
Same author

Comparison of Different Animal Models in Hindlimb Functional Recovery after Acute Limb Ischemia-Reperfusion Injury.

Biomedicines·2024

Related Experiment Video

Updated: Jul 1, 2026

Influence of Hybrid Perovskite Fabrication Methods on Film Formation, Electronic Structure, and Solar Cell Performance
11:38

Influence of Hybrid Perovskite Fabrication Methods on Film Formation, Electronic Structure, and Solar Cell Performance

Published on: February 27, 2017

19.0K

A multi-model deep learning framework for SEM-based defect detection in [Formula: see text] Perovskite thin films.

Zulfikar Ali Ansari1, Sahil Soni2, Shahin Fatima3

  • 1AIML Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Lavale, Pune, Maharashtra, 412115, India. zulfikar.ansari@sitpune.edu.in.

Scientific Reports
|November 25, 2025
PubMed
Summary

Deep learning models accurately classify defects in perovskite solar cells (PSCs), improving manufacturing quality control. This automated approach enhances the efficiency and reliability of next-generation photovoltaic technologies.

Keywords:
Data augmentationDeep learningDenseNet169Perovskite solar cellsResNet50V2YOLOv9

More Related Videos

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

Related Experiment Videos

Last Updated: Jul 1, 2026

Influence of Hybrid Perovskite Fabrication Methods on Film Formation, Electronic Structure, and Solar Cell Performance
11:38

Influence of Hybrid Perovskite Fabrication Methods on Film Formation, Electronic Structure, and Solar Cell Performance

Published on: February 27, 2017

19.0K
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

Area of Science:

  • Materials Science
  • Renewable Energy
  • Artificial Intelligence

Background:

  • Perovskite solar cells (PSCs) are promising for next-generation photovoltaics due to high efficiency and low-cost fabrication potential.
  • Structural defects in formamidinium lead iodide (FAPbI3) perovskite films significantly reduce PSC efficiency and long-term stability.
  • Current defect characterization methods using scanning electron microscopy (SEM) are time-consuming and subjective, hindering scalable quality control.

Purpose of the Study:

  • To develop and evaluate a multi-model deep learning framework for automated classification of critical defects in mixed-dimensionality FAPbI3 perovskite films.
  • To benchmark the performance of different deep learning architectures (ResNet50V2, DenseNet169, YOLOv9) for defect detection and classification.
  • To demonstrate the practical applicability of the developed framework for real-time quality control in PSC manufacturing.

Main Methods:

  • A multi-model deep learning framework was proposed, incorporating ResNet50V2, DenseNet169 for high-accuracy classification, and YOLOv9 for real-time detection.
  • The framework was trained on 2,380 SEM images of FAPbI3 perovskite films, targeting five defect types: pure 3D perovskite, FAPbI3 excess, pinholes, 3D-2D mixed perovskite, and 3D-2D mixed perovskite with pinholes.
  • Data augmentation and transfer learning techniques were utilized to address dataset scarcity and enhance model robustness.

Main Results:

  • ResNet50V2 and DenseNet169 achieved high test accuracy (96.7%) and weighted F1-score (0.966) for defect classification.
  • YOLOv9 demonstrated significant computational efficiency, with an 8-minute training time, although with moderate accuracy (45.0%).
  • The trained models were deployed as an interactive Streamlit-based web application for practical laboratory and industrial use.

Conclusions:

  • The proposed deep learning framework enables precise and automated identification of morphological defects in perovskite films.
  • The study highlights the potential of AI-driven defect analysis to accelerate the optimization and commercialization of PSC technologies.
  • The developed framework offers a scalable solution for quality control in PSC manufacturing, improving efficiency and reliability.