EUVIMEDScopri EUVIMED
Open access · CC BY-NC 3.0

Unsupervised and few-shot segmentation in photovoltaic electroluminescence images for defect detection via a novel enhanced iterative autoencoder with simple implementation

Ye Lin, Pingyang Sun, Rongcheng Wu, Shu Geng, Man Lung Yiu, Zhidong Li, Fang Chen, Yu Gao, Mingzhe Wang, Kaiwen Sun, Xiaojing Hao

Energy & Environmental Science · 2026 · 19 (2) · 513-526

DOI: 10.1039/d5ee05042a ↗

At a glance

Journal article in Energy & Environmental Science, 2026. Written by Ye Lin and 10 co-authors. Cited 3 times so far (Crossref); 63 references. The full text is freely available (open access, CC BY-NC 3.0). Funded by: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Fundamental Research Funds for the Central Universities.

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

PVEL images are particularly valuable for ML-based automated fault detection. A novel EI-AE incorporates an iterative mechanism into the conventional AE framework, providing simple, effective unsupervised pixel-level defect segmentation.

Funding

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Fundamental Research Funds for the Central Universities

Cite

APA

Lin, Y., Sun, P., Wu, R., Geng, S., Yiu, M. L., Li, Z., Chen, F., Gao, Y., Wang, M., Sun, K., & Hao, X. (2026). Unsupervised and few-shot segmentation in photovoltaic electroluminescence images for defect detection via a novel enhanced iterative autoencoder with simple implementation. Energy & Environmental Science, 19(2), 513-526. https://doi.org/10.1039/d5ee05042a

Vancouver

Lin Y, Sun P, Wu R, Geng S, Yiu ML, Li Z, et al. Unsupervised and few-shot segmentation in photovoltaic electroluminescence images for defect detection via a novel enhanced iterative autoencoder with simple implementation. Energy & Environmental Science. 2026;19(2):513-526. doi:10.1039/d5ee05042a

BibTeX
@article{Lin2026,
  author = {Lin, Ye and Sun, Pingyang and Wu, Rongcheng and Geng, Shu and Yiu, Man Lung and Li, Zhidong and Chen, Fang and Gao, Yu and Wang, Mingzhe and Sun, Kaiwen and Hao, Xiaojing},
  title = {Unsupervised and few-shot segmentation in photovoltaic electroluminescence images for defect detection via a novel enhanced iterative autoencoder with simple implementation},
  journal = {Energy & Environmental Science},
  year = {2026},
  volume = {19},
  number = {2},
  pages = {513--526},
  doi = {10.1039/d5ee05042a}
}
Start for free →