Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 15, issue 3
Articles | Volume 15, issue 3
https://doi.org/10.5194/amt-15-797-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-15-797-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 15, issue 3
Research article
 | 
14 Feb 2022
Research article |  | 14 Feb 2022

Applying self-supervised learning for semantic cloud segmentation of all-sky images

Yann Fabel, Bijan Nouri, Stefan Wilbert, Niklas Blum, Rudolph Triebel, Marcel Hasenbalg, Pascal Kuhn, Luis F. Zarzalejo, and Robert Pitz-Paal

Viewed

Total article views: 5,664 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
3,937 1,592 135 5,664 143 145
  • HTML: 3,937
  • PDF: 1,592
  • XML: 135
  • Total: 5,664
  • BibTeX: 143
  • EndNote: 145
Views and downloads (calculated since 19 Mar 2021)
Cumulative views and downloads (calculated since 19 Mar 2021)

Viewed (geographical distribution)

Total article views: 5,664 (including HTML, PDF, and XML) Thereof 5,629 with geography defined and 35 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 14 Apr 2026
Download
Short summary
This work presents a new approach to exploit unlabeled image data from ground-based sky observations to train neural networks. We show that our model can detect cloud classes within images more accurately than models trained with conventional methods using small, labeled datasets only. Novel machine learning techniques as applied in this work enable training with much larger datasets, leading to improved accuracy in cloud detection and less need for manual image labeling.
Read more
Share