Next Article in Journal
RASD: Relation Aware Spectral Decoupling Attention Network for Knowledge Graph Reasoning
Previous Article in Journal
Design and Optimization Analysis of a Multipoint Flexible Adhesive Support Structure for a Spaceborne Rectangular Curved Prism
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 15
Issue 16
10.3390/app15169051
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR)

by
Wuyang Yan
1,
Xiong Xiong
1,2,*,
Xinyuan Xia
3,
Yanchao Zhang
3 and
Xiaojie Guo
4
1
Information and Systems Science Institute, Nanjing University of Information Science and Technology, Nanjing 210044, China
2
Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, China
3
School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
4
School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2025, 15(16), 9051; https://doi.org/10.3390/app15169051 (registering DOI)
Submission received: 14 July 2025 / Revised: 10 August 2025 / Accepted: 15 August 2025 / Published: 16 August 2025
Versions Notes

Abstract

Solar irradiance, which is closely influenced by cloud cover, significantly affects photovoltaic (PV) power generation efficiency. To improve cloud type recognition without relying on labeled data tasks, this paper proposes a self-supervised cloud classification method based on patch rotation prediction. In the Pre-training stage, unlabeled ground-based cloud images are augmented through blockwise rotation, and high-level semantic representations are learned via a Swin Transformer encoder. In the fine-tuning stage, these representations are adapted to the cloud classification task using labeled data. Experimental results show that our method achieves 96.61% accuracy on the RCCD and 90.18% on the SWIMCAT dataset, outperforming existing supervised and self-supervised baselines by a clear margin. These results demonstrate the effectiveness and robustness of the proposed approach, especially in data-scarce scenarios. This research provides valuable technical support for improving the prediction of solar irradiance and optimizing PV power generation efficiency.
Keywords: photovoltaic power; solar irradiance; cloud classification; self-supervised; raindrop patch rotation photovoltaic power; solar irradiance; cloud classification; self-supervised; raindrop patch rotation

Share and Cite

MDPI and ACS Style

Yan, W.; Xiong, X.; Xia, X.; Zhang, Y.; Guo, X. Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR). Appl. Sci. 2025, 15, 9051. https://doi.org/10.3390/app15169051

AMA Style

Yan W, Xiong X, Xia X, Zhang Y, Guo X. Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR). Applied Sciences. 2025; 15(16):9051. https://doi.org/10.3390/app15169051

Chicago/Turabian Style

Yan, Wuyang, Xiong Xiong, Xinyuan Xia, Yanchao Zhang, and Xiaojie Guo. 2025. "Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR)" Applied Sciences 15, no. 16: 9051. https://doi.org/10.3390/app15169051

APA Style

Yan, W., Xiong, X., Xia, X., Zhang, Y., & Guo, X. (2025). Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR). Applied Sciences, 15(16), 9051. https://doi.org/10.3390/app15169051

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop