Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation
Abstract Remote sensing images are indispensable for continuous environmental monitoring and Earth observations. However, cloud occlusion can severely degrade image quality, posing a significant challenge for the accurate extraction of ground information. Existing cloud removal techniques often suff...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87296-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862321108221952 |
|---|---|
| author | Qingwei Tong Leiguang Wang Qinling Dai Chen Zheng Fangrong Zhou |
| author_facet | Qingwei Tong Leiguang Wang Qinling Dai Chen Zheng Fangrong Zhou |
| author_sort | Qingwei Tong |
| collection | DOAJ |
| description | Abstract Remote sensing images are indispensable for continuous environmental monitoring and Earth observations. However, cloud occlusion can severely degrade image quality, posing a significant challenge for the accurate extraction of ground information. Existing cloud removal techniques often suffer from incomplete cloud removal, artifacts, and color distortions. Owing to the scarcity of sequential data, the effective utilization of temporal information to enhance cloud removal performance poses a challenge. Therefore, we propose a cloud removal method based on cloud evolution simulation. This method is applicable to all paired cloud datasets, enabling the construction of cloud evolution time-series in the absence of actual temporal information. We embed temporal information from the sequence into the Temporal U-Net to achieve more accurate cloud predictions. We conducted extensive experiments on RICE and T-CLOUD datasets. The results demonstrate that our approach significantly improves the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) compared with existing methods. |
| format | Article |
| id | doaj-art-94e84f8ac92f4e95b79b2010565ba71f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-94e84f8ac92f4e95b79b2010565ba71f2025-02-09T12:32:37ZengNature PortfolioScientific Reports2045-23222025-02-0115111010.1038/s41598-025-87296-xEnhanced cloud removal via temporal U-Net and cloud cover evolution simulationQingwei Tong0Leiguang Wang1Qinling Dai2Chen Zheng3Fangrong Zhou4College of Big Data and Intelligent Engineering, Southwest Forestry UniversityCollege of Landscape Architecture and Horticulture, Southwest Forestry UniversityCollege of Art and Design, Southwest Forestry UniversitySchool of Mathematics and Statistics, Henan University Joint Laboratory of power remote sensing technology(Electric Power Research Institute, Yunnan Power Grid Company ltd., China Southern Power Grid)Abstract Remote sensing images are indispensable for continuous environmental monitoring and Earth observations. However, cloud occlusion can severely degrade image quality, posing a significant challenge for the accurate extraction of ground information. Existing cloud removal techniques often suffer from incomplete cloud removal, artifacts, and color distortions. Owing to the scarcity of sequential data, the effective utilization of temporal information to enhance cloud removal performance poses a challenge. Therefore, we propose a cloud removal method based on cloud evolution simulation. This method is applicable to all paired cloud datasets, enabling the construction of cloud evolution time-series in the absence of actual temporal information. We embed temporal information from the sequence into the Temporal U-Net to achieve more accurate cloud predictions. We conducted extensive experiments on RICE and T-CLOUD datasets. The results demonstrate that our approach significantly improves the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) compared with existing methods.https://doi.org/10.1038/s41598-025-87296-xRemote sensing imageCloud removalCloud cover evolution (CCE) moduleTemporal U-NetResidual learning |
| spellingShingle | Qingwei Tong Leiguang Wang Qinling Dai Chen Zheng Fangrong Zhou Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation Scientific Reports Remote sensing image Cloud removal Cloud cover evolution (CCE) module Temporal U-Net Residual learning |
| title | Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation |
| title_full | Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation |
| title_fullStr | Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation |
| title_full_unstemmed | Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation |
| title_short | Enhanced cloud removal via temporal U-Net and cloud cover evolution simulation |
| title_sort | enhanced cloud removal via temporal u net and cloud cover evolution simulation |
| topic | Remote sensing image Cloud removal Cloud cover evolution (CCE) module Temporal U-Net Residual learning |
| url | https://doi.org/10.1038/s41598-025-87296-x |
| work_keys_str_mv | AT qingweitong enhancedcloudremovalviatemporalunetandcloudcoverevolutionsimulation AT leiguangwang enhancedcloudremovalviatemporalunetandcloudcoverevolutionsimulation AT qinlingdai enhancedcloudremovalviatemporalunetandcloudcoverevolutionsimulation AT chenzheng enhancedcloudremovalviatemporalunetandcloudcoverevolutionsimulation AT fangrongzhou enhancedcloudremovalviatemporalunetandcloudcoverevolutionsimulation |