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.
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.
the Creative Commons Attribution 4.0 License.
Research article
| 
14 Feb 2022
Research article |
| 14 Feb 2022
| 14 Feb 2022
Applying self-supervised learning for semantic cloud segmentation of all-sky images
Institute of Solar Research, German Aerospace Center (DLR), 04001 Almeria, Spain
Bijan Nouri
CORRESPONDING AUTHOR
Institute of Solar Research, German Aerospace Center (DLR), 04001 Almeria, Spain
Stefan Wilbert
Institute of Solar Research, German Aerospace Center (DLR), 04001 Almeria, Spain
Niklas Blum
Institute of Solar Research, German Aerospace Center (DLR), 04001 Almeria, Spain
Rudolph Triebel
Institute of Robotics and Mechatronics, German Aerospace Center (DLR), 82234 Oberpfaffenhofen-Weßling, Germany
Chair of Computer Vision and Artificial Intelligence, Technical University of Munich, 85748 Garching, Germany
Marcel Hasenbalg
Pascal Kuhn
EnBW Energie Baden-Württemberg AG, 76131 Karlsruhe, Germany
Luis F. Zarzalejo
Renewable Energy Division, CIEMAT Energy Department, 28040 Madrid, Spain
Robert Pitz-Paal
Institute of Solar Research, German Aerospace Center (DLR), 51147 Cologne, Germany
Viewed
Total article views: 3,464 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 19 Mar 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,138 | 1,239 | 87 | 3,464 | 87 | 59 |
- HTML: 2,138
- PDF: 1,239
- XML: 87
- Total: 3,464
- BibTeX: 87
- EndNote: 59
Total article views: 2,114 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 14 Feb 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,377 | 677 | 60 | 2,114 | 70 | 52 |
- HTML: 1,377
- PDF: 677
- XML: 60
- Total: 2,114
- BibTeX: 70
- EndNote: 52
Total article views: 1,350 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 19 Mar 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 761 | 562 | 27 | 1,350 | 17 | 7 |
- HTML: 761
- PDF: 562
- XML: 27
- Total: 1,350
- BibTeX: 17
- EndNote: 7
Viewed (geographical distribution)
Total article views: 3,464 (including HTML, PDF, and XML)
Thereof 3,324 with geography defined
and 140 with unknown origin.
Total article views: 2,114 (including HTML, PDF, and XML)
Thereof 2,002 with geography defined
and 112 with unknown origin.
Total article views: 1,350 (including HTML, PDF, and XML)
Thereof 1,322 with geography defined
and 28 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
26 citations as recorded by crossref.
- Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems Y. Fabel et al. 10.1002/solr.202300808
- Improved RepVGG ground-based cloud image classification with attention convolution C. Shi et al. 10.5194/amt-17-979-2024
- Open-source sky image datasets for solar forecasting with deep learning: A comprehensive survey Y. Nie et al. 10.1016/j.rser.2023.113977
- Innovative cloud quantification: deep learning classification and finite-sector clustering for ground-based all-sky imaging J. Luo et al. 10.5194/amt-17-3765-2024
- Analyzing Spatial Variations of Cloud Attenuation by a Network of All-Sky Imagers N. Blum et al. 10.3390/rs14225685
- Short-term forecast of solar irradiance components using an alternative mathematical approach for the identification of cloud features M. Peña-Cruz et al. 10.1016/j.renene.2024.121691
- Detection of clouds in multiple wind velocity fields using ground-based infrared sky images G. Terrén-Serrano & M. Martínez-Ramón 10.1016/j.knosys.2023.110628
- Segmentation and Classification of Individual Clouds in Images Captured with Horizon-Aimed Cameras for Nowcasting of Solar Irradiance Absorption B. Martins et al. 10.4236/ajcc.2023.124027
- Obscurant Segmentation in Long Wave Infrared Images Using GLCM Textures M. Abuhussein & A. Robinson 10.3390/jimaging8100266
- CloudFU-Net: A Fine-Grained Segmentation Method for Ground-Based Cloud Images Based on an Improved Encoder–Decoder Structure C. Shi et al. 10.1109/TGRS.2024.3389089
- Solar Irradiance Ramp Forecasting Based on All-Sky Imagers S. Logothetis et al. 10.3390/en15176191
- Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification E. Gyasi & P. Swarnalatha 10.3390/atmos14020280
- Cloud Segmentation, Validation of Weather Data, and Precipitation Prediction Using Machine Learning Algorithms N. Rajendiran et al. 10.1007/s13369-023-08611-0
- Benchmarking of solar irradiance nowcast performance derived from all-sky imagers S. Logothetis et al. 10.1016/j.renene.2022.08.127
- Self-Supervised Learning for High-Resolution Remote Sensing Images Change Detection With Variational Information Bottleneck C. Wang et al. 10.1109/JSTARS.2023.3288294
- Aerosol Optical Properties and Type Retrieval via Machine Learning and an All-Sky Imager S. Logothetis et al. 10.3390/atmos14081266
- Image segmentation for thin structures using a zero-shot learner T. Siriborvornratanakul 10.1007/s41870-024-02215-z
- Validation of a camera-based intra-hour irradiance nowcasting model using synthetic cloud data P. Gregor et al. 10.5194/amt-16-3257-2023
- Assessment of cloudless-to-cloud transition zone from downwelling longwave irradiance measurements J. González et al. 10.1016/j.atmosres.2023.106657
- Probabilistic solar nowcasting based on all-sky imagers B. Nouri et al. 10.1016/j.solener.2023.01.060
- Blending of a novel all sky imager model with persistence and a satellite based model for high-resolution irradiance nowcasting N. Straub et al. 10.1016/j.solener.2024.112319
- Cloud Detection and Tracking Based on Object Detection with Convolutional Neural Networks J. Carballo et al. 10.3390/a16100487
- Probabilistic end-to-end irradiance forecasting through pre-trained deep learning models using all-sky-images S. Chaaraoui et al. 10.5194/asr-20-129-2024
- A Hybrid Solar Irradiance Nowcasting Approach: Combining All Sky Imager Systems and Persistence Irradiance Models for Increased Accuracy B. Nouri et al. 10.1002/solr.202100442
- Cloud height measurement by a network of all-sky imagers N. Blum et al. 10.5194/amt-14-5199-2021
- Contrastive Learning vs. Self-Learning vs. Deformable Data Augmentation in Semantic Segmentation of Medical Images H. Arabi & H. Zaidi 10.1007/s10278-024-01159-x
23 citations as recorded by crossref.
- Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems Y. Fabel et al. 10.1002/solr.202300808
- Improved RepVGG ground-based cloud image classification with attention convolution C. Shi et al. 10.5194/amt-17-979-2024
- Open-source sky image datasets for solar forecasting with deep learning: A comprehensive survey Y. Nie et al. 10.1016/j.rser.2023.113977
- Innovative cloud quantification: deep learning classification and finite-sector clustering for ground-based all-sky imaging J. Luo et al. 10.5194/amt-17-3765-2024
- Analyzing Spatial Variations of Cloud Attenuation by a Network of All-Sky Imagers N. Blum et al. 10.3390/rs14225685
- Short-term forecast of solar irradiance components using an alternative mathematical approach for the identification of cloud features M. Peña-Cruz et al. 10.1016/j.renene.2024.121691
- Detection of clouds in multiple wind velocity fields using ground-based infrared sky images G. Terrén-Serrano & M. Martínez-Ramón 10.1016/j.knosys.2023.110628
- Segmentation and Classification of Individual Clouds in Images Captured with Horizon-Aimed Cameras for Nowcasting of Solar Irradiance Absorption B. Martins et al. 10.4236/ajcc.2023.124027
- Obscurant Segmentation in Long Wave Infrared Images Using GLCM Textures M. Abuhussein & A. Robinson 10.3390/jimaging8100266
- CloudFU-Net: A Fine-Grained Segmentation Method for Ground-Based Cloud Images Based on an Improved Encoder–Decoder Structure C. Shi et al. 10.1109/TGRS.2024.3389089
- Solar Irradiance Ramp Forecasting Based on All-Sky Imagers S. Logothetis et al. 10.3390/en15176191
- Cloud-MobiNet: An Abridged Mobile-Net Convolutional Neural Network Model for Ground-Based Cloud Classification E. Gyasi & P. Swarnalatha 10.3390/atmos14020280
- Cloud Segmentation, Validation of Weather Data, and Precipitation Prediction Using Machine Learning Algorithms N. Rajendiran et al. 10.1007/s13369-023-08611-0
- Benchmarking of solar irradiance nowcast performance derived from all-sky imagers S. Logothetis et al. 10.1016/j.renene.2022.08.127
- Self-Supervised Learning for High-Resolution Remote Sensing Images Change Detection With Variational Information Bottleneck C. Wang et al. 10.1109/JSTARS.2023.3288294
- Aerosol Optical Properties and Type Retrieval via Machine Learning and an All-Sky Imager S. Logothetis et al. 10.3390/atmos14081266
- Image segmentation for thin structures using a zero-shot learner T. Siriborvornratanakul 10.1007/s41870-024-02215-z
- Validation of a camera-based intra-hour irradiance nowcasting model using synthetic cloud data P. Gregor et al. 10.5194/amt-16-3257-2023
- Assessment of cloudless-to-cloud transition zone from downwelling longwave irradiance measurements J. González et al. 10.1016/j.atmosres.2023.106657
- Probabilistic solar nowcasting based on all-sky imagers B. Nouri et al. 10.1016/j.solener.2023.01.060
- Blending of a novel all sky imager model with persistence and a satellite based model for high-resolution irradiance nowcasting N. Straub et al. 10.1016/j.solener.2024.112319
- Cloud Detection and Tracking Based on Object Detection with Convolutional Neural Networks J. Carballo et al. 10.3390/a16100487
- Probabilistic end-to-end irradiance forecasting through pre-trained deep learning models using all-sky-images S. Chaaraoui et al. 10.5194/asr-20-129-2024
3 citations as recorded by crossref.
- A Hybrid Solar Irradiance Nowcasting Approach: Combining All Sky Imager Systems and Persistence Irradiance Models for Increased Accuracy B. Nouri et al. 10.1002/solr.202100442
- Cloud height measurement by a network of all-sky imagers N. Blum et al. 10.5194/amt-14-5199-2021
- Contrastive Learning vs. Self-Learning vs. Deformable Data Augmentation in Semantic Segmentation of Medical Images H. Arabi & H. Zaidi 10.1007/s10278-024-01159-x
Latest update: 13 Dec 2024
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.
This work presents a new approach to exploit unlabeled image data from ground-based sky...
