Special Issue "Deep Learning-Based Cloud Detection for Remote Sensing Images"
Deadline for manuscript submissions: 15 November 2021.
The number of Earth observation satellites is growing exponentially. However, satellite images acquired by optical sensors can be affected significantly by the presence of clouds, which can be considered as a source of uncertainty, when the objective is to study the surface, or as the signal, when studying the atmosphere. In any case, automatic detection of clouds becomes mandatory for the operational exploitation of Earth observation satellite images and further retrieval of derived bio-physical products. Moreover, classification of cloud types is also gaining importance since clouds represent one of the bigger sources of uncertainty in climate projections.
Despite the efforts in developing robust and reliable cloud detection algorithms, there are still significant deficiencies in their overall accuracy, notably false detection over bright surfaces, omissions of optically thin clouds or confusion in snow/ice and cloud classification. Standard machine learning algorithms have provided promising results in this field but they do not efficiently cope with some aspects of cloud detection in satellite images. Deep learning-based algorithms could address key challenges that require urgent attention in cloud detection for current and upcoming satellites. Novel deep learning architectures and training procedures are required to better capture the spatial and spectral properties of Earth observation satellite images. Deep learning models excel exploiting the wealth of information contained in available labeled datasets, however, the generation of reference and public multi-mission datasets of satellite images for cloud detection is a key requirement that has to be better handled by the community.
In short, this Special Issue will review the state of the art in deep learning-based cloud detection algorithms for remote sensing images. Articles covering recent research about the following topics are invited for this Special Issue:
- New machine learning algorithms based on deep architectures for cloud detection.
- Cloud detection applications in multispectral and high-spatial resolution sensors.
- Deep learning-based cloud detection algorithms exploiting the temporal information.
- Cloud type classification.
- Cloud and cloud shadows removal from optical satellite images.
- Transfer learning approaches across similar satellite sensors.
- Improving domain adaptation among different satellites for cloud detection.
- Relevant datasets particularly interesting for cloud detection.
- Intelligent and active data labeling methods for cloud detection.
- Search and retrieval of cloud-free satellite images.
Prof. Dr. Luis Gómez-Chova
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- Cloud detection
- Cloud removal
- Cloud shadows
- Cloud type classification
- Earth observation satellites
- Multispectral images
- Image processing
- Machine learning
- Deep learning
- Transfer learning