remotesensing-logo

Journal Browser

Journal Browser

Deep Learning-Based Cloud Detection and Removal for Remote Sensing Images

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: 31 August 2025 | Viewed by 407

Special Issue Editors

College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Interests: deep learning; semi-supervision; cloud detection; cloud removal; target detection; temporal-spatial data fusion

E-Mail Website
Guest Editor
School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
Interests: deep learning; computer vision; remote sensing; semantic segmentation; transformer
Special Issues, Collections and Topics in MDPI journals
Urban Governance and Design Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China
Interests: computer vision; remote sensing; 3D modeling; urban analytics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor Assistant
College of Computer and Control Engineering, Northeast Forestry University, Harbin, China
Interests: remote sensing; deep learning; cloud removal; road extraction; super-resolution reconstruction

Special Issue Information

Dear Colleagues,

In today’s world, remote sensing images have emerged as indispensable data resources across diverse domains, including urban development planning, environmental surveillance, and agricultural evaluation. Cloud detection and removal in remote sensing imagery, which are fundamental to remote sensing data processing, hold extensive applications and far-reaching implications in multiple sectors.

Urban Development Planning: In the context of urban planning, cloud-free remote sensing images play a crucial role in tracking urban expansion and assessing infrastructure. By eliminating cloud cover from remote sensing data, urban planners can gain a clear and comprehensive view of the layout and evolution of urban buildings, transportation networks, and green spaces. This visual clarity facilitates the formulation of more rational urban development blueprints, the optimization of urban spatial configurations, and the enhancement of urban living conditions, thereby promoting the long-term, healthy development of cities.

Environmental Surveillance: Unobstructed by clouds, remote sensing images are pivotal for achieving a precise and accurate understanding of the Earth's surface environment. For instance, during the continuous monitoring of forest cover dynamics, the presence of clouds in remote sensing images can lead to misjudgments regarding the actual forest acreage. Employing advanced cloud detection and removal algorithms, we can ensure that the data obtained faithfully represent the real-time state of the forest ecosystem. This, in turn, enables the timely detection of deforestation, forest degradation, and other environmental changes, providing a solid foundation for effective environmental protection strategies.

Agricultural Evaluation: Cloud-free remote sensing images are of great value in monitoring crop growth and predicting yields. High-resolution remote sensing data, free from cloud interference, can offer detailed insights into various aspects of crop development, such as growth stages, nutrient deficiencies, and pest infestations. Armed with this information, farmers and agricultural researchers can make well-informed decisions regarding fertilization, irrigation, and pest management. As a result, not only can crop yields be enhanced, but the overall quality of agricultural products can also be improved, contributing to sustainable agricultural development.

In summary, the application of cloud detection and removal techniques in remote sensing images holds vast potential and is of great significance for driving progress in multiple fields. To further advance this field, we intend to compile a Special Issue on remote sensing image cloud detection and removal. We sincerely invite experts and scholars from around the world to contribute via sharing their latest research findings and cutting-edge developments in this area.

We welcome the submission of papers related to the following topics:

  • Algorithms for remote sensing image cloud detection;
  • Techniques for remote sensing image cloud removal;
  • Deep-learning-based approaches for cloud detection and removal;
  • Cloud processing in multispectral and hyperspectral remote sensing images;
  • Spatio-temporal analysis of cloud-contaminated remote sensing data;
  • The fusion of cloud-free remote sensing data with other data sources (e.g., LiDAR, ground-based observations);
  • Cloud-free remote sensing applications in emerging interdisciplinary fields such as climate-smart agriculture and urban ecological planning;
  • The development and application of real-time cloud detection and removal systems for dynamic remote sensing monitoring scenarios.

Dr. Jun Li
Dr. Libo Wang
Dr. Wufan Zhao
Guest Editors

Dr. Yang Du
Guest Editor Assistant

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 submissions that pass pre-check are 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 2700 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.

Keywords

  • remote sensing
  • cloud detection
  • cloud removal
  • image restoration
  • data fusion
  • pattern recognition

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 5107 KiB  
Article
MFAFNet: Multi-Scale Feature Adaptive Fusion Network Based on DeepLab V3+ for Cloud and Cloud Shadow Segmentation
by Yijia Feng, Zhiyong Fan, Ying Yan, Zhengdong Jiang and Shuai Zhang
Remote Sens. 2025, 17(7), 1229; https://doi.org/10.3390/rs17071229 - 30 Mar 2025
Viewed by 221
Abstract
The accurate segmentation of clouds and cloud shadows is crucial in meteorological monitoring, climate change research, and environmental management. However, existing segmentation models often suffer from issues such as losing fine details, blurred boundaries, and false positives or negatives. To address these challenges, [...] Read more.
The accurate segmentation of clouds and cloud shadows is crucial in meteorological monitoring, climate change research, and environmental management. However, existing segmentation models often suffer from issues such as losing fine details, blurred boundaries, and false positives or negatives. To address these challenges, this paper proposes an improved model based on DeepLab v3+. First, to enhance the model’s ability to extract fine-grained features, a Hybrid Strip Pooling Module (HSPM) is introduced in the encoding stage, effectively preserving local details and reducing information loss. Second, a Global Context Attention Module (GCAM) is incorporated into the Atrous Spatial Pyramid Pooling (ASPP) module to establish pixel-wise long-range dependencies, thereby effectively integrating global semantic information. In the decoding stage, a Three-Branch Adaptive Feature Fusion Module (TB-AFFM) is designed to merge multi-scale features from the backbone network and ASPP. Finally, an innovative loss function is employed in the experiments, significantly improving the accuracy of cloud and cloud shadow segmentation. Experimental results demonstrate that the proposed model outperforms existing methods in cloud and cloud shadow segmentation tasks, achieving more precise segmentation performance. Full article
Show Figures

Figure 1

Back to TopTop