Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs

Print Special Issue Flyer
Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A Special Issue of Remote Sensing (ISSN 2072-4292) belonging to the section "AI Remote Sensing".

Deadline for manuscript submissions: closed (31 August 2026) | Viewed by 23013

Share This Special Issue

Editors

Dr. Xin Zhang

E-Mail Website
Guest Editor

Radar Technology Research Institute, Beijing Institute of Technology, Beijing 100081, China
Interests: intelligent radar target detection and recognition; intelligent interpretation of remote sensing images

Dr. Xueyao Hu

E-Mail Website
Guest Editor

Radar Technology Research Institute, Beijing Institute of Technology, Beijing 100081, China
Interests: target detection and recognition

Prof. Dr. Yang Li

E-Mail Website
Guest Editor

Radar Technology Research Institute, Beijing Institute of Technology, Beijing 100081, China
Interests: target detection and recognition

Prof. Dr. Fernando José Aguilar

E-Mail Website
Guest Editor

Engineering Department, University of Almería, Carretera de Sacramento s/n, La Cañada de San Urbano, 04120 Almería, Spain
Interests: forest monitoring; OBIA; LiDAR; UAV; machine learning; optical satellite imagery; data fusion
Special Issues, Collections and Topics in MDPI journals

Dr. Muhammad Yasir

E-Mail Website
Guest Editor

College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China
Interests: computer vision remote sensing; deep learning; image processing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Remote sensing image interpretation, which is pivotal for environment, resource, and target monitoring, has experienced a profound transformation with the infusion of deep learning techniques. Deep learning algorithms possess the outstanding capacity to extract intricate patterns and features from extensive remote sensing image datasets, thereby facilitating more precise and efficient interpretation than conventional approaches. Concurrently, with the maturation of sensor technologies, a wealth of multi-source remote sensing image data have emerged, including those from radar, optical, and other sensors. These diverse data sources offer powerful technical means for remote sensing image interpretation.

This Special Issue unfolds methodically around several crucial and significant goals. Firstly, in terms of promoting the exploration of new tasks in remote sensing image interpretation, researchers are actively encouraged to break the routine. Nowadays, merely sticking to conventional recognition and detection tasks can no longer meet the development needs. We aim to leverage the powerful feature learning and data processing capabilities of deep learning technology to explore remote sensing image interpretation in new tasks and scenarios, thus broadening application fields and guiding research directions, enabling academic achievements to better serve practical demands. Secondly, reflecting on existing deep learning techniques is of great importance. Many traditional deep learning models proposed are rather general purpose, overlooking the differences in resolution, target characteristics, etc., among different source remote sensing images. Therefore, urging a rethinking helps develop improved architectures that better fit the unique nature of remote sensing images, allowing for more precise image analysis. Finally, the focus is on dissecting the limitations of deep learning technology in specific scenarios. When faced with thorny situations like imbalanced samples, weak targets, and complex backgrounds, the performance of models often falls short. We encourage researchers to propose innovative solutions to further enhance the interpretation performance of existing methods in these scenarios.

Articles may address, but are not limited to, the following topics:

Multi-source remote sensing image processing;
Remote sensing image generation;
Multimodal remote sensing image interpretation model;
Target characteristic analysis;
Radar signal processing；
New task dataset and benchmark for remote sensing image interpretation.

Dr. Xin Zhang
Dr. Xueyao Hu
Prof. Dr. Yang Li
Prof. Dr. Fernando José Aguilar
Dr. Muhammad Yasir
Guest Editors

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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized 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

multi-source remote sensing image processing
remote sensing image generation
multimodal remote sensing image interpretation model
target characteristic analysis
radar signal processing
new task dataset and benchmark for remote sensing image interpretation

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.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (13 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

15 pages, 8817 KB

Open AccessArticle

TSAR-Net: Transfer-Enhanced Local-to-Global Representation Learning for Micro-Doppler Classification of Small Aerial Targets

by Yuxian Sun, Yuanshuai Li, Jiaxiang Zhang, Huayu Fan and Yuanyuan Song

Remote Sens. 2026, 18(19), 3442; https://doi.org/10.3390/rs18193442 - 8 Oct 2026

Viewed by 134

Abstract

Radar remote sensing provides an effective means of analyzing target characteristics for low-altitude surveillance, and the rapid growth and misuse of drones highlight the need for efficient classification of small aerial targets such as drones and birds. Micro-motions, such as rotor rotation or wing flapping, induce characteristic frequency shifts in radar echoes known as micro-Doppler effects. These radar-derived features provide essential structural and kinematic information for deep-learning-based target classification. However, in practical applications, existing methods still suffer from inadequate micro-Doppler feature extraction capability and rarely account for small-sample scenarios, both of which limit their classification performance. To address these challenges, this article proposes a transfer learning and self-attention enhanced ResNet50 (TSAR-Net), which combines transferred hierarchical convolutional features with multi-head self-attention to jointly exploit local and global time–frequency characteristics. Furthermore, to alleviate the small-sample classification problem, we introduce a projection-based TSAR-Net (PTSAR-Net), which maps the 2048-dimensional pooled feature through a 512-dimensional layer to a compact 128-dimensional representation for limited-label classification. On the measured DIAT-

μ

SAT dataset, TSAR-Net achieves 99.59% accuracy, compared with 96.71% for VGG19, an improvement of 2.88 percentage points. With five training samples per class, PTSAR-Net achieves 81.14% accuracy, compared with 70.72% for TSAR-Net, an improvement of 10.42 percentage points. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

36 pages, 34812 KB

Open AccessArticle

Triple-Level Topology Awareness Using Hypergraph for Marine Ship Surveillance from SAR Imagery

by Rui Zhu and Tianwen Zhang

Remote Sens. 2026, 18(19), 3268; https://doi.org/10.3390/rs18193268 - 22 Sep 2026

Viewed by 266

Abstract

Marine ship surveillance from synthetic aperture radar (SAR) imagery is extensively studied. Still, previous methods may not fully capture high-order topological relationships, which can limit performance in complex scenarios. To this end, we propose a triple-level topology awareness (TLTA) framework using hypergraphs for effective SAR marine ship surveillance. TLTA dynamically captures higher-order dependencies in latent spaces by hypergraph convolution, addressing a limitation of prior techniques that rely solely on pairwise correlation analysis. TLTA is implemented at three levels—input-level, feature-level, and proposal-level—to obtain gradually enhanced feature representations, known as i-LTA, f-LTA, and p-LTA. i-LTA designs a super-pixel segmentation module (SPSM) to yield compact and semantically similar regions through an efficient iterative clustering, and the resulting regions are used for super-pixel hypergraph construction (SP-HGC) to produce features rich in spatial topology relationships at the input level, and finally, a cross-attention collaborative network (CACN) is constructed to aggregate high-order and low-order features to achieve a synergistic integration of topological structures and key details. f-LTA explores topology awareness in the backbone feature extraction, mainly through feature-adaptive hypergraph construction (FA-HGC), vertex-level feature self-attention (VL-FSA), and edge-level feature self-attention (EL-FSA), to enable comprehensive modeling of complex inter-patch dependencies beyond simplistic pairwise interactions. p-LTA leverages a proposal prediction network (PPN) to yield positive/negative proposals for proposal-guided hypergraph construction (PG-HGC), and then leverages instance-level spatial priors to ensure the topology interactions between feature subsets. Experimental results reveal the competitive performance of TLTA, achieving AP values of 77.9% and 76.4% on SSDD and HRSID, respectively, and demonstrate the efficacy of each strategy. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

27 pages, 3768 KB

Open AccessArticle

Multi-Stage Aggregation CNN–Transformer Hybrid Architecture for Infrared Small-Target Detection

by Yufei Wei, Lei Chen, Xuehe Zheng and Longyao Liu

Remote Sens. 2026, 18(14), 2309; https://doi.org/10.3390/rs18142309 - 10 Jul 2026

Viewed by 616

Abstract

Infrared small-target detection plays a vital role in applications such as imaging detection and remote sensing. Because infrared small targets are weak and lack distinctive features, they are easily submerged in cluttered backgrounds, which makes their detection challenging. Preserving spatial details, jointly modeling local and global features, and strengthening feature representation are therefore critical to improving detection accuracy and robustness. However, existing methods often fail to fully exploit multi-level feature relationships, struggle to integrate local and global complementary information, and lack mechanisms to compress redundant features while emphasizing salient information. To address these issues, we propose MACT-Net, a network designed specifically for infrared small-target detection. First, a multi-level aggregation encoder–decoder architecture with convolution-enhanced skip connections and multi-scale decoder fusion is employed to progressively abstract and reconstruct features, preserving spatial details and improving multi-scale responsiveness. Second, a CNN–Transformer hybrid feature modeling module is introduced to adaptively capture local textures and global semantic dependencies, enhancing feature representation and discriminative capability. Third, a vector quantization-based feature discretization and representation enhancement mechanism is embedded at the network bottleneck to compress redundant information and emphasize salient features, further improving robustness under low signal-to-noise ratio conditions. We evaluate MACT-Net on three public datasets: SIRST, IRSTD-1K, and NUDT-SIRST. Extensive experimental results confirm that the combination of multi-level aggregation, hybrid feature modeling, and feature discretization mechanisms effectively enhances infrared small-target detection performance. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

19 pages, 5347 KB

Open AccessArticle

FEDM: Feature-Encoding Diffusion Model for Large-Scale SAR Image Inpainting

by Junyu Yang, Wenzheng Wang and Chenwei Deng

Remote Sens. 2026, 18(13), 2116; https://doi.org/10.3390/rs18132116 - 1 Jul 2026

Viewed by 495

Abstract

With the wide application of generative models in the field of SAR image inpainting, inadequate reconstruction quality of scattering characteristics and insufficient global coherence of semantic logic remain the core challenges of such tasks. To address these issues, this paper proposes a Feature-Encoding Diffusion Model (FEDM). Guided by local valid regions, the proposed model accurately learns the microwave backscattering distribution law of ground features through a SAR-specific Variational Auto-Encoder (SAR-VAE), thus improving the reconstruction accuracy of backscattering statistics. Meanwhile, it integrates semantic embedding and cross-attention mechanism to strengthen the semantic constraints of SAR scenes, ensuring the logical rationality of the ground feature layout. With progressive diffusion generation and sliding window strategy, the model achieves high-quality reconstruction with coherent semantics and consistent global spatial structure for large-scale missing regions. Experiments on public datasets including OSdataset, SEN1-2, SRSDD-v1.0 and MRSSC show that the proposed method achieves excellent performance in terms of scattering characteristic reconstruction quality and globally coherent generation of semantic logic, and realizes high-quality SAR image inpainting. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

35 pages, 51987 KB

Open AccessArticle

Structurally Consistent and Grounding-Aware Stagewise Reasoning for Referring Remote Sensing Image Segmentation

by Shan Dong, Jianlin Xie, Liang Chen, He Chen, Baogui Qi and Yunqiu Ge

Remote Sens. 2026, 18(7), 1015; https://doi.org/10.3390/rs18071015 - 28 Mar 2026

Viewed by 1145

Abstract

Referring Remote Sensing Image Segmentation (RRSIS) is a representative multimodal understanding task for remote sensing, which segments designated targets from remote images according to free-form natural language descriptions. However, complex remote sensing characteristics, such as cluttered backgrounds, large-scale variations, small scattered targets and repetitive textures, lead to unstable visual grounding and further spatial grounding drift, resulting in inaccurate segmentation results. Existing approaches typically perform implicit visual–linguistic fusion across encoding and decoding stages, entangling spatial grounding with mask refinement. This tightly coupled formulation lacks explicit structural constraints and is prone to cross-modal ambiguity, especially in complex remote sensing layouts. To address these limitations, we propose a Structurally consistent and Grounding-aware Stagewise Reasoning Framework (SGSRF) that follows a grounding-first, segmentation-second paradigm. The framework decomposes inference into three cascaded stages with progressively imposed structural constraints. First, Cross-modal Consistency Refinement (CCR) lays the foundation for stable spatial grounding by enhancing visual–textual structural alignment via CLIP-based features and Structural Consistency Regularization (SCR), producing well-aligned multimodal representations and reliable grounding cues. Second, Grounding-aware Prompt (GPG) Generation bridges grounding and segmentation by converting aligned representations into complementary sparse and dense prompts, which serve as explicit grounding guidance for the segmentation model. Third, Grounding Modulated Segmentation (GMS) leverages the Segment Anything Model (SAM) to generate fine-grained mask prediction under the joint guidance of prompts and grounding cues, improving spatial grounding stability and robustness to background interference and scale variation. Extensive experiments on three remote sensing benchmarks, namely RefSegRS, RRSIS-D, and RISBench, demonstrate that SGSRF achieves state-of-the-art performance. The proposed stagewise paradigm integrates structural alignment, explicit grounding, and prompt-driven segmentation into a unified framework, providing a practical and robust solution for RRSIS in real-world Earth observation applications. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

25 pages, 20535 KB

Open AccessArticle

DWTF-DETR: A DETR-Based Model for Inshore Ship Detection in SAR Imagery via Dynamically Weighted Joint Time–Frequency Feature Fusion

by Tiancheng Dong, Taoyang Wang, Yuqi Han, Deren Li, Guo Zhang and Yuan Peng

Remote Sens. 2025, 17(19), 3301; https://doi.org/10.3390/rs17193301 - 25 Sep 2025

Cited by 9 | Viewed by 2264

Abstract

Inshore ship detection in synthetic aperture radar (SAR) imagery poses significant challenges due to the high density and diversity of ships. However, low inter-object backscatter contrast and blurred boundaries of docked ships often result in performance degradation for traditional object detection methods, especially under complex backgrounds and low signal-to-noise ratio (SNR) conditions. To address these issues, this paper proposes a novel detection framework, the Dynamic Weighted Joint Time–Frequency Feature Fusion DEtection TRansformer (DETR) Model (DWTF-DETR), specifically designed for SAR-based ship detection in inshore areas. The proposed model integrates a Dual-Domain Feature Fusion Module (DDFM) to extract and fuse features from both SAR images and their frequency-domain representations, enhancing sensitivity to both high- and low-frequency target features. Subsequently, a Dual-Path Attention Fusion Module (DPAFM) is introduced to dynamically weight and fuse shallow detail features with deep semantic representations. By leveraging an attention mechanism, the module adaptively adjusts the importance of different feature paths, thereby enhancing the model’s ability to perceive targets with ambiguous structural characteristics. Experiments conducted on a self-constructed inshore SAR ship detection dataset and the public HRSID dataset demonstrate that DWTF-DETR achieves superior performance compared to the baseline RT-DETR. Specifically, the proposed method improves mAP@50 by 1.60% and 0.72%, and F1-score by 0.58% and 1.40%, respectively. Moreover, comparative experiments show that the proposed approach outperforms several state-of-the-art SAR ship detection methods. The results confirm that DWTF-DETR is capable of achieving accurate and robust detection in diverse and complex maritime environments. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Graphical abstract

32 pages, 6397 KB

Open AccessArticle

Enhancing YOLO-Based SAR Ship Detection with Attention Mechanisms

by Ranyeri do Lago Rocha and Felipe A. P. de Figueiredo

Remote Sens. 2025, 17(18), 3170; https://doi.org/10.3390/rs17183170 - 12 Sep 2025

Cited by 7 | Viewed by 4393

Abstract

This study enhances Synthetic Aperture Radar (SAR) ship detection by integrating attention mechanisms, Bi-Level Routing Attention (BRA), Swin Transformer, and a Convolutional Block Attention Module (CBAM) into state-of-the-art YOLO architectures (YOLOv11 and v12). Addressing challenges like small ship sizes and complex maritime backgrounds in SAR imagery, we systematically evaluate the impact of adding and replacing attention layers at strategic positions within the models. Experiments reveal that replacing the original attention layer at position 4 (C3k2 module) with the CBAM in YOLOv12 achieves optimal performance, attaining an mAP@0.5 of 98.0% on the SAR Ship Dataset (SSD), surpassing baseline YOLOv12 (97.8%) and prior works. The optimized CBAM-enhanced YOLOv12 also reduces computational costs (5.9 GFLOPS vs. 6.5 GFLOPS in the baseline). Cross-dataset validation on the SAR Ship Detection Dataset (SSDD) confirms consistent improvements, underscoring the efficacy of targeted attention-layer replacement for SAR-specific challenges. Additionally, tests on the SADD and MSAR datasets demonstrate that this optimization generalizes beyond ship detection, yielding gains in aircraft detection and multi-class SAR object recognition. This work establishes a robust framework for efficient, high-precision maritime surveillance using deep learning. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

24 pages, 4589 KB

Open AccessArticle

Semantic Segmentation of Clouds and Cloud Shadows Using State Space Models

by Zhixuan Zhang, Ziwei Hu, Min Xia, Ying Yan, Rui Zhang, Shengyan Liu and Tao Li

Remote Sens. 2025, 17(17), 3120; https://doi.org/10.3390/rs17173120 - 8 Sep 2025

Cited by 7 | Viewed by 2153

Abstract

In remote sensing image processing, cloud and cloud shadow detection is of great significance, which can solve the problems of cloud occlusion and image distortion, and provide support for multiple fields. However, the traditional convolutional or Transformer models and the existing studies combining the two have some shortcomings, such as insufficient feature fusion, high computational complexity, and difficulty in taking into account local and long-range dependent information extraction. In order to solve these problems, this paper proposes the MCloud model based on Mamba architecture is proposed, which takes advantage of its linear computational complexity to effectively model long-range dependencies and local features through the coordinated work of state space and convolutional support and the Mamba-convolutional fusion module. Experiments show that MCloud have the leading segmentation performance and generalization ability on multiple datasets, and provides more accurate and efficient solutions for cloud and cloud shadow detection. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

22 pages, 5692 KB

Open AccessArticle

RiceStageSeg: A Multimodal Benchmark Dataset for Semantic Segmentation of Rice Growth Stages

by Jianping Zhang, Tailai Chen, Yizhe Li, Qi Meng, Yanying Chen, Jie Deng and Enhong Sun

Remote Sens. 2025, 17(16), 2858; https://doi.org/10.3390/rs17162858 - 16 Aug 2025

Cited by 3 | Viewed by 3678

Abstract

The accurate identification of rice growth stages is critical for precision agriculture, crop management, and yield estimation. Remote sensing technologies, particularly multimodal approaches that integrate high spatial and hyperspectral resolution imagery, have demonstrated great potential in large-scale crop monitoring. Multimodal data fusion offers complementary and enriched spectral–spatial information, providing novel pathways for crop growth stage recognition in complex agricultural scenarios. However, the lack of publicly available multimodal datasets specifically designed for rice growth stage identification remains a significant bottleneck that limits the development and evaluation of relevant methods. To address this gap, we present RiceStageSeg, a multimodal benchmark dataset captured by unmanned aerial vehicles (UAVs), designed to support the development and assessment of segmentation models for rice growth monitoring. RiceStageSeg contains paired centimeter-level RGB and 10-band multispectral (MS) images acquired during several critical rice growth stages, including jointing and heading. Each image is accompanied by fine-grained, pixel-level annotations that distinguish between the different growth stages. We establish baseline experiments using several state-of-the-art semantic segmentation models under both unimodal (RGB-only, MS-only) and multimodal (RGB + MS fusion) settings. The experimental results demonstrate that multimodal feature-level fusion outperforms unimodal approaches in segmentation accuracy. RiceStageSeg offers a standardized benchmark to advance future research in multimodal semantic segmentation for agricultural remote sensing. The dataset will be made publicly available on GitHub v0.11.0 (accessed on 1 August 2025). Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

23 pages, 7944 KB

Open AccessArticle

BCTDNet: Building Change-Type Detection Networks with the Segment Anything Model in Remote Sensing Images

by Wei Zhang, Jinsong Li, Shuaipeng Wang and Jianhua Wan

Remote Sens. 2025, 17(15), 2742; https://doi.org/10.3390/rs17152742 - 7 Aug 2025

Cited by 2 | Viewed by 1752

Abstract

Observing building changes in remote sensing images plays a crucial role in monitoring urban development and promoting sustainable urbanization. Mainstream change detection methods have demonstrated promising performance in identifying building changes. However, buildings have large intra-class variance and high similarity with other objects, limiting the generalization ability of models in diverse scenarios. Moreover, most existing methods only detect whether changes have occurred but ignore change types, such as new construction and demolition. To address these issues, we present a building change-type detection network (BCTDNet) based on the Segment Anything Model (SAM) to identify newly constructed and demolished buildings. We first construct a dual-feature interaction encoder that employs SAM to extract image features, which are then refined through trainable multi-scale adapters for learning architectural structures and semantic patterns. Moreover, an interactive attention module bridges SAM with a Convolutional Neural Network, enabling seamless interaction between fine-grained structural information and deep semantic features. Furthermore, we develop a change-aware attribute decoder that integrates building semantics into the change detection process via an extraction decoding network. Subsequently, an attribute-aware strategy is adopted to explicitly generate distinct maps for newly constructed and demolished buildings, thereby establishing clear temporal relationships among different change types. To evaluate BCTDNet’s performance, we construct the JINAN-MCD dataset, which covers Jinan’s urban core area over a six-year period, capturing diverse change scenarios. Moreover, we adapt the WHU-CD dataset into WHU-MCD to include multiple types of changing. Experimental results on both datasets demonstrate the superiority of BCTDNet. On JINAN-MCD, BCTDNet achieves improvements of 12.64% in IoU and 11.95% in F1 compared to suboptimal methods. Similarly, on WHU-MCD, it outperforms second-best approaches by 2.71% in IoU and 1.62% in F1. BCTDNet’s effectiveness and robustness in complex urban scenarios highlight its potential for applications in land-use analysis and urban planning. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

25 pages, 17505 KB

Open AccessArticle

A Hybrid Spatio-Temporal Graph Attention (ST D-GAT Framework) for Imputing Missing SBAS-InSAR Deformation Values to Strengthen Landslide Monitoring

by Hilal Ahmad, Yinghua Zhang, Hafeezur Rehman, Mehtab Alam, Zia Ullah, Muhammad Asfandyar Shahid, Majid Khan and Aboubakar Siddique

Remote Sens. 2025, 17(15), 2613; https://doi.org/10.3390/rs17152613 - 28 Jul 2025

Cited by 11 | Viewed by 2800

Abstract

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Graphical abstract

Review

Jump to: Research

37 pages, 27926 KB

Open AccessReview

A Review of Remote Sensing Image Translation Based on Generative Adversarial Networks

by Zhaowei Wang, Futao Wang, Zhenqing Wang, Litao Wang, Tianhao Wang, Xinguang Gu, Yanchao Wang, Luoyao Hao, Ziqi Nie, Haojie Tao, Chengyue Xiong, Jinfeng Zhu and Wenliang Liu

Remote Sens. 2026, 18(19), 3388; https://doi.org/10.3390/rs18193388 - 2 Oct 2026

Viewed by 194

Abstract

Generative adversarial networks (GANs) have become an important approach for translating remote sensing images across sensing modalities, acquisition domains, and degraded observation conditions. This paper reviews 111 studies published between 2018 and 2026 and analyzes the field from three translation perspectives: intra-modal or domain translation, cross-modal translation, and image restoration or completion. The review also examines the use of translated imagery in change detection, object detection, semantic segmentation, and data augmentation. Existing methods are compared in terms of supervision strategy, data pairing, network architecture, feature representation, loss-function design, datasets, and evaluation practice. The literature shows a strong concentration on SAR-to-optical translation, accompanied by growing use of multiscale feature extraction, attention mechanisms, contrastive learning, cross-modal alignment, and pretrained representations. However, translation quality remains closely related to dataset characteristics, sensor configuration, preprocessing, and evaluation protocol. Pixel-level, structural, perceptual, distributional, sensor-related, and downstream metrics provide complementary evidence of translation performance. Major challenges include the non-unique nature of cross-modal mappings, preservation of geometric and sensor-related information, dependence on auxiliary observations in restoration tasks, and limited evidence for cross-domain generalization. Future research should develop task- and sensor-aware evaluation and strengthen cross-region and cross-sensor validation. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Figure 1

37 pages, 8981 KB

Open AccessReview

Review of Snow Identification Algorithms: From Traditional Machine Learning to Semantic Methods

by Keyu Ma, Zhixuan Zhang, Kai Hu, Ning Wang, Qi Liu and Tengyue Guo

Remote Sens. 2026, 18(7), 1067; https://doi.org/10.3390/rs18071067 - 2 Apr 2026

Viewed by 850

Abstract

Snow plays a significant role in the global energy balance, climate change, hydrological cycles, and other areas. However, traditional surface observation methods are limited in capturing the spatiotemporal dynamics of snow. This paper systematically reviews Machine Learning algorithms applicable to snow cover recognition. It highlights traditional Machine Learning methods such as Support Vector Machines and Random Forests, as well as more semantically oriented Deep Learning methods, including CNNs, attention mechanisms, and Transformers. These methods have shown robust performance in the domain of snow identification. Lastly, the paper discusses the strengths and weaknesses of different approaches and suggests directions for future research. Through this paper, readers will gain a comprehensive understanding of Machine Learning-based snow recognition algorithms and how these algorithms can be leveraged better. Full article

(This article belongs to the Special Issue Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs)

► Show Figures

Journal Menu

Journal Browser

Deep Learning for Multi-Source Remote Sensing Image Interpretation: Exploring, Rethinking, and Limiting Breakthroughs

Share This Special Issue

Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (13 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI