Coastline extraction from remote sensing imagery is persistently challenged by intra-class heterogeneity (e.g., diverse coastline types) and boundary ambiguity. Existing methods often exhibit suboptimal performance in complex scenes mixing artificial and natural landforms, as they tend to ignore coastline morphological priors and struggle to recover details in low-contrast regions. To address these issues, this paper introduces TopoSeg-Net, a novel collaborative framework centered on a dual-decoder architecture. A segmentation decoder utilizes a Morphology-Aware Attention (MAA) module to adaptively decouple and model diverse coastline morphologies, and a Structure-Detail Synergistic Enhancement (SDSE) module to reconstruct weak boundaries with high fidelity. Meanwhile, a learnable topology decoder frames topology construction as a graph reasoning task, which ensures the geometric and topological integrity of the final vector output.TopoSegNet was evaluated on the public Landsat-8 and a custom Lianyungang Gaofen-1 (GF-1) dataset. The experimental results show that the proposed method reached 98.64%, 66.80%, and 0.795 on the mIoU, BIoU, and APLS metrics, respectively, verifying its validity and superiority. Compared to state-of-the-art methods, the TopoSegNet model demonstrates significantly higher accuracy and topological fidelity.

Transition zones in coastal wetlands are prone to frequent semantic changes due to dynamic ecological processes such as tidal fluctuations, seasonal changes, and runoff dynamics. However, existing semantic change detection (SCD) methods generally lack explicit modeling and a structured representation of such regions, making it difficult to accurately locate and identify semantic changes within them. To address this issue, TDNet is proposed for SCD in coastal wetlands. First, a transition zone detection branch is added to identify semantically sensitive regions and guide the network to focus on change-prone areas. Then, a transition zone driven module (TZDM) temporally concatenates the initial segmentation features (ISFs) and transition zone features (TZFs) from the bi-temporal inputs into a four-frame sequence, processes it with a 3D convolutional structure to model spatiotemporal evolution in transition zones , and ultimately generates the final segmentation features (FSFs). Additionally, a transition zone indicator (TZI) is employed to generate pixel-level transition labels that provide spatial supervision, further improving the model’s ability to distinguish change-prone regions. Experimental results demonstrate that TDNet outperforms state-of-the-art methods in addressing the challenge of SCD within transition zones.

Accurate monitoring of Golden Tides (Sargassum Harmful Algal Blooms) is critical for preventing and mitigating marine ecological disasters. Image-level weakly supervised semantic segmentation (WSSS) methods employ image-level labels to derive pixel-level predictions. While they considerably reduce annotation costs and accelerate deployment compared to fully supervised approaches, they still encounter several challenges: Golden Tide occurs as irregular floating patches at sea and class activation maps (CAMs) focus only on the most discriminative regions, many discrete targets are overlooked and pseudo-labels remain incomplete. Moreover, complex marine backgrounds distract model attention and introduce semantic noise, reducing pseudo-label reliability and hindering detection accuracy from meeting practical requirements. We propose MPECAM, a multi-prototype-enhanced weakly supervised framework for Golden Tide detection, which consists of three main components: (i) Multi-Prototype Fusion (MPF) strategy and Multi-Prototype Re-Activation (MPRA) module, which dynamically maintain a prototype bank and reweight feature maps to activate weak-response regions, thereby enhancing completeness for irregular targets; (ii) Inter-Prototype Contrastive Constraint (IC2) module, which employs a foreground-global-background triplet contrastive loss to decoupling Golden Tide feature from seawater features, suppress semantic confusion, and refine pseudo-label purity; (iii) a self-supervised consistency mechanism, which leverages the refined CAM as supervision to reintegrate structurally complete pseudo-label knowledge back into the backbone, enabling joint optimization of the modules. Experimental results on hybrid sensor remote sensing imagery covering the Yellow and East China Seas demonstrate that our method achieves state-of-the-art performance (59.25% mIoU and 74.41% F1-score), providing reliable segmentation of Golden Tide regions and offering a scalable solution for marine HAB agile monitoring.

Monitoring glacier changes is essential for understanding global climate dynamics and assessing their environmental impacts. However, accurate detection remains challenging due to seasonal variations, illumination differences, and heterogeneous textures in remote sensing imagery. To address these issues, we propose VPGCD-Net, a Transformer-based dual-branch network that achieves robust glacier change detection through visual prompt engineering. The visual prompting branch integrates threshold segmentation and difference calculation, leveraging a visual prompt transformer (VPT) to encode regions of significant change and generate high-level semantic prompts. Meanwhile, the change detection branch adopts ResNet18 as the backbone to extract dual-temporal features, followed by a Transformer module for modeling global spatiotemporal dependencies and a FiLM module for adaptive feature modulation to emphasize real change regions. Complementing the method, we introduce the first polar glacier-focused dataset specifically designed for deep learning-based glacier change detection in remote sensing. Experimental results demonstrate that VPGCD-Net outperforms existing state-of-the-art methods, achieving superior accuracy even under complex conditions such as shadow interference. The dataset is publicly available at https://huggingface.co/datasets/cuibinge/Glacier-Dataset.

Accurate segmentation of multiclass raft aquaculture areas (RAAs) from high-resolution remote sensing images is challenging due to spectral similarity across classes, boundary ambiguity caused by complex marine conditions, and intraregion inconsistency. To address these challenges, this letter proposes PBFANet, a deep segmentation network that integrates boundary guidance and frequency-adaptive filtering mechanisms. A gated boundary–semantic fusion module (GBSFM) dynamically combines pseudo-boundary cues with semantic features to enhance edge localization, while the consistency-aware fusion module (CAFM) employs an adaptive low-pass filter (LPF) and a high-pass filter (HPF) to suppress intraregion noise and restore boundary details. Notably, CAFM leverages the distinct frequency-domain characteristics of different aquaculture classes—such as dense high-frequency textures in laver areas and low-frequency dominance in fish cage regions—to improve class separability. Experiments on GF-1 satellite imagery covering laver, hijiki, and fish cages demonstrate that PBFANet achieves a mean${F}1$-score of 0.914 and a mean intersection over union (mIoU) of 82.78%, outperforming state-of-the-art methods in classification accuracy, boundary precision, and segmentation consistency.

Domain adaptation methods enable model migration and adaptation across different domain data distributions. However, the source and target domains of hyperspectral images (HSIs) have large spectral offsets and spatial distribution differences, making the extraction of high-quality domain-invariant features between different domains is essential for classification. To achieve a more consistent feature representation for each category between the source and target domains, we propose a category semantic guided unsupervised domain adaptation network (CSGNet) for HSIs classification. CSGNet is designed to learn cross-domain invariant representation from category semantic information. First, to embed category semantic prior knowledge during feature learning, we extracted textual semantic features from the textual descriptions for each category and projected visual features into the semantic space via visual-linguistic alignment. A category representation memory pool is then introduced to store the visual-linguistic representations of different categories. Second, we propose a bi-classifier adversarial learning method designed to generate inconsistent category predictions in the unlabeled target domain, thereby enhancing the classifier’s discriminative capability regarding those hard-to-transfer features. Finally, to utilize the domain-invariant features stored in the category memory pool, a category attention module is proposed to guide the model’s adaptation to the data from different domains, mitigating the impact of the differences in the domain data distributions. Extensive experimental results validated on three cross-domain datasets demonstrate that the proposed method outperforms other state-of-the-art methods. The source code is available at http://github.com/cuibinge/CSGNet.

Fine-grained classification of coastal wetlands from remote sensing images is a challenging task due to the spectral overlap between different wetland vegetation types, making them difficult to distinguish. Traditional methods for remote sensing interpretation often rely on manual classification or shallow machine learning approaches, which fail to effectively capture complex spatial relationships and contextual information. To integrate ecological and biological prior knowledge and enhance the generalization performance of the model, this paper proposes a remote sensing image classification method for coastal wetlands based on Category Representation Learning, called CRLNet. The core idea is to learn category-invariant representations of land cover types in coastal wetlands using geoscience knowledge graphs and deep neural networks. First, deep feature maps and classification probability maps generated by a semantic segmentation network are used to initialize the representations of each category; then, the Spatial Topological Relationship Encoder (STRE) and Category Attribute Knowledge Encoder (CAKE) are proposed, employing a two-stream architecture to refine the representations of each category; finally, each pixel is assigned to the category with the highest similarity based on the aforementioned deep feature maps and category-invariant representations. By combining graph convolution and self-attention mechanisms, CRLNet effectively integrates ecological and biological prior knowledge into category representation learning, thereby reducing the likelihood of conflicts between classification results and geoscience prior knowledge. Experimental results demonstrate that CRLNet outperforms state-of-the-art methods on the Huanghe River and Yancheng coastal wetland datasets. Notably, CRLNet is a lightweight framework with only 1/55 of the parameter count of CGGLNet, making it computationally efficient while maintaining high classification accuracy. The codes will be available from the website: https://github.com/cuibinge/CRLNet.

Significant progress has been made in modern remote sensing (RS) image change detection (CD) by leveraging the powerful feature learning capabilities of convolutional neural networks (CNNs) and transformers. However, current popular change detection techniques primarily focus on extracting deep semantic features and pixel-level interactions while overlooking the potential benefits of cluster-level semantic interaction in bitemporal images. In this letter, we propose a novel approach called the Bitemporal Graph Semantic Interaction Network for Remote Sensing Images Change Detection (BGSINet-CD). Specifically, the land cover types in bitemporal images are clustered by employing soft clustering for each pixel, and then each cluster is separately projected to a vertex in graph space. Additionally, we introduce a graph semantic interaction module (GSIM) that enhances the interactions between bitemporal features at the semantic level. GSIM effectively improves the information coupling between bitemporal features, thereby suppressing task-irrelevant information. In comparison to other competing methods, our approach demonstrates a significant improvement in F1 scores, achieving 88.25% and 91.02% on the GZ-CD and WHU-CD datasets, respectively. Furthermore, our method employs a reduced number of network parameters and exhibits lower complexity, striking a superior balance between accuracy and computational efficiency.

Accurate monitoring of raft aquaculture areas is particularly important for raft aquaculture planning and management. However, due to natural and human factors such as tidal changes and crop harvesting, the spectral response in some aquaculture areas is weak, leading to omissions and incompleteness in extraction results. To address this problem, we propose a progressive semantic-guided network (PSGNet) for accurate extraction of raft aquaculture areas from remote sensing images. Specifically, inspired by the human visual system, we introduce a feature enrichment module (FEM) with parallel dilated convolution to capture more discriminative features of aquaculture areas, and then a partial decoder is used to aggregate high-level features and generate an initial semantic map. In addition, we propose a semantic-guided module (SGM) that progressively suppresses background information and enhances feature response in aquaculture areas through dual-branch semantic guidance. The experimental results on the GF-1 aquaculture area dataset have shown that the proposed PSGNet performs better than other models in extracting raft aquaculture areas and significantly reduces the omissions and incompleteness of extracted aquaculture areas, with the F1-score reaching 0.91, which is 2% higher than SOTA models. Furthermore, the experimental results on the Sentinel-2, GF-2 and Dongtou datasets verify the generalization ability of PSGNet.

Accurate monitoring of raft aquaculture areas (RAAs) is particularly important for the protection of marine ecosystems. However, existing semantic segmentation methods are often degraded by severe shrinkage when extracting inapparent RAAs caused by natural factors such as tide level changes and human activities including laver harvesting. In this letter, a graph-based boundary-interior interaction network (BI2Net) is proposed for laver RAA extraction. Graph convolution based on soft clustering is introduced to capture the global distribution patterns among RAAs. For the network structure, we designed the RAA-boundary branch and RAA-interior branch, one for locating the boundaries and the other for extracting the RAAs. Importantly, unlike traditional dual-branch methods that only use additional information from the auxiliary tasks to assist with the primary task, BI2Net introduces a graph interaction module (GIM) that implements reasoning about the relationship between differ-ent distribution patterns, which sufficiently and comprehensively exploits mutual benefits between RAA extraction and boundary detection. After the addition of GIM, precision, recall, F1 and IoU were improved by 2.0%, 8.2%, 0.060 and 8.2% respectively.Extensive experiments have shown that our proposed BI2Net outperforms existing methods in terms of the consistency and completeness of RAA extraction, with precision, recall, F1 and IoU reached 93.0%, 90.6%, 0.916 and 84.7%, respectively.

The fine mapping of coastal wetlands is a major challenge due to the spectral aliasing of vegetation. In this letter, we selected Zhuhai-1 hyperspectral images (HSIs) for coastal wetland mapping and proposed a tiny-scene embedding network (TSE-Net) based on scene representation and attention mechanism. In TSE-Net, the tiny-scene representation associated with each hyperspectral pixel was extracted and used to enhance the spectral discrimination of ground objects. DenseNet was chosen as the backbone network, and the attention mechanism was introduced into the dense blocks to extract remarkable features. Experiments on the Yellow River estuary coastal wetland showed that the results of TSE-Net had a significant improvement in accuracy compared to other models, especially for the coastal wetland vegetation with confusing spectra, such as Spartina alterniflora, Suaeda salsa, Phragmites australis, and Tamarix.

GF-1 multispectral wide field of view (WFV) images, with a spatial resolution of 16 m, have been widely used in earth monitoring. However, the spatial details provided by WFV images are not sufficient for many applications. Thus, this letter proposes a novel WFV image super-resolution (SR) algorithm called GFRCAN based on a very deep residual coordinate attention network. To form a very deep network, the residual-in-residual (RIR) structure consisting of several residual groups (RG) with long skip connections is used. Meanwhile, the residual coordinate attention block (RCOAB) and adaptive multi-scale spatial attention module (AMSA) are incorporated to focus on the high-frequency information and multi-scale features adaptive weighted fusion. Besides, the spectral and spatial details of SR images are improved by incorporating peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) into the loss function. Both subjective and objective evaluation results show that the proposed model outperforms the state-of-the-art methods.

A serious problem in the classification of hyperspectral images is that labeled samples are scarce. A single classifier cannot satisfy a variety of situations; therefore, a multiple kernel learning algorithm based on rolling guidance recursive filtering is proposed in this paper. It extracts feature images by the rolling guidance recursive filtering method, and the algorithm can obtain different types of feature images by changing the number of iterations. Additionally, a strong classifier is obtained by combining many of basic classifiers with different feature images based on the multiple kernel learning framework, which significantly improves the classification performance. The combination of basic classifiers is determined by evaluating the classification performance without solving complex optimization problems. Three real hyperspectral images are used to evaluate the proposed method, and the experimental results show that the proposed algorithm exhibits better classification performance than state-of-the-art methods.

In this paper, a novel SuperPixel-based Extended Random Walker (SPERW) classification method for hyperspectral images is proposed that consists of three main steps. First, a multiscale segmentation algorithm is adopted to generate many superpixels, each of which represents a homogeneous region of adaptive shape and size. Then, a new weighted graph is constructed based on the superpixels in which the nodes correspond to the superpixels and the edges correspond to the links connecting two adjacent superpixels. Each edge has a weight that defines the similarity between the two superpixels. Second, a widely used pixelwise classifier, i.e., the support vector machine, is adopted to obtain classification probability maps for a hyperspectral image, which are then used to approximate the prior probabilities of the superpixels. Finally, the obtained prior probability maps of the superpixels are optimized by using the Extended Random Walker (ERW) algorithm, which encodes the spatial information both among and within the superpixels of the hyperspectral image in a weighted graph. Compared with the spectrum of a single pixel, the spectrum of a superpixel is more stable and less affected by noise; therefore, superpixels are more appropriate for adoption as the basic elements in the hyperspectral image classification. Because the spectral correlation between pixels within the same superpixel and the spatial correlation among adjacent superpixels are both well considered in the ERW-based global optimization framework, the proposed method shows high classification accuracy on four widely used real hyperspectral data sets even when the number of training samples is relatively small.

In this paper, a novel model of process slicing and user-centered recommendation is presented to make flexible reuses of business rules. Business processes are sliced in such angles as condition, action and resource. Suitable process slices are recommended to end-users with a proposed algorithm. The approach has been trial-used in emergency management, for supporting the modeling, execution and management of emergency plans before and during a disaster.