This study highlights the coastline position changes of Qingdao coastal area from 2000 to 2019, using GIS and remote sensing technologies through Digital Shoreline Analysis System and LANDSAT images. Understanding the coastline movement by suitable method is an important challenge for this extremely dynamic coast. The shoreline changes were statistically measured using three techniques, namely; Linear Regression Rate, End Point Rate and Net Shoreline Movement. For the automatic coastline extraction, different methods were applied, but among them most suitable techniques is the canny edge algorithm technique, which gives the accurate result. The result show maximum accretion reached was 266.07m/yr, 2391.85m,124.47m/yr for End point rate, net shoreline movement and linear regression rate, respectively. While, the maximum erosion was -142.55m/yr, -1234.59m, -63.22m/yr for End point rate, net shoreline movement and linear regression rate, respectively. This paper hence presents the monitoring processes of coast and analyzing the coastline change by the use of geospatial techniques that would be helpful for the coastal planning and management of the Qingdao coast. The applicability of the proposed model is tested with other generic edge detection algorithms that include; Sobel, Prewitt, and Robert edge detection techniques and it was concluded that our model outperforming in accurately detecting the coastline.

Autoencoders (AEs) are commonly utilized for acquiring low-dimensional data representations and performing data reconstruction, which makes them suitable for hyperspectral unmixing. However, AE networks trained pixel by pixel and those employing localized convolutional filters disregard the global material distribution and distant interdependencies, resulting in the loss of necessary spatial feature information essential for the unmixing process. To overcome this limitation, we propose an innovative deep neural network model named U-shaped transformer network using shifted windows (UST-Net). UST-Net prioritizes spatial information in the scene that is more discriminative and significant by using multi-head self-attention blocks based on shifted windows. Unlike patch-based unmixing networks, UST-Net operates on the complete image, eliminating inconsistencies associated with patches. Moreover, the downsampling and upsampling stages are used to extract HSI feature maps at different scales. This process generates a context-rich and spatially accurate abundance map without losing local details. The experimental results of one synthetic dataset and three real datasets demonstrate that UST-Net significantly outperforms both traditional and several other advanced neural network methods. Our code is publicly available at https://github.com/UPCGIT/UST-Net.

Coastlines mapping techniques or the coastline automated analyses have been sought after. In practice, various sorts of seacoasts, for example, biological, silty, arenaceous, artificial, and bedrock coasts, have their own attributes, which force various degrees of intricacy on coastline mapping. As an extraordinary kind of complex artificial coast, aquaculture coast is shaped by the farming of aquatic organisms on silt tidal flats. With the rapid growth of coastal aquaculture in recent years, aquaculture coasts have increased in some developing countries. It has been estimated that aquaculture coasts constitute about 30% of all coastlines in mainland China. In order to identify, monitor, model, and manage the vast expanse of coastal aquaculture, effective methods of extracting aquaculture coastlines from remotely sensed imagery are desired. Secondly, with the rapid economic development in coastal areas, the development of coastal zone resources is also increasing day by day, which benefits the development of island coastal zone. Using oneself has become an important link in the development of marine economy. Due to the limited coastal resources and low environmental carrying capacity, the overexploitation and utilization of coastal resources will lead to a series of problems, such as coastal erosion, coastal migration and accumulation, island area reduction, etc., Both man-made activities and natural factors will lead to coastline changes, which will lead to corresponding changes in coastal ecological environment, thus affecting the coordinated development of coastal economy and the survival of coastal residents. Therefore, efficient, accurate and timely acquisition of coastline information and research on the spatial-temporal changes of coastline are of great significance to the protection of the living environment of coastal residents, the effective development of island and coastal resources, the coordination of sustainable economic development in coastal areas and the mitigation of marine disasters. This paper presents a review of those papers reporting coastline extraction and land use and land cover (LULC) change analysis using remote sensing (RS) and geographic information system (GIS) technology.

Sea fog is a precarious weather disaster affecting transportation on the sea. The accuracy of the threshold method for sea fog detection is limited by time and region. In comparison, the deep learning method learns features of objects through different network layers and can therefore accurately extract fog data and is less affected by temporal and spatial factors. This study proposes a scSE-LinkNet model for daytime sea fog detection that leverages residual blocks to encoder feature maps and attention module to learn the features of sea fog data by considering spectral and spatial information of nodes. With the help of satellite radar data from Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP), a ground sample database was extracted from Moderate Resolution Imaging Spectroradiometer (MODIS) L1B data. The scSE-LinkNet was trained on the training set, and quantitative evaluation was performed on the test set. Results showed the probability of detection (POD), false alarm rate (FAR), critical success index (CSI), and Heidke skill scores (HSS) were 0.924, 0.143, 0.800, and 0.864, respectively. Compared with other neural networks (FCN, U-Net, and LinkNet), the CSI of scSE-LinkNet was improved, with a maximum increase of nearly 8%. Moreover, the sea fog detection results were consistent with the measured data and CALIOP products.

High resolution remote sensing imagery plays a crucial role in monitoring coastal wetlands. Coastal wetland landscapes exhibit diverse features, ranging from fragmented patches to expansive areas. Mainstream Convolutional Neural Networks (CNN) cannot effectively analyze spatial relationships among consecutive image elements. This limitation impedes their performance in accurately classifying coastal wetlands. In order to tackle the above issues, we propose a Vision Transformer based UNet (ViT-UNet) model. This model extracts wetland features from high resolution remote sensing images by sensing and optimizing multi-scale features. To establish global dependencies, the Vision Transformer (ViT) is introduced to replace the convolutional layer in the UNet encoder. Simultaneously, the model incorporates a Convolutional Block Attention Module (CBAM) and a Multiple Hierarchies Attention Module (MHAM) to restore attentional features and reduce feature loss. Additionally, a skip connection is added to the single-skip structure of the original UNet model. This connection simultaneously links the output of the entire transformer and internal attention features to the corresponding decoder level. This enhancement aims to furnish the decoder with comprehensive global information guidance. Finally, all the extracted feature information is fused using Bilinear Polymerization Pooling (BPP). The BPP assists the network in obtaining a more comprehensive and detailed feature representation. Experimental results on the Gaofen-1 (GF-1) dataset demonstrate that the proposed ViT-UNet method achieves a Precision (P) score of 93.50%, outperforming the original UNet model by 4.10%. Compared with other state-of-the-art networks, ViT-UNet performs more accurately and finer in the extraction of wetland information in the Yellow River Delta.

Hyperspectral unmixing (HU) can obtain sub-pixel level ground object information, which is crucial for the fine advancement of imaging spectrum processing technology. Deep learning (DL) has been widely used in HU recently because of its ability to deeply mine complex relevant features in data. Existing DL unmixing methods usually operate only in the original spatial-spectral feature domain. However, due to noise, spectral variation, and other factors, it is difficult to fully mine effective features and easy to be interfered by only relying on the original domain. To get over these obstacles, we propose an innovative stationary wavelet convolutional network (SWC-Net) for HU. Stationary wavelet transform is introduced in SWC-Net to extend the original feature domain to feature domains with different frequencies, which promotes the multi-view extraction of information. What is more, a new generative self-supervised feature learning strategy based on wavelet (GSFL-W) is proposed for SWC-Net. More robust features can be obtained by GSFL-W through introducing noisy perturbations into high-frequency inputs and forcing the network to generate the original inputs. The proposed SWC-Net surpasses the advanced approaches by sufficient experiments on one simulated and three real hyperspectral datasets. The code is publicly available at https://github.com/UPCGIT/SWC-Net.