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.

The combination of multispectral image (MSI) and synthetic aperture radar (SAR) data has made certain progress in coastal wetland classification. How to realize the interactive fusion between the two data and make full use of their fusion characteristics becomes challenging. However, the existing joint classification methods neglect interaction information between features and underutilize fusion features. Therefore, this paper proposes a dual-branch feature interaction network (DFI-Net) that joins MSI and SAR data for coastal wetland classification. The dual-branch independent structure of 3DCNN processing MSI and 2DCNN processing SAR is designed, which can effectively capture spectral-spatial features and polarization features. In addition, we develop two novel modules. The feature interaction fusion block (FIFB) is designed to enhance the complementarity between the features of the two kinds of data. This block employs a cross-agent attention mechanism to realize effective interaction between MSI and SAR features and adaptive fusion of contextual information from the two branches. Finally, a plug-and-play module channel-spatial transformer encode (CSTE) is proposed to improve the utilization rate of interactive fusion data. The CSTE utilizes two parallel transformers to deeply mine information in interactive fusion data, and explore channel-spatial features across all dimensions to the maximum extent possible. The classification experiment is conducted on the Yellow River Delta Coastal Wetland Dataset (YRCWD). The experimental results show that the overall accuracy (OA) of DFI-Net reaches 97.03%, which outperforms the performance of other competitive approaches. The effectiveness of DFI-Net provides a reference method for combining MSI and SAR for coastal wetland classification.

Fisheries and bottom seawater data were collected in July in 2022 and 2023 from 15 sampling stations in the Huanghe River Estuary and adjacent seas in China. The patterns of functional alpha- and beta-diversity of fish communities in this area and their relationship with environmental factors were studied using trait-based analysis. Five functional classifications, which included 16 functional traits, four functional alpha-diversity indices (functional richness, functional evenness, functional divergence, and community-weighted mean), three functional beta-diversity indices (functional beta-diversity and its turnover and nestedness components), and 14 bottom environmental factors were considered. The dominant traits of fish communities were: benthivorous feeding habits, small and front-facing mouths, high trophic level, demersal, anguilliform, low growth coefficient, medium resilience, low vulnerability, and adapted to warm temperate conditions. The dominant migration traits and types of fish eggs varied by year, and fish abundance was the main factor affecting the dominant traits of the communities. The results of multiple regression on distance matrices and variance partitioning analysis indicated that ammonia nitrogen content, total phosphorus content, and pH were the main environmental factors that affected fish functional diversity. The N/P ratio had an upward control effect on fish functional diversity. Our findings also revealed that high pH gradients and distant geographical distances can inhibit trait turnover in fish communities.