The sediment microbial community plays a key role in the cycling of organic matter in marine ecosystems. The characteristics of the sediment microbial community are significantly related to changes in the environment. In this study, we analyzed the diversity and distribution of microbial communities in sediments from different geographical regions (the Liao River estuary, Yellow River estuary, hypoxic zone, and offshore zone) of the Bohai Sea using high-throughput sequencing. The results showed that the community richness and diversity (especially the unique diversity) of the Liao River estuary were larger than those of the Yellow River estuary, hypoxic zone, and offshore zone. The phylum Proteobacteria dominated in the Liao River estuary (46.26%), hypoxic zone (76.19%), and offshore zone (69.79%), while the dominant phylum in the Yellow River estuary was the Bacteroidetes phylum. The genus Gillisia was the dominant genus in both the Liao River estuary and Yellow River estuary. The offshore zone and hypoxic zone shared the same dominant Photobacterium genus. The results of Pearson correlation and redundancy analysis showed that environmental parameters such as nitrite, silicate, nitrate, phosphate, ammonia, dissolved oxygen, pH, and salinity interfered significantly with the structure and diversity of the microbial community. The results of this study will provide support for future research on the interaction mechanism of pollutants and microorganisms in the estuaries and a typical hypoxic zone of the Bohai Sea.

The rapid development of factory aquaculture not only brings economic benefits to coastal areas but also poses numerous ecological and environmental challenges. Therefore, understanding the distribution of coastal factory aquaculture is of great significance for ecological protection. To tackle the issue of the complex spectral and spatial characteristics in remote-sensing images of different factory aquaculture plants in coastal areas, a multiscale residual attention network (MRAN) model for extracting factory aquaculture information is proposed in this study. MRAN is a modification of the U-Net model. By introducing a residual structure, an attention module, and a multiscale connection MRAN can solve the problem of inadequately detailed information extraction from a complex background. In addition, the coastal areas of Huludao City and Dalian City in Liaoning Province were selected as the research areas, and experiments were conducted using the domestic Gaofen-1 remote-sensing image data. The results indicate that the pixel accuracy (PA), mean PA, and mean intersection over union of the proposed model are 98.31%, 97.85%, and 92.46%, respectively, which are superior to those of other comparison models. Moreover, the proposed model can effectively reduce misidentification and missing identification phenomena caused by complex backgrounds and multiple scales.