Jiangsu coastal wetland has the largest area of the invasive plant, Spartina alterniflora (S. alterniflora), in China. S. alterniflora has been present in the wetland for nearly 40 years and poses a substantial threat to the safety of coastal wetland ecosystems. There is an urgent need to control the distribution of S. alterniflora. The biological characteristics of the invasion process of S. alterniflora contribute to its multi-scale distribution. However, the current classification methods do not deal successfully with multi-scale problems, and it is also difficult to perform high-precision land cover classification on multi-temporal remote sensing images. In this study, based on Landsat data from 1990 to 2020, a new deep learning multi-scale residual convolutional neural network (MRCNN) model was developed to identify S. alterniflora. In this method, features at different scales are extracted and concatenated to obtain multi-scale information, and residual connections are introduced to ensure gradient propagation. A multi-year data unified training method was adopted to improve the temporal scalability of the MRCNN. The MRCNN model was able to identify the annual S. alterniflora distribution more accurately, overcame the disadvantage that traditional CNNs can only extract feature information at a single scale, and offered significant advantages in spatial characterization. A thematic map of S. alterniflora distribution was obtained. Since it was introduced in 1982, the distribution of S. alterniflora has expanded to approximately 17,400 ha. In Jiangsu, the expansion process of S. alterniflora over time was divided into three stages: the growth period (1982–1994), the outbreak period (1995–2004), and the plateau period (2005–2020). The spatial expansion direction was mainly parallel and perpendicular to the coastline. The hydrodynamic conditions and tidal flat environment on the coast of Jiangsu Province are suitable for the growth of S. alterniflora. Reclamation of tidal flats is the main factor affecting the expansion of S. alterniflora.

Marine oil spills due to ship collisions or operational errors have caused tremendous damage to the marine environment. In order to better monitor the marine environment on a daily basis and reduce the damage and harm caused by oil pollution, we use marine image information acquired by synthetic aperture radar (SAR) and combine it with image segmentation techniques in deep learning to monitor oil spills. However, it is a significant challenge to accurately distinguish oil spill areas in original SAR images, which are characterized by high noise, blurred boundaries, and uneven intensity. Hence, we propose a dual attention encoding network (DAENet) using an encoder–decoder U-shaped architecture for identifying oil spill areas. In the encoding phase, we use the dual attention module to adaptively integrate local features with their global dependencies, thus improving the fusion feature maps of different scales. Moreover, a gradient profile (GP) loss function is used to improve the recognition accuracy of the oil spill areas’ boundary lines in the DAENet. We used the Deep-SAR oil spill (SOS) dataset with manual annotation for training, testing, and evaluation of the network, and we established a dataset containing original data from GaoFen-3 for network testing and performance evaluation. The results show that DAENet has the highest mIoU of 86.1% and the highest F1-score of 90.2% in the SOS dataset, and it has the highest mIoU of 92.3% and the highest F1-score of 95.1% in the GaoFen-3 dataset. The method proposed in this paper not only improves the detection and identification accuracy of the original SOS dataset, but also provides a more feasible and effective method for marine oil spill monitoring.

Coastal development such as sea reclamation, port terminals, and breakwater construction has significantly altered the southwestern coastline of Laizhou Bay, changing the regional hydrodynamic environment. To explore how tidal range and tidal prism respond to these 20-year coastline changes, this paper selected the southwestern coastline data of Laizhou Bay in 2000 and 2020, established a 2-D tidal model, and studied the impact of the 20-year coastline changes on tidal range and tidal prism in this sea area. The results show that during the 20 years from 2000 to 2020, most of the bay area’s coastline was in a growth trend of advancing toward the sea, 85.3% of the cross-sections were growth areas, 11.9% were dynamic stable areas, and there was almost no erosion area. Affected by reclamation activities, the area of the southwestern part of Laizhou Bay decreased by 11.66%, the coastline increased by 63.27%, and the center of mass moved 2.22 km to the northeast. The reclamation of tidal flats caused the potential energy of tidal waves in the bay to increase, the maximum possible tidal wave in the southwestern part of the bay showed an increasing trend, and the bay top between Weifang Port and Guangli Port increased particularly significantly, with a maximum increase of 22 cm. The spring tide period, neap tide period and average tidal prism in the southwestern bay decreased by 4.79%, 3.29%, and 4.24%, respectively. The reclamation of tidal flats is the main reason for the decrease in tidal prism in the southwestern part of the bay.

Accurately understanding the impact of Significant Wave Height (SWH) on mariculture productivity is crucial for developing a sustainable blue economy and mitigating the effects of increasing marine extreme events under climate change. However, a significant research gap exists in macroscale empirical tools capable of quantifying the complex, non-linear, and spatially non-stationary relationships between SWH and mariculture yield. Addressing this, our study focused on the Bohai and Yellow Seas, a critical mariculture region in China. We developed five novel SWH indices (LSDI, MSDI, HSDI, RSI, NDSI) to statistically link SWH with the Unit Area Yield (UAY) using buoy-calibrated ERA5 reanalysis data and regional fishery statistics. Geographically Weighted Regression (GWR) was further employed to uncover the spatial heterogeneity of this relationship. Results demonstrated that the Normalized Difference SWH Index (NDSI) most effectively captured the SWH-UAY relationship (r = 0.61, R² = 0.37), as its non-linear form integrates the positive effects of low SWH conditions and the negative effects of high SWH conditions. GWR analysis revealed significant spatial non-stationarity, with the SWH impact on yield being stronger in the eastern and southern open waters of the Yellow Sea and weaker in the northern semi-enclosed Bohai Sea. The index framework and spatial analysis method developed in this study provide a transferable tool for quantifying the impact of physical oceanographic processes on mariculture productivity at a macro scale, which can offer a scientific basis for climate-resilient mariculture zoning and adaptive management.