The increasingly severe issue of marine debris presents a critical threat to the sustainable development of marine ecosystems. Real-time detection is essential for timely intervention and cleanup. Furthermore, the density of marine debris exhibits significant depth-dependent variation, resulting in degraded detection accuracy. Based on 9625 publicly available underwater images spanning various depths, this study proposes UTNet, a lightweight neural model, to improve the effectiveness of real-time intelligent identification of marine debris through multidimensional optimization. Compared to Faster R-CNN, SSD, and YOLOv5/v8/v11/v12, the UTNet model demonstrates enhanced performance in random image detection, achieving maximum improvements of 3.5% in mAP50 and 9.3% in mAP50-95, while maintaining reduced parameter count and low computational complexity. The UTNet model is further evaluated on underwater videos for real-time debris recognition at varying depths to validate its capability. Results show that the UTNet model exhibits a consistently increasing trend in confidence levels across different depths as detection distance decreases, with peak values of 0.901 at the surface and 0.764 at deep-sea levels. In contrast, the other six models display greater performance fluctuations and fail to maintain detection stability, particularly at intermediate and deep depths, with evident false positives and missed detections. In summary, the lightweight UTNet model developed in this study achieves high detection accuracy and computational efficiency, enabling real-time, high-precision detection of marine debris at varying depths and ultimately benefiting mitigation and cleanup efforts.

The Yellow Sea is an important offshore area in China, and the accurate prediction of its seawater temperature is of great significance for marine environmental monitoring and climate adaptation management. However, existing research on predicting the three-dimensional (3D) temperature field in the Yellow Sea is scarce and insufficiently accurate. This study proposes a TCN-U-Net++ fusion model to reconstruct the Yellow Sea temperature field using remote sensing satellite data and SODA reanalysis data, while considering the influence of a series of factors, including wind (USSW and VSSW), absolute bathymetric data (BAT), sea surface height anomaly (SSHA), latitude (LAT), longitude (LON), solar radiation (SR), surface runoff (SRO), and precipitation (P). The results show that the model can accurately capture the temporal and spatial distribution characteristics of the temperature field in the Yellow Sea. The results indicate that the deviations from SODA are generally within 2 °C, with errors being approximately 45% lower than those of other models, while the prediction errors relative to Argo and voyage observations are mostly within 1 °C, further demonstrating the accuracy and robustness of the proposed model. In addition, the predictions of the Yellow Sea Cold Water Mass (CWM) are highly consistent with SODA in terms of their evolution and key characteristic parameters. Specifically, the maximum deviation in core temperature is only 0.3 °C, and the difference in its spatial extent is less than 1%. The results demonstrate that TCN-U-Net++ effectively enhances the accuracy of 3D sea temperature prediction in the Yellow Sea, providing technical support for temperature monitoring, ecological early warning, and climate change research.