This study examined the effects of hydrodynamic conditions on the growth performance and nutritional quality of Pacific oysters (Crassostrea gigas) in raceway flumes. Oysters were reared under three flow velocities—low (LV, 5 cm/s), medium (MV, 10 cm/s), and high (HV, 20 cm/s)—using three replicate flumes per treatment, each containing 100 individuals. Results indicated that while shell morphology remained unaffected by flow rate, MV significantly enhanced soft tissue weight and meat yield compared to LV. Physiologically, HV upregulated the activities of trypsin and amylase, with trypsin levels significantly exceeding those in LV. Furthermore, MV exhibited the highest crude protein and glycogen content. Notably, both MV and HV improved the accumulation of total and essential amino acids. Fatty acid profiles showed clear separation among treatments, primarily driven by C16:0, C18:0, C20:5n3, C22:1n9, and C20:2. Collectively, moderate flow velocity (10 cm/s, MV) resulted in a well-balanced enhancement of growth, biochemical composition, and nutritional value compared to low or high velocities, highlighting the potential value of controlled hydrodynamic conditions in oyster farming.

Kelp, often referred to as a “sea vegetable”, holds substantial economic significance. Currently, the drying process for kelp in China primarily relies on outdoor sun-drying methods. Detecting kelp in the field presents challenges arising from issues such as overlapping and obstruction. To address these challenges, this study introduces a lightweight model, K-YOLOv5, specifically designed for the precise detection of sun-dried kelp. YOLOv5-n serves as the base model, with several enhancements implemented in this study: the addition of a detection head incorporating an upsampling layer and a convolution module to improve the recognition of small objects; the integration of an enhanced I-CBAM attention mechanism, focusing on key features to enhance the detection accuracy; the replacement of the CBS module in the neck network with GSConv to reduce the computational burden and accelerate the inference speed; and the optimization of the IoU algorithm to improve the identification of overlapping kelp. Utilizing drone-captured images of sun-dried kelp, a dataset comprising 2190 images is curated. Validation on this self-constructed dataset indicates that the improved K-YOLOv5 model significantly enhances the detection accuracy, achieving 88% precision and 78.4% recall. These values represent 6.8% and 8.6% improvements over the original model, respectively, meeting the requirements for the real-time recognition of sun-dried kelp.