Image-Based Modelling of Attachment Density and Morphometric Size in Rhopilema esculentum Polyps

Fudi Chen¹Yan Duan¹Yuwei Zhang²Qiyang Min²Yuhao Xian²Ming Sun^1*

• ¹Liaoning Ocean and Fisheries Research Institute, Dalian, China
• ²Dalian Ocean University, Dalian, China

Accurate monitoring of polyp attachment density is critical for the efficient culture of the edible jellyfish Rhopilema esculentum, yet quantitative guidelines remain limited. In the present study, image-based deep learning was coupled with conventional morphometry to characterise density-dependent growth. Calyx diameter measured manually followed a power-law decay with density (Calyx diameter=1.5752Density-0.281, R2=0.9614. Meanwhile, standardised photography combined with U-Net segmentation provided individual counts and projected areas, yielding an exponential density–polyp area model (Polyp area=4.3888e−0.202Density, R²=0.9909). Both models revealed a strong inverse relationship: as density increased, average polyp size and relative growth efficiency declined, while size variability increased. Compared to manual measurement, the automatic polyp segmentation approach demonstrated a significant advantage in processing speed, enabling efficient high-throughput analysis for aquaculture applications. Processing time was under one second per image, dramatically faster than manual measurements. These results demonstrated that AI-driven image segmentation provides accurate, high-throughput polyp size estimation, offering a promising tool for precision jellyfish aquaculture.