Oysters are a group of economically important bivalves in China, with estuaries serving as one of their primary cultivation areas. However, heavy metal pollution in these estuarine environments poses a potential threat to aquaculture by leading to the accumulation of heavy metals in farmed oysters, which could impact their safety and marketability. This study was conducted in the aquaculture area of the Luoyangjiang River estuary, where eight sampling sites were selected. Water, sediment, and oysters categorized by shell length were collected from each site. The concentrations of heavy metals (Ag, As, Cd, Cr, Cu, Ni, Pb, and Zn) were determined in both the environmental samples and oyster tissues. Additionally, multiplex species-specific PCR was used to identify oyster species. The results showed significant variations in dissolved-phase and suspended particulate matter (SPM) metal concentrations across different sampling sites, while sediment metal concentrations were more consistent but similar to those in SPM. The large oysters were comprised of 50% Magallana angulata and 50% Magallana gigas, while small oysters were identified as Magallana sikamea. The Cd, Cu, Pb, and Zn levels in both size groups of oysters exceeded data from previous studies, indicating contamination in the estuary. The observed differences in heavy metal concentrations between large and small oysters primarily reflect species-specific variability in metal accumulation, which may also be influenced by factors such as growth and exposure duration. Furthermore, the lack of significant correlation between metal concentrations in environmental media and oysters suggests that oysters may be exposed to multiple sources of metal contamination.

The analysis of 3D meshes with deep learning has become prevalent in computer graphics. As an essential structure, hierarchical representation is critical for mesh pooling in multiscale analysis. Existing clustering-based mesh hierarchy construction methods involve nonlinear discretization optimization operations, making them nondifferential and challenging to embed in other trainable networks for learning. Inspired by deep superpixel learning methods in image processing, we extend them from 2D images to 3D meshes by proposing a novel differentiable chart-based segmentation method named geodesic differential supervertex (GDSV). The key to the GDSV method is to ensure that the geodesic position updates are differentiable while satisfying the constraint that the renewed supervertices lie on the manifold surface. To this end, in addition to using the differential SLIC clustering algorithm to update the nonpositional features of the supervertices, a reparameterization trick, the Gumbel-Softmax trick, is employed to renew the geodesic positions of the supervertices. Therefore, the geodesic position update problem is converted into a linear matrix multiplication issue. The GDSV method can be an independent module for chart-based segmentation tasks. Meanwhile, it can be combined with the front-end feature learning network and the back-end task-specific network as a plug-in-plug-out module for training; and be applied to tasks such as shape classification, part segmentation, and 3D scene understanding. Experimental results show the excellent performance of our proposed algorithm on a range of datasets.