Biology subjects

van Walraven, L.

Publications and source records attributed to van Walraven, L..

3 recordsLinked to original sources

bioRxiv2026

Optimizing automated classification for zooplankton in coastal conditions: the impact of model selection, imaging instruments, and colour information

The advancement in deep learning techniques has made Convolutional Neural Networks (CNNs) a powerful tool for the fully automated classification of zooplankton images. In this study, we systematically investigate how network selection, colour information and differences in imaging instruments affect the classification of zooplankton images by comparing multiple state-of-the-art CNNs on images of zooplankton and marine snow from the in situ Continuous Particle Imaging and Classification Sensor (CPICS), Video Plankton Recorder (VPR), In Situ Ichtyoplankton Imaging System (ISIIS), and the on-board Plankton Imager (Pi-10). With differences between models of 7.8 to 19% in F1-score, we find that model selection strongly affects the classification performance, with EfficientNetV2S showing the most reliable overall performance. Moreover, differences between model architectures are largest for the least abundant classes (<100 labeled images), which implies that when these are present, careful model selection is most beneficial. The high image quality of the Pi-10 strongly increases the performance for the least abundant classes compared to the other instruments. In addition, we find a significant correlation (r = 0.597) between ImageNet the performance and F1-score on zooplankton images, which implies that more generally, a model that performs well on ImageNet will perform well for zooplankton classification. Colour information increases the F1-score of the best performing classifier with 2.8%, but provides a stronger benefit (25% F1-score) for classes with <100 images. The overall performance increase of colour information is less than expected and questions the advantage of recording colour information for zooplankton.

bioinformatics↗

bioRxiv2020

Metabarcoding reveals different zooplankton communities in northern and southern areas of the North Sea

Zooplankton are key players in marine ecosystems, linking primary production to higher trophic levels. The high abundance and high taxonomic diversity renders zooplankton ideal for biodiversity monitoring. However, taxonomic identification of the zooplankton assemblage is challenging due to its high diversity, subtle morphological differences and the presence of many meroplanktonic species, especially in coastal seas. Molecular techniques such as metabarcoding can help with rapid processing and identification of taxa in complex samples, and are therefore promising tools for identifying zooplankton communities. In this study, we applied metabarcoding of the mitochondrial cytochrome c oxidase I gene to zooplankton samples collected along a latitudinal transect in the North Sea, a shelf sea of the Atlantic Ocean. Northern regions of the North Sea are influenced by inflow of oceanic Atlantic waters, whereas the southern parts are characterised by more coastal waters. Our metabarcoding results indicated strong differences in zooplankton community composition between northern and southern areas of the North Sea, particularly in the classes Copepoda, Actinopterygii (ray-finned fishes) and Polychaeta. We compared these results to the known distributions of species reported in previous studies, and by comparing the abundance of copepods to data obtained from the Continuous Plankton Recorder (CPR). We found that our metabarcoding results are mostly congruent with the reported distribution and abundance patterns of zooplankton species in the North Sea. Our results highlight the power of metabarcoding to rapidly assess complex zooplankton samples, and we suggest that the technique could be used in future monitoring campaigns and biodiversity assessments. HighlightsO_LIZooplankton communities are different in northern and southern areas of the North Sea C_LIO_LIMetabarcoding results are consistent with known species distributions and abundance C_LIO_LIMetabarcoding allows for fast identification of meroplanktonic species C_LI

molecular biology↗

bioRxiv2018

Temporally varying isotopic niche overlap of the invasive ctenophore Mnemiopsis leidyi with other zooplanktivores in the western Dutch Wadden Sea

The invasive ctenophore Mnemiopsis leidyi can be a major predator of zooplankton in areas where it has been introduced. In this study, the possible competition of M. leidyi with native macroplankton and nekton in the western Dutch Wadden Sea was investigated in March-August, 2011 by determining and comparing isotopic niches of zooplanktivores. Stable carbon and nitrogen isotope signatures were determined from tissue samples of fish, scyphozoa, hydromedusa, ctenophores, crustaceans and cephalopods.{delta} 15N of M. leidyi was positively related to ctenophore size, suggesting that small ctenophores occupied a lower trophic level than large ones. A cluster analysis showed that in the spring and early summer period, when M. leidyi densities are low, average{delta} 13C and{delta} 15N ratios of the invasive M. leidyi were similar to those of most other gelatinous zooplankton and pelagic fish species sampled. At the beginning of the bloom period in August there was no overlap in isotopic niche of M. leidyi with that of any other pelagic zooplanktivore. During this month the population consisted mainly of larvae and juveniles with lower{delta} 15N ratios. At present, M. leidyi appears not to be a significant competitor for other gelatinous zooplankton and fish species because the period of high diet overlap with other consumers was also the period in which M. leidyi was least abundant.

ecology↗