Background Plankton are foundational to marine food webs and an important feature for characterizing ocean health. Recent developments in quantitative imaging devices provide in-flow high-throughput sampling from bulk volumes—opening new ecological challenges exploring microbial eukaryotic variation and diversity, alongside technical hurdles to automate classification from large datasets. However, a limited number of deployable imaging instruments have been coupled with the most prominent classification algorithms—effectively limiting the extraction of curated observations from field deployments. Holography offers relatively simple coherent microscopy designs with non-intrusive 3-D image information, and rapid frame rates that support data-driven plankton imaging tasks. Classification benchmarks across different domains have been set with transfer learning approaches, focused on repurposing pre-trained, state-of-the-art deep learning models as classifiers to learn new image features without protracted model training times. Combining the data production of holography, digital image processing, and computer vision could improve in-situ monitoring of plankton communities and contribute to sampling the diversity of microbial eukaryotes. Results Here we use a light and portable digital in-line holographic microscope (The HoloSea) with maximum optical resolution of 1.5 μm, intensity-based object detection through a volume, and four different pre-trained convolutional neural networks to classify > 3800 micro-mesoplankton (> 20 μm) images across 19 classes. The maximum classifier performance was quickly achieved for each convolutional neural network during training and reached F1-scores > 89%. Taking classification further, we show that off-the-shelf classifiers perform strongly across every decision threshold for ranking a majority of the plankton classes. Conclusion These results show compelling baselines for classifying holographic plankton images, both rare and plentiful, including several dinoflagellate and diatom groups. These results also support a broader potential for deployable holographic microscopes to sample diverse microbial eukaryotic communities, and its use for high-throughput plankton monitoring.
Legal requirement in Europe asks for Ecosystem-Based Fisheries Management (EBFM) in European seas, including consideration of trophic interactions and minimization of negative impacts of fishing on food webs and ecosystem functioning. This study presents the first mass-balanced ecosystem model focused on the western Baltic Sea (WBS). Results show that heavy fishing pressure exerted on the WBS has forced top predators such as harbour porpoise and cod to cover their dietary needs by shifting from forage fish to other prey or find food outside of the model area. The model was then developed to explore the dynamics of four future fishery scenarios: (1) business as usual (BAU), (2) maximum sustainable fishing (F = FMSY), (3) half of FMSY, and (4) EBFM with F = 0.5 FMSY for forage fish and F = 0.8 FMSY for other fish. Simulations show that BAU would perpetuate low catches from depleted stocks with a high risk of extinction for harbour porpoise. In contrast, the EBFM scenario would allow the recovery of harbour porpoise, forage fish and cod with increases in catch of herring and cod. EBFM promotes ecosystem resilience to eutrophication and ocean warming, and through the rebuilding of commercial stocks increases by more than three times carbon sequestration compared to BAU. The model provides an interrelated assessment of trophic guilds in the WBS, as required by European law to assess whether European seas are in good environmental status.
The planktonic diversity throughout the oceans is vital to ecosystem functioning and linked to environmental change. Plankton monitoring tools have advanced considerably with high-throughput in-situ digital cameras and genomic sequencing, opening new challenges for high-frequency observations of community composition, structure, and species discovery. Here, we combine multi-marker metabarcoding based on nuclear 18S (V4) and plastidial 16S (V4–V5) rRNA gene amplicons with a digital in-line holographic microscope to provide a synoptic diversity survey of eukaryotic plankton along the Newfoundland Shelf (Canada) during the winter transition phase of the North Atlantic bloom phenomenon. Metabarcoding revealed a rich eukaryotic diversity unidentifiable in the imaging samples, confirming the presence of ecologically important saprophytic protists which were unclassifiable in matching images, and detecting important groups unobserved or taxonomically unresolved during similar sequencing campaigns in the Northwest Atlantic Ocean. In turn, imaging analysis provided quantitative observations of widely prevalent plankton from every trophic level. Despite contrasting plankton compositions portrayed by each sampling method, both capture broad spatial differences between the northern and southern sectors of the Newfoundland Shelf and suggest complementary estimations of important features in eukaryotic assemblages. Future tasks will involve standardizing digital imaging and metabarcoding for wider use and consistent, comparable ocean observations.
As a result, in the Methods section, under the subheading 'Bioinformatic analysis' , "To summarize compositional diferences between transects a principal component analysis of the Euclidean (Aitchison) distances40 was performed on log-transformed ASV counts37 and tested for statistical signifcance using a permutational analysis of variance102 in the vegan package (v. 2.5.7) 84 . " now reads: "To summarize compositional diferences between transects a principal component analysis of the Euclidean (Aitchison) distances40 was performed on log-transformed ASV counts37 and tested for statistical signifcance using a permutational analysis of variance102 in the vegan package (v. 2.5.7) 102 . "The original Article has been corrected.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.