Machine learning techniques to characterize functional traits of plankton from image data

Introducing ARTiMiS: A Low-Cost Flow Imaging Microscope for Microalgal Monitoring

Manual microscopy is the gold standard for phytoplankton monitoring in diverse engineered and natural environments. However, it is both labor-intensive and requires specialized training for accuracy and consistency, and therefore difficult to implement on a routine basis without significant time investment. Automation can reduce this burden by simplifying the measurement to a single indicator (e.g., chlorophyll fluorescence) measurable by a probe, or by processing samples on an automated cytometer for more granular information. The cost of commercially available flow imaging cytometers, however, poses a steep financial barrier to adoption. To overcome these labor and cost barriers, we developed ARTiMiS: the Autonomous Real-Time Microbial 'Scope. The ARTiMiS is a low-cost flow imaging microscopy-based platform with onboard software capable of providing taxonomically resolved quantitation of phytoplankton communities in real-time. ARTiMiS leverages novel multimodal imaging and onboard machine learning-based data processing that is currently optimized for a curated and expandable database of industrially relevant microalgae. We demonstrate its operational limits, performance in identification of laboratory-cultivated microalgae, and potential for continuous monitoring of complex microalgal communities in full-scale industrial cultivation systems.

Morphological and taxonomic diversity of mesozooplankton is an important driver of carbon export fluxes in the ocean

Mesozooplankton is a very diverse group of small animals ranging in size from 0.2 to 20 mm not able to swim against ocean currents. It is a key component of pelagic ecosystems through its roles in the trophic networks and the biological carbon pump. Traditionally studied through microscopes, recent methods have been however developed to rapidly acquire large amounts of data (morphological, molecular) at the individual scale, making it possible to study mesozooplankton using a trait-based approach. Here, combining quantitative imaging with metabarcoding time-series data obtained in the Sargasso Sea at the Bermuda Atlantic Time-series Study (BATS) site, we showed that organisms' transparency might be an important trait to also consider regarding mesozooplankton impact on carbon export, contrary to the common assumption that just size is the master trait directing most mesozooplankton-linked processes. Three distinct communities were defined based on taxonomic composition, and succeeded one another throughout the study period, with changing levels of transparency among the community. A co-occurrences' network was built from metabarcoding data revealing six groups of taxa. These were related to changes in the functioning of the ecosystem and/or in the community's morphology. The importance of Diel Vertical Migration at BATS was confirmed by the existence of a group made of taxa known to be strong migrators. Finally, we assessed if metabarcoding can provide a quantitative approach to biomass and/or abundance of certain taxa. Knowing more about mesozooplankton diversity and its impact on ecosystem functioning would allow to better represent them in biogeochemical models.

Morphological diversity increases with decreasing resources along a zooplankton time series

Biodiversity is studied notably because of its reciprocal relationship with ecosystem functions such as production. Diversity is traditionally described from a taxonomic, genetic or functional point of view but the diversity in organism morphology is seldom explicitly considered, except for body size. We describe morphological diversity of marine zooplankton seasonally and over 12 years using quantitative imaging of weekly plankton samples, in the northwestern Mediterranean Sea. We extract 45 morphological features on greater than 800 000 individuals, which we summarize into four main morphological traits (size, transparency, circularity and shape complexity). In this morphological space, we define objective morphological groups and, from those, compute morphological diversity indices (richness, evenness and divergence) using metrics originally defined for functional diversity. On both time scales, morphological diversity increased when nutritive resources and plankton concentrations were low, thus matching the theoretical reciprocal relationship. Over the long term at least, this diversity increase was not fully attributable to taxonomic diversity changes. The decline in the most common plankton forms and the increase in morphological variance and in extreme morphologies suggest a mechanism akin to specialization under low production, with likely consequences for trophic structure and carbon flux.

Temperature dependence of parasitoid infection and abundance of a diatom revealed by automated imaging and classification

Diatoms are a group of phytoplankton that contribute disproportionately to global primary production. Traditional paradigms that suggest diatoms are consumed primarily by larger zooplankton are challenged by sporadic parasitic "epidemics" within diatom populations. However, our understanding of diatom parasitism is limited by difficulties in quantifying these interactions. Here, we observe the dynamics of Cryothecomonas aestivalis (a protist) infection of an important diatom on the Northeast U.S. Shelf (NES), Guinardia delicatula, with a combination of automated imaging-in-flow cytometry and a convolutional neural network image classifier. Application of the classifier to >1 billion images from a nearshore time series and >20 survey cruises across the broader NES reveals the spatiotemporal gradients and temperature dependence of G. delicatula abundance and infection dynamics. Suppression of parasitoid infection at temperatures <4 °C drives annual cycles in both G. delicatula infection and abundance, with an annual maximum in infection observed in the fall-winter preceding an annual maximum in host abundance in the winter-spring. This annual cycle likely varies spatially across the NES in response to variable annual cycles in water temperature. We show that infection remains suppressed for ~2 mo following cold periods, possibly due to temperature-induced local extinctions of the C. aestivalis strain(s) that infect G. delicatula. These findings have implications for predicting impacts of a warming NES surface ocean on G. delicatula abundance and infection dynamics and demonstrate the potential of automated plankton imaging and classification to quantify phytoplankton parasitism in nature across unprecedented spatiotemporal scales.