English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Climate change is increasing the frequency and severity of harmful algalblooms (HABs), which cause significant fish deaths in aquaculture farms. Thiscontributes to ocean pollution and greenhouse gas (GHG) emissions since deadfish are either dumped into the ocean or taken to landfills, which in turnnegatively impacts the climate. Currently, the standard method to enumerateharmful algae and other phytoplankton is to manually observe and count themunder a microscope. This is a time-consuming, tedious and error-prone process,resulting in compromised management decisions by farmers. Hence, automatingthis process for quick and accurate HAB monitoring is extremely helpful.However, this requires large and diverse datasets of phytoplankton images, andsuch datasets are hard to produce quickly. In this work, we explore thefeasibility of generating novel high-resolution photorealistic syntheticphytoplankton images, containing multiple species in the same image, given asmall dataset of real images. To this end, we employ Generative AdversarialNetworks (GANs) to generate synthetic images. We evaluate three different GANarchitectures: ProjectedGAN, FastGAN, and StyleGANv2 using standard imagequality metrics. We empirically show the generation of high-fidelity syntheticphytoplankton images using a training dataset of only 961 real images. Thus,this work demonstrates the ability of GANs to create large synthetic datasetsof phytoplankton from small training datasets, accomplishing a key step towardssustainable systematic monitoring of harmful algal blooms.

Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms