Estimation of Phytoplankton Size Classes in the Littoral Sea of Korea Using a New Algorithm Based on Deep Learning

Abstract

The size of phytoplankton (a key primary producer in marine ecosystems) is known to influence the contribution of primary productivity and the upper trophic level of the food web. Therefore, it is essential to identify the dominant sizes of phytoplankton while inferring the responses of marine ecosystems to change in the marine environment. However, there are few studies on the spatio-temporal variations in the dominant sizes of phytoplankton in the littoral sea of Korea. This study utilized a deep learning model as a classification algorithm to identify the dominance of different phytoplankton sizes. To train the deep learning model, we used field measurements of turbidity, water temperature, and phytoplankton size composition (chlorophyll-a) in the littoral sea of Korea, from 2018 to 2020. The new classification algorithm from the deep learning model yielded an accuracy of 70%, indicating an improvement compared with the existing classification algorithms. The developed classification algorithm could be substituted in satellite ocean color data. This enabled us to identify spatio-temporal variation in phytoplankton size composition in the littoral sea of Korea. We consider this to be highly effective as fundamental data for identifying the spatio-temporal variation in marine ecosystems in the littoral sea of Korea.

Trophic niche of a neustonic copepod community sustained by local production in high- and low-salinity summer water masses in the northeastern East China Sea

“…These fronts significantly influence the temporal and spatial fluctuations in water masses, which, in turn, affect the composition and distribution of neustonic copepod species (Jeong et al, 2014;Choi et al, 2020). Variations in size-based phytoplankton compositions, such as picosized cyanobacteria in offshore warm waters vs. microsized diatoms in coastal cold waters, correspond to the distribution of these water masses (Yoon et al, 2020;Kang et al, 2022). In the nECS, the feeding strategies of Euchaeta sp.…”

Integrated Ecosystem Assessments for Fisheries Management in the Yellow Sea, the East China Sea, and the East/Japan Sea

“…Kang et al ( 2022) [6] assess a new algorithm based on a deep learning model suitable for the estimation of phytoplankton size classes (micro, nano, and pico size) in Korean waters. This algorithm is expected to be useful for understanding long-term variations in phytoplankton size structure using satellite ocean color data.…”