In several countries, the public health and fishery industries have suffered from harmful algal blooms (HABs) that have escalated to become a global issue. Though computational modeling offers an effective means to understand and mitigate the adverse effects of HABs, it is challenging to design models that adequately reflect the complexity of HAB dynamics. This paper presents a method involving the application of deep learning to an ocean model for simulating blooms of Alexandrium catenella. The classification and regression convolutional neural network (CNN) models are used for simulating the blooms. The classification CNN determines the bloom initiation while the regression CNN estimates the bloom density. GoogleNet and Resnet 101 are identified as the best structures for the classification and regression CNNs, respectively. The corresponding accuracy and root means square error values are determined as 96.8% and 1.20 [log(cells L^–1)], respectively. The results obtained in this study reveal the simulated distribution to follow the Alexandrium catenella bloom. Moreover, Grad-CAM identifies that the salinity and temperature contributed to the initiation of the bloom whereas NH₄-N influenced the growth of the bloom.

Paralytic shellfish toxins (PSTs) produced by Alexandrium catenella (formerly A. tamarense) in Korean coastal waters caused the deaths of four people (in 1986 and 1996) who consumed contaminated mussels (Mytilus edulis). This led to more detailed consideration of the risks of PST outbreaks and incidents in Korea, including the introduction of shellfish collection bans. In this study, we investigated the relationships between A. catenella population dynamics and PST accumulation in the mussel M. galloprovincialis. Discharges from the Nakdong River affect the environmental conditions along the Geoje coast, resulting in low salinity and high nutrient levels that trigger blooms of A. catenella. At the toxin peak on 24 April 2017, the toxins detected in A. catenella cells were C1, gonyautoxin (GTX)1 and GTX2, whereas the concentrations of PSTs in M. galloprovincialis were high and in the order of GTX4 > GTX1 > GTX3 > saxitoxin (STX) > GTX2 > neoSTX > decarbamoylgonyautoxin (dcGTX)2 > dc GTX3. The PST level in mussels was also high. At 15 °C, the PSTs are constantly found to be higher (10-fold higher in 2017 and 30-fold higher in 2018) than safe levels for human consumption (80 μg STX diHCl equivalents 100 g⁻¹).