Deep Learning for Simulating Harmful Algal Blooms Using Ocean Numerical Model

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.

Automated summary

This paper proposes a method of using deep learning combined with convolutional neural network models to simulate blooms of Alexandrium catenella, achieving high accuracy and root mean square error values. The results show that the simulated distribution follows the actual bloom pattern, with salinity and temperature influencing the bloom initiation and NH4-N affecting the bloom growth.