Application of deep learning technique to simulate fishing behavior in Antarctic krill fishery

The existing implementation of a management policy for Antarctic krill fishery has faced challenges due to the diverse and variable management strategies. Understanding the fishing behavior of krill fishery is crucial for developing sustainable policies, and the increasingly developed deep learning may assist the fishing monitoring and fishery management. In this study, Chinese krill fishery data collected on the Antarctic Peninsula was used to model krill fishing behavior using the deep learning technique - generative adversarial networks (GANs). The GANs successfully captured fishing behavior, particularly important features such as temporal characteristics and the Lévy flight, and the performance was better than the previous approaches (for example, Wang and Zhu, 2019). Overall, this modeling approach shows promise as a tool for monitoring fishing behavior and management of krill fishery in the Southern Ocean, and potentially for monitoring other fishing activities. As a powerful tool, the machine/deep learning techniques are therefore recommended to be discussed as a dedicated topic in the Working Groups.