Satellite-based vessel-tracking technologies have ushered in a new era for monitoring fishing activity at scale. By combining artificial intelligence (AI) methods with remotely-sensed data, researchers can now detect, classify and analyse fishing behaviour across vast and previously unobservable ocean regions. Technological advancements in vessel tracking are rapidly reshaping fisheries science and management, enabling new insights into fleet behaviour and its effects on marine ecosystems. This review synthesizes the state of the science in AI-enabled vessel tracking and highlights its transformative potential across four core domains: stock assessment and catch reconstruction, effort controls, spatial management, and monitoring, control, and surveillance. We explore how satellite-based vessel-tracking data complement legacy systems such as logbooks and observers, while also unlocking new capabilities to track ‘dark vessels’ that are not publicly observable by other means. We also identify key scientific and institutional challenges that are priorities for advancing the scientific frontier, including: filling data gaps for small-scale fleets, resolving uncertainty in behavioural inference and vessel identities for dark fleets, integrating catch and effort reporting, expanding real-time decision support, designing cutting-edge policy instruments to manage fisheries and developing shared standards for algorithm transparency and validation. As the field matures, we propose a forward-looking agenda to ensure that fleet tracking delivers on its promise to enhance transparency, support real-time decision-making and drive more inclusive, science-based ocean governance.

Fish size and fish biomass have been shown to increase inside the borders of Marine Protected Areas (MPAs) after the cessation of fishing. However, the effects of marine protection on fishing fleet behaviour and fish catches outside of MPAs are less well understood. Here we investigated changes in total catch and Catch per Unit Effort (CPUE) of bottom trawlers outside the borders of offshore MPAs in New Zealand. We used Regression Discontinuity in Time (before versus after protection) on both aggregate and individual trawl event data for one Marine Reserve, two Benthic Protected Areas, one Closed Seamount Area and one Marine Mammal Sanctuary. Despite the various forms of protection that reduce the total fishable area, total catch tended to increase after MPA implementation. Yet, there was little evidence that this was due to the net-movement of fish from larger populations within MPA boundaries i.e. spillover. Rather, the increases in catch in the post protection period appeared to be a consequence of changes in the behaviours of commercial fishers. This may be an unintended and previously unreported negative consequence of marine protection that could dampen some of the many benefits of MPAs.

Marine Protected Areas have been shown to be effective policy tools that confer environmental, economic and socio-cultural benefits. However, as with any policy that affects multiple stakeholders, trade-offs must be made between agents with disparate interests and goals. This paper utilises Multi-Attribute Utility Theory to develop a multi-criteria framework intended to inform decision makers of optimal policies based on their subjective preferences. Using an Ecosystem Based Management approach where multiple uses, knowledge types and interactions between ecological components are considered, the user is presented with utilities generated through simulation across ecological, economic and social dimensions that demonstrate how optimal policies may change with their weighting preferences. Novel to applications in marine policy, this paper explores how these utilities change with temporal consumption preferences and time spans under consideration. An application of this framework to a theoretical study area illustrates the relevance of such a tool for marine spatial planning.