Monitoring and understanding the behavior of fishing vessels are important in facilitating effective management, preventing illegal fishing, informing fishing grounds and evaluating effects of harvests on fishery resources. In recent decades, a large quantity of real-time data of fishing vessels have become available with the development of vessel-tracking systems, making it possible to study the behavior of fishing vessels in high spatial and temporal resolutions. To effectively and efficiently deal with the large amount of data, algorithms from artificial intelligence (AI) are increasingly applied in the study of fishing vessel behavior. In this paper, we first introduce the various data sources for studying fishing vessel behavior and compare their pros and cons. Secondly, we review the AI methods that have been used to monitor and extract the behavior of fishing vessels from big data. Then, studies on the physical, ecological and social mechanisms affecting the behavior of fishing vessels were synthesized. Lastly, we review the applications of fishing vessel behavior in fishery science and management.

Climate change-induced variabilities in the environment and fishing pressure affect the distribution and abundance of bigeye tuna in the Pacific Ocean. Understanding the causal relationships among these factors is complicated and challenging. We constructed a multi-output neural network model based on data from four types of bigeye tuna fisheries (longline and purse seine in the west-central and eastern Pacific Ocean, respectively) and marine environmental data, aiming to analyse the response of bigeye tuna to natural and anthropogenic factors from 1995 to 2019 in the Pacific Ocean. The input layer weights were used to explore the importance of environmental variable, while the output layer weights evaluated the contribution of fishing operations. These factors determined the final spatiotemporal distribution and abundance dynamics for bigeye tuna. The optimal model predicted a strong correlation between the locations of major habitats and El Niño southern Oscillation (ENSO) events, indicating that bigeye tuna abundance dynamics respond to the intensity of climate variability. During El Niño events, suitable conditions lead to an expansion of the main habitats east of 170°W, while during La Niña events, the strengthening of the westward advection leads to the contraction of major habitats west of 170°W. Furthermore, the resource abundance of bigeye tuna is predicted to be higher during moderate to weak El Niño events than during strong El Niño events. The abundances in purse seine and longline-dependent fisheries demonstrate significant different distribution patterns under different ENSO events, reflecting the unique environmental preferences at different life stages of bigeye tuna. Given the increasing frequency of climate variability and escalating fishing pressures, our findings provide beneficial insights for the sustainable development of bigeye tuna resource in the Pacific Ocean.

Climate-induced environmental variability is proving to be a driving factor reshaping the distribution and altering the movement of marine species. However, how Pacific Ocean squids, with their 1-year life span and adaptive abilities, and which support >25% of global squid fisheries, respond to environmental variability is poorly understood. We address this knowledge gap by constructing spatio–temporal models for two squid species in three fishing grounds (Ommastrephes bartramii in the northwest Pacific Ocean and Dosidicus gigas in the eastern Pacific Ocean) using generalized additive mixed models based on data from digitized Chinese squid-jigging logbooks for 2005–2017. The relationships between environmental variables and local abundance of squids reflected by environmental and traditional spatial response curves track changes in climate. The peaks and troughs in squid biomass coincide with La Niña and El Niño events, but are moderate in contrast to the effects of directional climate-induced environmental variability. We find substantial poleward shifts by squids inhabiting low and middle latitudes. These findings have broad implications for food security and open ocean ecosystem dynamics.

With consideration of sophisticated modern commercial fisheries, the commonly used metric catch per unit effort (CPUE) may not be a reasonable proxy for generating abundance indices (AIs) for all species. Presumably, spatiotemporal scale is a critical factor that affects the accuracy of local/aggregated AIs derived from spatial modelling approaches, thus it is necessary to evaluate how scale affects scientific estimates of abundance. We explored three commonly utilized AI proxies, including aggregated catch (CatchAI), aggregated effort (EffortAI), and CPUEAI from the perspective of accuracy and spatial representational ability using a neural network (NN) model at different spatiotemporal scales. As a case example, we grouped the Chinese fleet's Northwest Pacific neon flying squid (Ommastrephes bartramii) fishery dataset (2009–2018) at four spatial scales (0.25° × 0.25°, 0.5° × 0.5°, 1° × 1°, 2° × 2°) to construct monthly and annual resolution models. The results showed that for both simulated and real datasets, AIs based on catch data had better accuracy, consistency, and spatial representational ability compared to CPUE and effort-dependent AI models at all spatial scales. Relative to the finest spatial scale, only results from the model with 0.5° × 0.5° resolution preserved enough distributional detail to reflect the known migration route for O. bartramii. Model results exhibited large variation dependent on spatial scale, particularly amongst CPUEAI scenarios. We suggest that scale comparisons among potential proxies should be conducted prior to AIs being used for applications such as population trends in stock assessment.

Ommastrephid squids are short-lived ecological opportunists and their recruitment is largely driven by the surrounding environment. While recent studies suggest that recruitment variability in several squid species can be partially explained by environmental variability derived from synoptic oceanographic data, assessment of ommastrephid stocks using environmental variability is rare. In thisstudy, we modified asurplus production model to incorporate environmental variability into the assessment of threeommastrephid squids (Ommastrephes bartramii in the northwest Pacific, Illex argentinus in the southwest Atlantic and Dosidicus gigas in the southwest Pacific). We assumed that the key environmental variables—suitable sea surface temperature on spawning grounds during the spawning seasons and feeding grounds during the feeding seasons—have effects on the carrying capacity and the instantaneous population growth rate, respectively, in the surplus production model. For each squid stock, the assessment model with environmental variability had the highest fitting accuracy and the lowest mean squared error and coefficient of variation, and the management reference points based on the optimal model were more precautionary. This study advances our understanding of the interactions between the environment and ommastrephid squid population dynamics and can therefore improve the management of these commercially valuable stocks with a short life cycle.