ABSTRACT 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.

There is a widespread perception that illegal fishing is common in marine protected areas (MPAs) due to strong incentives for poaching and the high cost of monitoring and enforcement. Using artificial intelligence and satellite-based Earth observations, we provide estimates of industrial fishing activity in fully and highly protected MPAs worldwide, in which such fishing is banned. We find little to no activity in most cases. On average, these MPAs had just one fishing vessel present per 20,000 square kilometers during the satellite overpass, a density nine times lower than that of the unprotected waters of exclusive economic zones.

The expansion of marine protected areas (MPAs) is a core focus of global conservation efforts, with the “30x30” initiative to protect 30% of the ocean by 2030 serving as a prominent example of this trend. We consider a series of proposed MPA network expansions of various sizes, and we forecast the impact this increase in protection would have on global patterns of fishing effort. We do so by building a predictive machine learning model trained on a global dataset of satellite-based fishing vessel monitoring data, current MPA locations, and spatiotemporal environmental, geographic, political, and economic features. We then use this model to predict future fishing effort under various MPA expansion scenarios compared to a business-as-usual counterfactual scenario that includes no new MPAs. The difference between these scenarios represents the predicted change in fishing effort associated with MPA expansion. We find that regardless of the MPA network objectives or size, fishing effort would decrease inside the MPAs, though by much less than 100%. Moreover, we find that the reduction in fishing effort inside MPAs does not simply redistribute outside—rather, fishing effort outside MPAs would also decline. The overall magnitude of the predicted decrease in global fishing effort principally depends on where networks are placed in relation to existing fishing effort. MPA expansion will lead to a global redistribution of fishing effort that should be accounted for in network design, implementation, and impact evaluation.

Wildlife species generate significant economic value through recreational opportunities, ecosystem services, and their existence and preservation for future generations. Policymaker decisions about fish and wildlife conservation, population management, hunting and fishing limits, and damage assessments all rely to some extent on nonmarket valuation estimates of the species in question. Focusing on individual species, we present a comprehensive review of the nonmarket valuation literature from 1990 to 2023. We quantify studies by species and synthesize the characteristics of these species. We examine why certain species or uses have been the historical focus. Finally, we offer some insights into gaps in our knowledge and directions for future research. While the wildlife valuation literature is extensive, we question the scope of coverage and speculate on the reasons for such heavy coverage of some species and limited coverage of others. Charisma, endemism, and rarity play a large role, as do species with large use values.

The world’s population increasingly relies on the ocean for food, energy production and global trade 1 – 3 , yet human activities at sea are not well quantified 4 , 5 . We combine satellite imagery, vessel GPS data and deep-learning models to map industrial vessel activities and offshore energy infrastructure across the world’s coastal waters from 2017 to 2021. We find that 72–76% of the world’s industrial fishing vessels are not publicly tracked, with much of that fishing taking place around South Asia, Southeast Asia and Africa. We also find that 21–30% of transport and energy vessel activity is missing from public tracking systems. Globally, fishing decreased by 12 ± 1% at the onset of the COVID-19 pandemic in 2020 and had not recovered to pre-pandemic levels by 2021. By contrast, transport and energy vessel activities were relatively unaffected during the same period. Offshore wind is growing rapidly, with most wind turbines confined to small areas of the ocean but surpassing the number of oil structures in 2021. Our map of ocean industrialization reveals changes in some of the most extensive and economically important human activities at sea.

Previous research has cast doubt on the potential for marine protected areas (MPAs) to provide refuge and fishery spillover benefits for migratory species as most MPAs are small relative to the geographic range of these species. We test for evidence of spillover benefits accruing from the world’s largest fully protected MPA, Papahānaumokuākea Marine National Monument. Using species-specific data collected by independent fishery observers, we examine changes in catch rates for individual vessels near to and far from the MPA before and after its expansion in 2016. We find evidence of spillover benefits for yellowfin ( Thunnus albacares ) and bigeye tuna ( Thunnus obesus ).

SignificanceMeasuring the economic benefits conveyed by predators is difficult—often, effects are indirect and operate through complex ecological changes. As a result, debates about the expansion of predators have pit salient costs against more speculative estimates of benefits that might be dismissed as unreliable or ideologically motivated. We quantify the indirect benefits of wolves (Canis lupus) to human lives and property through reductions in deer-vehicle collisions. Moreover, we decompose the effect into two components: changes in prey behavior versus prey abundance. This decomposition is important when effective policy depends on whether hunters can replicate the effects of predators. In the case of wolves, we conclude that human deer hunters cannot.

The Chinook salmon population in Lake Michigan is declining precipitously due to ecological changes, and the impact on recreational fishing value is unknown. We estimate a conditional logit model to characterize how Wisconsin resident anglers react to changes in species-specific availability and catch rates. Using these results, we calculate the non-market value of access to the fishery that reflects current, historical, and potential future fishing conditions. We then predict whether native lake trout and walleye, which are more resilient to the changing conditions in the lake, can maintain the fishery’s value if non-native Chinook salmon collapses. Results show that while large losses would occur absent other improvements, a portion of the fishery’s value could be maintained if substitute species, particularly walleye, improved in quality and were readily accessible.

Two of the largest protected areas on earth are U.S. National Monuments in the Pacific Ocean. Numerous claims have been made about the impacts of these protected areas on the fishing industry, but there has been no ex post empirical evaluation of their effects. We use administrative data documenting individual fishing events to evaluate the economic impact of the expansion of these two monuments on the Hawaii longline fishing fleet. Surprisingly, catch and catch-per-unit-effort are higher since the expansions began. To disentangle the causal effect of the expansions from confounding factors, we use unaffected control fisheries to perform a difference-in-differences analysis. We find that the monument expansions had little, if any, negative impacts on the fishing industry, corroborating ecological models that have predicted minimal impacts from closing large parts of the Pacific Ocean to fishing.

Relative to target species, priority conservation species occur rarely in fishery interactions, resulting in imbalanced, overdispersed data. We present Ensemble Random Forests (ERFs) as an intuitive extension of the Random Forest algorithm to handle rare event bias. Each Random Forest receives individual stratified randomly sampled training/test sets, then down-samples the majority class for each decision tree. Results are averaged across Random Forests to generate an ensemble prediction. Through simulation, we show that ERFs outperform Random Forest with and without down-sampling, as well as with the synthetic minority over-sampling technique, for highly class imbalanced to balanced datasets. Spatial covariance greatly impacts ERFs’ perceived performance, as shown through simulation and case studies. In case studies from the Hawaii deep-set longline fishery, giant manta ray Mobula birostris syn. Manta birostris and scalloped hammerhead Sphyrna lewini presence had high spatial covariance and high model test performance, while false killer whale Pseudorca crassidens had low spatial covariance and low model test performance. Overall, we find ERFs have 4 advantages: (1) reduced successive partitioning effects; (2) prediction uncertainty propagation; (3) better accounting for interacting covariates through balancing; and (4) minimization of false positives, as the majority of Random Forests within the ensemble vote correctly. As ERFs can readily mitigate rare event bias without requiring large presence sample sizes or imparting considerable balancing bias, they are likely to be a valuable tool in bycatch and species distribution modeling, as well as spatial conservation planning, especially for protected species where presence can be rare.