Apparent fishing effort (AIS)
Overview
The automatic identification system (AIS) is a tracking system developed for maritime safety and collision avoidance. Global Fishing Watch collects and analyzes AIS data transmitted by vessels to understand global vessel activity.
AIS data includes a vessel’s identity, location, speed, direction and more, collected through a global network of satellite and terrestrial receivers. Global Fishing Watch processes billions of AIS messages daily, focusing on vessels likely to be fishing based on their movement patterns and registry information. Using machine learning algorithms, Global Fishing Watch classifies (Kroodsma et al. 2018) vessel type and infers fishing activity from features such as changes in speed and direction.
To produce a global dataset of fishing activity predictions—tracking positions interpreted as indicative of fishing—our general fishing model must operate across diverse fisheries, each with varying definitions of what constitutes “fishing.” As a result, the training data used to build the model, and thus the predicted fishing activity, encompass a range of fishing-related behaviors, including searching, setting gear, hauling and gear soaking.
The outcome of these models is displayed as “apparent fishing effort” and “apparent fishing events” in the Global Fishing Watch platform and data, which are not confirmed records of fishing. Suggested use cases and caveats described below explain the strengths and limitations of these datasets.
Use cases
- Monitor fishing activity in near real-time: Governments, NGOs, and researchers can track vessel activity and apparent fishing hours across global waters, EEZs and marine protected areas (MPAs).
- Support enforcement and compliance: AIS data helps identify suspicious vessel behavior, such as potential fishing near MPAs. This aids authorities in prioritizing patrols and investigations.
- Analyze trends and behavior over time: Long-term AIS archives enable users to examine how fishing patterns shift due to seasonal changes, policy interventions or environmental events.
- Inform fisheries management and spatial planning: AIS-derived apparent fishing effort can be layered with ecological and jurisdictional data to support zoning decisions, policy development and ecosystem-based management.
- Increase transparency and accountability: Publicly available AIS-based analyses contribute to open and inclusive ocean governance and support market-based mechanisms for responsible sourcing.
AIS Limitations
- Not all vessels carry AIS transponders: AIS is mainly used by vessels over 24 meters that operate further from shore. Many small-scale or artisanal vessels do not carry AIS and subsequently are not captured in the AIS-based apparent fishing effort layer.
- Inconsistent transmission: AIS broadcasts are more frequent and detectable with Class A devices, which are common on larger vessels. Class B devices (used by smaller vessels) have weaker signals and are received less reliably, especially by satellite. Where a vessel inconsistently transmits, the vessel positions that are predicted as fishing may have a disproportionate amount of time associated with them, which can lead to over or under predictions of fishing effort.
- Signal interference and reception gaps: In dense vessel traffic areas, AIS signals can overlap and interfere, reducing satellite detection of individual transmissions.
- Deliberate disabling or falsification: AIS can be turned off or deliberately spoofed, leading to false locations or shared identities.
- Data quality and update lag: Not all providers capture or share complete AIS datasets. Terrestrial stations may log messages less frequently, and satellite data coverage is uneven.
- Interpretation over time: Increases or decreases in apparent activity could reflect changing AIS usage, changing access to terrestrial stations or dynamic AIS, or reception quality rather than actual changes in fishing behavior. When doing a long-term study on fishing activity trends with our data, we suggest contacting us to help with the interpretation.
Caveats
- Interpreting apparent fishing effort: Our general fishing model estimates fishing-related activity and is intended to reflect a range of fishing-related behaviors—such as searching or preparing gear—not just gear deployment or retrieval. These estimates should not be interpreted as precise records of gear setting or hauling.
- False positives: AIS-based models identify fishing based on movement patterns. As with any model, there can be false positives. False positives may appear in the dataset where vessels slow down and change direction, but aren’t engaged in fishing activity. We are continuously working on reducing false positives and this should be reflected in future data releases.
- Bias in vessel identification and gear classification: Misclassifications in vessel type may occur due to inconsistent or incomplete vessel registry data. Misclassifications can happen when algorithms struggle to appropriately categorize vessels, for instance, where vessels use several gears (thus changing their behavioral patterns) or when a vessel’s MMSI (maritime mobile service identity) number is used by more than one vessel, then MMSI recycling may result in misclassification of vessel type by our vessel classification model. Misclassification of vessel type can result in the unexpected presence or absence of vessels in the apparent fishing effort estimates.
- Apparent fishing events vs apparent fishing effort: Apparent fishing events group consecutive apparent fishing positions into summarized events for easier visualization. They apply filters based on time, distanc, and vessel behavior, which can exclude some fishing positions. As a result, apparent fishing events and apparent fishing effort may differ, especially when fishing activity is spread out over long distances or time gaps.
Squid jigger predictions
Apparent fishing activity for squid jiggers is generated with a simple rule-based approach (or heuristic) and it does not come from the general fishing model. Squid jigging can be observed through loitering movement patterns at night, often involving operations with bright lights while stationary (Seto et al. 2023). The heuristic algorithm classifies positions as fishing if the squid jigger is more than 10 nautical miles from shore and moving slower than 1.5 knots at night for more than four hours.
Data sources and verification
Fishing models are trained and validated using observer, logbook and expert-labeled data. Regional accuracy varies depending on AIS (or VMS, when applicable) use, reception quality and gear characteristics.
Source data and citations
All vessel data are freely available through the Global Fishing Watch data portal at https://globalfishingwatch.org. To learn more, read the supplementary materials of the Global Fishing Watch AIS-based fishing activity paper.
License
Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.
Data Download Portal
The platform and API apparent fishing effort data differs from the data available in the data download portal. Learn more.