Projects

Disabled Signals

When and why vessels stop broadcasting their position

map showing disabled ais signals
Regions of the global ocean are highlighted in orange where levels of suspected intentional disabling of vessel position signals are highest

The automatic identification system (AIS) has revolutionized the way fishing activity is monitored across the ocean. But vessels don’t always broadcast their locations—AIS devices can be switched off to conceal a vessel’s activity. Our work on disabled signals seeks to identify when and why fishing vessels intentionally stop broadcasting their position, with a goal to better understand the vessels and areas at high risk of illegal, unreported, and unregulated (IUU) fishing.

When signals stop 

IUU fishing results in global losses estimated at tens of billions of dollars each year, yet it has been extremely difficult to monitor and prevent. While AIS is invaluable for understanding a vessel’s fishing behavior and managing fishing fleets, it has a key limitation: fishing vessels can switch off their signal, usually with no repercussions. While the disabling of AIS can sometimes be permitted—such as in areas of high piracy—fishers may often stop broadcasting their position for nefarious reasons—to cover up illegal activities or hide from enforcement authorities. Gaps in AIS signals, which can be caused by poor satellite reception, present an even greater challenge by making it difficult to tell suspicious AIS disabling events from gaps simply caused by technical issues.

A global database of disabling events 

In collaboration with our partners at the National Oceanic and Atmospheric Administration’s Southwest Fisheries Science Center, we are developing algorithms to detect which gaps in AIS data are caused intentionally, as well as learning to identify environmental and behavioral factors that can be used to predict future disabling events. We start by estimating how often a vessel’s AIS signal should be received, then analyze gaps in the signal to determine whether a vessel likely dropped the transmission on purpose, and apply a popular machine learning method called boosted regression trees to identify potential reasons.The result is the first global dataset of AIS disabling, which highlights known areas of IUU fishing concern and suggests that vessels shut off their signals most frequently near transshipment hotspots and exclusive economic zone boundaries—particularly contested ones. ​​This information can be used by governing bodies and authorities to inform fisheries management policy and enforcement activity.

Recent Work
semounts

Satellite Data Casts Light on Seamounts at Risk

Emerging tools and datasets help quantify fishing pressure and can inform management at remote, unmonitored seamounts Seamounts—large underwater mountains— hold vital biological diversity, but they also contend with heavy exploitation. Numbering in the tens of

Read More »
Scroll to Top