A surprising amount of crime takes place at sea, ranging from illegal fishing to drug smuggling and human trafficking. To detect, locate and eventually predict such activities, researchers from Oregon State University are developing new algorithms based on artificial intelligence (AI) and big data.

Called illegal, unreported and unregulated activities (IUUs), crimes committed at sea are generally commited by people using vessels called “dark fleets” — so named for their ability to hide their location by deactivating their GPS systems and moving among legally operating and visible vessels.

“IUUs include all kinds of terrible things,” said James Watson, a marine scientist expert at Oregon State University, and a principal investigator on the project. “We came into this thinking primarily about illegal fishing, but that turns out to be just the tip of the iceberg. It is much, much bigger.”

“Illegal fishing threatens food security, compromises ocean health, penalizes honest fishermen and fishing companies and is all-too-often linked to slave labor, human trafficking and drug trafficking,” said Jane Lubchenco an Oregon State researcher and co-principal investigator on the project. “The issue has been what to do about it. Fortunately, the world has recently made huge strides in creating policy agreements, mobilizing political will and harnessing technology and artificial intelligence to ‘see,’ crack down on, and deal with some of the illegal fishing.”

Funded by a grant from NASA, the Oregon State researchers are developing their tools by synthesizing data concerning the location of most of the world’s vessels. By observing the behavior patterns of these vessels that are operating legally, researchers believe — as in the case of astronomers identifying far-away planets based not on actually “seeing” the planets, but on the behaviors of the celestial bodies located near those planets — that alterations or changes in the legally operating vessels' behaviors might signal the presence of a “dark fleet.”

Another possible indicator of an IUU, according to Watson, is when a vessel navigates into a suspicious area, deactivating its GPS system once it enters.

“One can infer that they are participating in illegal fishing from their activity,” he said. “There are tons of data out there — it’s a matter of synthesizing it and recognizing patterns. There is a behavioral psychology aspect to it. When I study fish, I look not only at the behavior of an individual fish, but also how the school moves.

“When a vessel begins an illegal activity, the legal boats often begin acting differently. They get out of the area. Those anomalous responses can be telling.”

Once the algorithms have been developed, the researchers will train those using datasets of recorded instances of maritime IUU activities, eventually using that data to develop a model to help make real-time predictions of such activities and, inevitably, to develop tools for intervention.

Watson expects the data to be made available to “anyone interested in, or has a vested interest in, the oceans and what happens at sea.” In other words, coast guards and navies around the world, as well as fishermen, humanitarian NGOs, conservation groups and shipping companies to name a few.

By harnessing the power of both big data and AI, scientists and researchers all over the world are making it possible to make predictions about everything from the ideal conditions for delivering a child to predicting when and where a criminal might strike.

To contact the author of this article, email mdonlon@globalspec.com