Hashish and pirates: How AI is cleaning up the high seas

The state of maritime monitoring hasn't changed much in generations. Pirates beware; AI is changing that.
Written by Greg Nichols, Contributing Writer

On August 8th, 2021, Spanish police and customs agents intercepted the cargo ship NATALIA on suspicion of narcotics trafficking. The ship was en route from Lebanon via Iskenderun, Turkey, to Lagos, Nigeria, and hidden on board was nearly 20 tons of hashish worth $470 million.

That may sound like the opening scene of an action flick, but it's the kind of occurrence that happens more frequently than you might expect on the high seas. Drug smuggling, illegal fishing, and piracy are constant threats. Following a number of recent piracy incidents in the Gulf of Aden, Iran, Russia, and China recently began naval and air drills seeking to counter maritime piracy. The problem is that these crimes are very difficult to track and police.

How can nations effectively monitor their seas to make countering piracy and other maritime-based criminal activity more efficient?

Maybe it's because I live on a sailboat with my family, but I'm fascinated by the evolving efforts to monitor our oceans in an increasingly complex law enforcement paradigm. Artificial intelligence, not surprisingly, is a tool used increasingly frequently for the challenging job of keeping the seas (and global commerce) secure.

The NATALIA is a great example and a telling case study for a company called Windward, which used risk models to detect criminal activity via markers like anomalous loitering. In this case, Windward helped European authorities intercept a ship with hundreds of millions of dollars of illicit drugs on board. 

To find out more about the use of AI in maritime law enforcement, I connected with Ami Daniel, co-founder and CEO of Windward, who believes that AI modeling can help nations understand the state of the seas, enabling them to make better decisions based on data. Factoring into consideration each individual vessel's behavior, type of cargo on board, ports and docks visited in the past, routes sailed, cruising speed, and more, it's possible to use AI models to predict whether a vessel is engaging in illicit behavior.

Greg Nichols: What's the current state of global sea monitoring? What technologies are most used today, and where are the shortcomings?

Ami Daniel: In general, most global reactions to maritime crime are reactive, with governments only acting once an event becomes relevant to their domain. If a crime occurs in international waters, most nations will pass the buck and won't see it as a priority until it approaches their borders. Comprehensive Maritime Domain Awareness (MDA) -- defined by the International Maritime Organization (IMO) as the understanding of anything associated with the maritime domain that could impact the security, safety, economy, or environment -- is essential for handling maritime issues. However, a physical maritime presence is not nearly enough to monitor a country's shores, let alone the whole sea. 

At any given moment, there is $14T worth of cargo, hundreds of millions of containers, and over 50K merchant ships in operation at sea that global authorities need to be aware of. These authorities face many challenges, ranging from information overload, an incomplete picture of all the vessels at sea and related counterparties, and fragmented data when protecting their maritime borders from illicit activities. There's also an inherent confusion by design in maritime trade, with complex ownership structures, geopolitical tensions, and deep interdependencies. 

Currently, the main tool for MDA is Automatic Identification Systems (AIS) which is essentially a mandatory GPS for vessels that transmits their location. However, AIS is susceptible to manipulation, both by individual vessels as well as by governments, as China did in November last year. Vessels can turn off their AIS, both for legitimate and illegitimate purposes, making it incredibly difficult to pinpoint where a vessel is at any given time. Added to this complexity is a new method of deceptive shipping practices, which was uncovered by Windward last year, called GNSS manipulation, wherein bad actors can spoof their location, so their AIS signal transmits from a completely different location somewhere across the globe. The discovery, which was covered extensively, has massive global and national security implications and demonstrates how nefarious actors are upgrading their sanctions evasion techniques from low-tech deceptive shipping practices to military-grade technologies and electronic warfare tactics.

In light of these advancements, legacy methods of MDA are not enough. To protect borders and businesses, organizations and law-enforcement agencies must take a proactive approach toward maritime crime. 

GN: What's at stake if nations are unable to effectively monitor their oceans?

Ami Daniel: Nations face countless maritime risks. The vastness of the waters and the relative isolation of vessels traveling through the ocean makes maritime crime appealing for criminals. Among the risks governments face if they cannot effectively monitor their oceans are sanction evasion and drug smugglingHuman trafficking is a serious human rights issue, and like drug smuggling, much of it takes place at sea. We hear heartbreaking news stories of ships crammed full of people being transported across the world. Labor trafficking is the effective equivalent of modern-day slave labor, another major issue that doesn't get enough attention. Maritime workers endure inhumane conditions, sometimes working 20-hour workdays, seven days a week, for little to no pay. 

There are also environmental risks that can happen when nations are unable to effectively monitor their territorial waters. Illegal, unreported and unregulated fishing, which has both environmental and geopolitical implications, accounts for approximately $23.5 billion worth of seafood every year, with around 1 out of 5 fish taken from the ocean. In addition, while the sheer number of oil spills each year is decreasing, the environmental damages incurred are still massive, and in February 2021, there was an oil spill off the coast of Israel. Windward was able to work with the government to eventually identify the culprit, but with effective monitoring, the spill could have been detected much earlier, with a smaller impact on the environment. 

GN: Predictive policing and enforcement depend largely on accurate training sets, right? What kinds of data are being used to train your AI monitoring solution? How can errors be mitigated to avoid false positives?

Ami Daniel: Windward's algorithms were developed from over a decade of analyzing vessel behavior and are powered by advanced AI technology, trained on behavioral analysis models, and over 10 billion data points. To create accurate models, Windward utilizes various sources of data, including data from vessels, ports, and flag registries, combined with satellite data, AIS data, weather data, and more. 

Windward's maritime expertise and comprehensive analysis of vessels lower the risk of false positives by 4X compared to traditional methods of vessel investigation. The platform screens, searches, and analyzes dynamic data to connect the dots and discover potential risks. By continuously applying behavioral analysis models, Windward's solution provides dynamic Predictive Intelligence based on vessel identity, cargo visibility, ownership structures, true location, and voyage patterns that is accurate and effective, empowering authorities to make go-no-go decisions. 

GN: Has your system been deployed effectively? Can you please describe where and how and what the results have been?

Ami Daniel: Windward has various clients across the public sector, including the UN Security Council; the US Drug Enforcement Administration (DEA); the US Coast Guard; Frontex, the European Border and Coast Guard Agency; The Maritime Analysis and Operations Centre-Narcotics (MAOC (N)), an EU Law Enforcement unit created to respond to the threat of illicit drug trafficking by maritime and air conveyances; The Caribbean Community Implementation Agency for Crime and Security (CARICOM IMPACS); the Israeli Navy; and the Indian Navy

Windward's platform is also used to monitor Marine Protected Areas (MPAs) by the Sea Shepherd Conservation Society, an international organization on a mission to protect all marine animals. 

While we can't publicize the internal investigations of the authorities using Windward's technology, we can provide specific case studies that are public (see case study).  

Editorial standards