In 1995, a lone wave 26 meters high crashed into the Norwegian oil platform Draupner in the North Sea. It was the first time that it was possible to measure this type of waves, also called errant or monstrous waves, until that date considered more of a sailors’ myth. There are more similar stories. In April 2005, the Norwegian Dawn was hit by three gigantic waves that seemed to come out of nowhere while it was sailing off the coast of Norway. “The sea was completely calm when a 21-meter wave seemed to come out of the air… Our captain, who has been in this job for 20 years, said that he had never seen anything like it,” one of the crew said at the time. . In 2001 two other ships, the Bremen and the Caledonian Star, suffered serious damage to their structures when they encountered a huge wave in the South Atlantic. All their windows were blown out. “It was like a mountain, a wall of water coming against us,” the captain of the Caledonian Star himself would later declare.
Researchers at the Niels Bohr Institute at the University of Copenhagen have used artificial intelligence to discover a mathematical model that anticipates when and how these gigantic waves may occur. The results have just been published in the journal ‘Proceedings of the National Academy of Sciences’ (PNAS).
In their model, the researchers combined available data on ocean motions and sea state, as well as water depths and bathymetric information. Wave data was collected from buoys at 158 different locations around the coasts of the US and overseas territories that collect data 24 hours a day. When combined, this data (from more than a billion waves) contains 700 years of information about wave height and sea state.
Researchers analyzed many types of data to find the causes of solitary waves, including extreme ones that can be more than 20 meters high. Using machine learning, they transformed everything into an algorithm that they then applied to their data set.
100,000 lonely waves
«Our analysis shows that abnormal waves occur all the time. In fact, we recorded 100,000 waves in our data set that can be defined as solitary waves. This equates to about one monster wave every day at any random location in the ocean. However, not all of them are monster waves of extreme size,” explains Johannes Gemmrich, co-author of the study.
By examining more than a billion waves, the researchers’ algorithm analyzed its own way of finding the causes of this phenomenon and condensed them into an equation that describes the recipe for a rogue wave. The AI learns the causality of the problem and communicates it to humans in the form of an equation that researchers can analyze and incorporate into their future research.
The new study also breaks with the common perception of the causes of solitary waves. Until now, the most common cause was believed to be when one wave briefly combined with another and stole its energy, causing a large wave to move forward.
However, the researchers establish that the most dominant factor is what is known as “linear overlap.” The phenomenon, known since the 18th century, occurs when two wave systems intersect and reinforce each other for a short period of time.
“If two wave systems meet in the sea in a way that increases the possibility of generating high crests followed by deep troughs, the risk of extremely large waves arises. This is knowledge that has been around for 300 years and that we now back up with data. » says Dion Häfner, lead author of the study.
Assess the risk
The researchers’ algorithm may be useful to the shipping industry, which has approximately 50,000 cargo ships sailing around the planet. In fact, with the help of the algorithm, it will be possible to predict when this “perfect” combination of factors is present to raise the risk of a monster wave that could pose a danger to anyone at sea.
“As shipping companies plan their routes well in advance, they can use our algorithm to assess risk and determine if there is a chance of encountering dangerous waves along the way. Based on this, they can choose alternative routes,” says Dion Häfner.
Both the algorithm and the research are publicly available, as is the weather and wave data used by the researchers. Therefore, Häfner ensures that interested parties, such as public authorities and meteorological services, can easily begin to calculate the probability of solitary waves occurring.
