Giant waves pose a danger to navigation and oil platforms. However, until now there were no tools to predict its formation. Anticipating will be possible thanks to the application of Artificial Intelligence (AI), according to a study carried out by the Niels Bohr Institute at the University of Copenhagen.
The authors have used AI methods to discover a mathematical model that provides a recipe for how and when waves of this size can occur, “caused by a combination of many factors.”
“In the study, we mapped the causal variables that create rogue waves and used AI to assemble them into a model capable of calculating the probability of rogue wave formation,” explains Dion Häfner, former PhD student at the Niels Bohr Institute and first author of the scientific study, which is 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 depth and bathymetric information. More importantly, the wave data was collected from buoys located at 158 different locations along the coasts of the US and overseas territories that collect data 24 hours a day. In total, data was collected from more than one billion waves, containing 700 years of information.
In the study, the researchers were helped by artificial intelligence. They used several AI methods, including symbolic regression, which results in an equation, rather than returning a single prediction, as traditional AI methods do.
By examining more than a billion waves, the researchers' algorithm has analyzed its own path to finding the causes of rogue waves and condensed it into an equation that describes the recipe for a rogue wave.
According to the authors, the study also breaks with the common perception of the causes of rogue waves. Until now, the most common cause of a rogue wave was believed to be when one wave briefly combined with another and stole its energy, causing a large wave to follow its path. However, they establish that the most dominant factor in the materialization of these waves is what is known as "linear superposition."
"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 existed for 300 years and which we now support with data," Häfner continues.
Häfner says that interested parties, such as public authorities and meteorological services, can easily start calculating the probability of rogue waves. And unlike many other models created using artificial intelligence, all intermediate calculations of the researchers' algorithm are transparent.
