Scientists at the University of Copenhagen and The University of Victoria have used artificial intelligence to find a formula to predict of rogue waves. The study analyzed over 1 billion waves to find out what causes the unpredictable behemoths.
Until recently, rogue waves were considered to be a myth. However, in the past few decades they have finally been accepted by scientists, who define them as open ocean waves that are twice as large as the average surrounding waves. They are also notoriously unpredictable. “Basically, it is just very bad luck when one of these giant waves hits,” Dion Häfner, first author of the study, told phys.org. “They are caused by a combination of many factors that, until now, have not been combined into a single risk estimate. In the study, we mapped the causal variables that create rogue waves and used artificial intelligence to gather them in a model which can calculate the probability of rogue wave formation.”
The team used data mining and interpretable machine learning to analyze a huge amount of observational data. The study used FOWD (The Free Ocean Wave Dataset), a wave catalogue based on data recorded by buoys in 158 different locations around the US coasts and overseas territories, based on raw data from CDIP (Coastal Data Information Program). This catalogue constituted 1.5 billion waves in total, 100,000 of which fit the criteria for rogue waves. They then used the wave dataset to train an AI network, which then returned a mathematical equation synthesizing the various causes of rogue waves. This equation was then interpreted using existing wave theory to produce a model that can both reproduce behavior we’ve previously seen in rogue waves, as well as predict future ones.
“Over decades, Tycho Brahe collected astronomical observations from which Kepler, with lots of trial and error, was able to extract Kepler’s Laws. Dion used machines to do with waves what Kepler did with planets. For me, it is still shocking that something like this is possible,” says Professor Markus Jochum, Dion’s thesis supervisor and co-author.
As a result, the new model could make for safer shipping. Not only are we now better capable of better predicting rogue waves that could pose a danger for open ocean vessels, but the means to use the model have been made readily available to the public. The algorithm and research, as well as the weather and wave data deployed by the researchers, is al available to the masses. “As shipping companies plan their routes well in advance, they can use our algorithm to get a risk assessment of whether there is a chance of encountering dangerous rogue waves along the way,” says Häfner. “Based on this, they can choose alternative routes.”