Newswise – Long considered a myth, terrifyingly large rogue waves are very real and can wreck ships and even damage oil rigs. Using 700 years of wave data from more than a billion waves, scientists from the University of Copenhagen and Victoria University used artificial intelligence to find a formula to predict the emergence of these sea monsters. New knowledge can make shipping safer.
Embargoed content until Monday, November 20, 2023 at 3:00 PM EST
Tales of monster waves, called rogue waves, have been the story of sailors for centuries. But when a 26m rogue wave hit the Norwegian oil rig Draupner in 1995, digital instruments were there to capture and measure the North Sea monster. It was the first time a hoaxer had been measured and provided scientific evidence that abnormal ocean currents do exist.
Since then, these extreme waves have been the subject of many studies. And now researchers from the University of Copenhagen‘The Niels Bohr Institute used artificial intelligence methods to discover a mathematical model that provides a recipe for how rogue waves can occur, and especially when.
With the help of huge data on ocean movement, researchers can predict the probability of a monster wave hitting the sea at any time.
“Basically, it's very bad luck when one of these giant waves hits. They're caused by a combination of many factors that haven't been combined into a single risk assessment before. In the study, we identified the causal variables that create rogue waves and used artificial intelligence to collect them in a model , which can calculate the probability that rogue waves will occur,” says Dion Hafner.
Hafner is a former postdoctoral fellow at the Niels Bohr Institute and the first author of a scientific study recently published in a prestigious journal. Proceedings of the National Academy of Sciences (PNAS).
Rogue waves happen every day
In their model, the researchers combined existing data on ocean movement and sea state, as well as water depths and bathymetric information. Most importantly, wave data was collected from buoys at 158 different locations along the US coast and overseas territories that collect data 24 hours a day. Combined, this data – from more than a billion waves – spans 700 years‘ Wave height and sea state information.
The researchers analyzed many types of data to find the causes of rogue waves, defined as waves that are at least twice as high as surrounding waves — including extreme rogue waves that can be more than 20 meters high. Using machine learning, they converted all of this into an algorithm that they then applied to their database.
“Our analysis shows that abnormal waves happen all the time. In fact, we have registered 100,000 waves in our database that can be defined as evil waves. That's about 1 monster wave that happens every day in any random place in the ocean. However, they are not‘Monster waves of all extreme sizes,” explains Johannes Gemrich, research‘Second author.
Artificial intelligence as a scientist
Artificial intelligence helped the researchers in the research. They used several AI methods, including symbolic regression, which provides an equation as an output, rather than just returning a single prediction, as traditional AI methods do.
By studying more than 1 billion waves, the researchers' algorithm analyzed its own way to determine the causes of rogue waves and compiled it into an equation that describes the recipe for a rogue wave. AI learns the causality of a problem and sends that causality to humans in the form of an equation that researchers can analyze and incorporate into their future research.
“For decades, Tycho Brahe collected astronomical observations from which Kepler, through much trial and error, managed to extract Kepler's laws. Dion used machines with waves, what Kepler did with planets. It's still shocking to me that something like this. It's possible,” says Markus Jochum.
The phenomenon has been known since 1700
New research also debunks common perceptions about what causes haughty waves. Until now, the most common cause of a rogue wave was thought to be when one wave briefly merged with another and stole its energy, causing one large wave to move.
However, the researchers claim that the most dominant factor in the materialization of these strange waves is what is known as “linear superposition”. The phenomenon, known since the 1700s, occurs when two wave systems cross and reinforce each other for a short period of time.
“If two wave systems meet offshore in a way that increases the chance of high crests followed by deep troughs, there is a risk of extremely large waves.” This is knowledge that has existed for 300 years and that we are now confirming with data. Dion Hafner says.
The researchers' algorithm is good news for the shipping industry, which has about 50,000 cargo ships around the planet at any given time. Indeed, with the help of an 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 endanger anyone at sea.
“Because shipping companies plan their routes in advance, they can use our algorithm to assess the risk of whether there is a chance of hitting dangerous waves along the way. Based on that, they can choose alternative routes,” says Dion Hafner. .
Both the algorithm and the research are public, as are the weather and tide data used by the researchers. Therefore, Dion Hafner says, stakeholders such as government agencies and weather 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.
“AI and machine learning are typically black boxes that do not augment human understanding. But in this study, Dion used artificial intelligence methods to transform a huge database of wave observations into a new equation for the probability of rogue waves that is easily understood by humans and related to the laws of physics.” , – concludes Professor Markus Jochum, Dion‘Dissertation supervisor and co-author.
Read the paper “Machine-guided detection of real-world rogue wave models” published in PNAS: https://www.pnas.org/cgi/doi/10.1073/pnas.2306275120
Read Wikipedia's list of registered scams: https://en.wikipedia.org/wiki/List_of_rogue_waves
Dion Hafner's research continues in St Pasteur Laboratories.