Artificial intelligence finds formula for how to predict huge waves using 700-year-old data

Artificial intelligence finds formula for how to predict huge waves using 700-year-old data

This article has been reviewed in accordance with Science

Fact check

Peer-reviewed publication

trusted source


Credit: Pixabay/CC0 Public Domain

× Close

Credit: Pixabay/CC0 Public Domain

Long considered a myth, huge rogue waves are very real and can split ships and even damage oil rigs. Using 700 years of wave data from more than a billion waves, scientists at the University of Copenhagen and Victoria University used artificial intelligence to find a formula for how to predict the occurrence of these sea monsters. New knowledge could make shipping safer.

Stories about monster waves, called rogue waves, have been the lore of sailors for centuries. But when a rogue 26-meter wave hit the Norwegian oil platform Drubner in 1995, there were digital tools to capture and measure the North Sea monster. This was the first time a rogue fish had been measured and provided scientific evidence that abnormal ocean waves actually exist.

Since then, these extreme waves have been the subject of many studies. Now, researchers from the University of Copenhagen’s Niels Bohr Institute have used artificial intelligence methods to discover a mathematical model that provides a recipe for how rogue waves occur – and not least when.

With the help of huge amounts of big data about ocean movements, researchers can predict the probability of being hit by a huge wave at sea at any time.

“Basically, it’s just very bad luck when one of these giant waves hits. 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 causal variables that create “Rogue waves and uses artificial intelligence to collect them into a model that can calculate the probability of a rogue wave forming.”

Hafner is a former Ph.D. student at the Niels Bohr Institute and first author of the scientific study published in the journal Proceedings of the National Academy of Sciences (With people).

Rogue waves happen every day

In their model, the researchers combined available data on ocean movements and sea state, as well as water depths and bathymetric information. Most importantly, wave data was collected from buoys at 158 ​​different locations around the US coast and overseas territories that collect data 24 hours a day. When combined, this data – from more than a billion waves – contains 700 years’ worth of wave height and sea state information.

Researchers analyzed many types of data to find the causes of rogue waves, which are defined as waves at least twice as high as the surrounding waves, including extreme rogue waves that can be more than 20 meters high. Through machine learning, they turned all of that into an algorithm that was then applied to their dataset.

“Our analysis shows that abnormal waves happen all the time. In fact, we recorded 100,000 waves in our data set that could be defined as rogue waves. This equates to about one monster wave occurring every day in any random place in the ocean. However, Johannes explains Gemmrich, the second author of the study, says that not all of them are monster waves of large size.

Dion Hafner defends his Ph.D. Thesis “An ocean of data – inferring the causes of rogue waves in the real world” at the Niels Bohr Institute, University of Copenhagen. Source: Niels Bohr Institute/University of Copenhagen.

× Close

Dion Hafner defends his Ph.D. Thesis “An ocean of data – inferring the causes of rogue waves in the real world” at the Niels Bohr Institute, University of Copenhagen. Source: Niels Bohr Institute/University of Copenhagen.

Artificial intelligence as a scientist

In the study, the researchers were assisted by artificial intelligence. They used several AI methods, including symbolic regression which gives an equation as output, rather than just returning a single prediction as traditional AI methods do.

By examining more than a billion waves, the researchers’ algorithm analyzed its own method for finding the causes of rogue waves and condensed them into an equation that describes the recipe for a rogue wave. AI learns the causality of a problem and transmits this 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, with much trial and error, was able to derive Kepler’s laws. Dione used machines to do to waves what Kepler did to planets. To me, it is still shocking that something like this could happen,” says Markus Jochum. This is possible”.

A phenomenon known since the eighteenth century

The new study also contradicts the common perception of what causes rogue waves. Until now, the most common cause of a rogue wave was thought to be when one wave briefly combines with another and steals its energy, causing a large wave to continue.

However, researchers have proven that the most influential factor in rendering these strange waves is what is known as “linear superposition.” This phenomenon, known since the 18th century, occurs when two wave systems cross over each other and reinforce each other for a brief period of time.

“If two wave systems meet at sea in a way that increases the chance of generating high crests followed by deep troughs, the risk of very large waves arises. This is knowledge that has been around for 300 years and which we now support with data,” says Dion Hafner.

Safer shipping

The researchers’ algorithm is good news for the shipping industry, which at any given time 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 there will be this “perfect” combination of factors to increase the risk of a massive wave that could pose a danger to anyone at sea.

“Since shipping companies plan their routes in advance, they can use our algorithm to get a risk assessment to see if there is a chance of encountering dangerous rogue waves along the way. Based on that, they can choose alternative routes,” says Dion Hafner. .

Both the algorithm and research are publicly available, as is the weather and wave data published by the researchers. Therefore, Dion Haffner says, interested parties, such as public authorities and meteorological services, can easily start calculating the possibility of rogue waves. Unlike many other models created using artificial intelligence, all intermediate calculations in the researchers’ algorithm are transparent.

“Artificial intelligence and machine learning are usually black boxes that do not add to human understanding. But in this study, Dionne used AI methods to transform a massive database of wave observations into a new equation for the probability of rogue waves, which can be easily understood” by people. “It is related to the laws of physics,” concludes Professor Markus Jochum, Dionne’s thesis supervisor and co-author.

more information:
Hafner, Dion et al., Automated guided detection of rogue wave model in the real world, Proceedings of the National Academy of Sciences (2023). doi: 10.1073/pnas.2306275120.

Magazine information:
Proceedings of the National Academy of Sciences

You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *