The study was published in ‘Scientific Reports’. What would be its main use? Preventive. It can anticipate the event up to five minutes. The tool that predicts giant waves has a high level of precision.
The authors are Thomas Breunung and Balakumar Balachandran of the University of Maryland in the US. They suggest the tool could be used to provide advance warnings to ships and offshore platforms so that those working on them can seek shelter, make emergency stops or manoeuvre to minimise the impacts of approaching giant waves.

Training
The tool they developed consists of a neural network. It was trained to distinguish ocean waves that will be followed by rogue waves from those that will not. The authors trained the neural network using a data set. It consists of 14 million 30-minute samples. And they come from sea surface elevation measurements from 172 buoys located near the coasts of the continental United States and Pacific islands. They used their tool to predict the occurrence of rogue waves using a separate data set. This one consists of 40,000 sea surface elevation measurements from the same buoys.
The authors found that their tool was able to correctly predict the occurrence of 75% of rogue waves one minute in advance. And 73% of rogue waves five minutes in advance. In addition, it predicted rogue waves near two buoys not included in the datasets used in training. And it was 75% accurate one minute in advance. This highlights that the tool may be able to predict rogue waves in new locations.

Best predictions
The tool that predicts rogue waves is still under development. The authors suggest that the accuracy and warning time could even be improved further. It should incorporate data on water depth, wind speed and wave location. Future research could also make it possible to predict the height of the next rogue wave, including the timing of the wave, they add.