Greek scientists in the US have developed a new technique that allows extreme and rare events in society and nature to be predicted, such as a pandemic, an unexpected rogue wave at sea or the sudden collapse of a large bridge, even if there are insufficient historical data to work off.
The “smart” method, which bypasses the need for a large amount of previous data, is a combination of a sophisticated artificial intelligence (machine learning) system with special sampling techniques.
The professors of mechanical engineering and ocean science Themistoklis Sapsis of the Massachusetts Institute of Technology (MIT) and applied mathematics & engineering George Karniadakis of Brown University, Rhode Island, together with two of their American colleagues, made the relevant publication in the computational science journal “Nature Computational Science” .
The scientists combined statistical algorithms (which need less data to make accurate and efficient predictions) with a powerful machine learning technique called DeepOnet developed in 2019 at Brown University by Karniadakis and now “trained” to predict scenarios, probabilities and some times a year of rare events, despite the lack of relevant historical records.
Predicting future disasters from extreme events (earthquakes, pandemics, tidal waves, etc.) is terribly difficult, often because some such events are so rare that there is not enough data to use predictive models to predict what and when something similar may happen in the future.
The new study attempts to provide a solution to this problem by emphasizing the quality rather than the quantity of data already available.
“You have to realise that these are stochastic events. An outburst of pandemic like COVID-19, environmental disaster in the Gulf of Mexico, an earthquake, huge wildfires in California, a 30-metre wave that capsizes a ship — these are rare events and because they are rare, we don’t have a lot of historical data. We don’t have enough samples from the past to predict them further into the future. The question that we tackle in the paper is: What is the best possible data that we can use to minimise the number of data points we need?” said Karniadakis.
The researchers used the sampling technique called active learning, which involves statistical algorithms. These are combined with the computational model DeepOnet, a type of artificial neural network that mimics the neurons of the human brain. It is more powerful than standard artificial neural networks because it is actually made up of two separate networks that process data in parallel. This allows giant sets of data and scenarios to be analyzed at lightning speed and probabilities derived. When this possibility is combined with the intelligent statistical algorithms of active learning, then DeepOnet can make predictions of catastrophic events even when it doesn’t have much data to process.
“The key is not to take all the data possible and feed it into the system, but to look in advance for events that will signal rare events. We may not have many examples of the actual event, but they may have their precursor events. Through mathematics we identify them and these, along with real events, will help us train this data-hungry DeepOnet system ,” Karniadakis said.
In this way, the researchers calculated various probabilities for future outbreaks of a pandemic, or for the appearance out of nowhere of a massive wave twice to three times the size of neighbouring waves.
The researchers reported that their new method outperforms most existing prediction models, and they believe it can be leveraged to predict all kinds of rare events. Karniadakis is already working with environmental scientists to use the new technique in forecasting climate events, such as hurricanes.
In the paper, the research team outlines how scientists should design future experiments so that they can minimize costs and increase the forecasting accuracy. Karniadakis, for example, is already working with environmental scientists to use the novel method to forecast climate events, such as hurricanes.
Both T.Sapsis and G.Karniadakis are graduates of the School of Mechanical Engineering of the NTUA, with a PhD from MIT. Sapsis is, among other things, the holder of the 2021 Bodosakis scientific award.
READ MORE: Pierrakakis: Greece carried out digital reforms and is now in the sphere of the desirable.
