The provisional toll from the violent earthquake that struck Morocco on the night of Friday September 8 to Saturday September 9 continues to increase. Monday morning, it stood at more than 2,100 dead, including 4 French people, according to the French Ministry of Foreign Affairs.

According to the National Center for Scientific and Technical Research, the epicenter of the earthquake was located in the province of al-Haouz, southwest of Marrakech, and the earthquake caused significant damage in several cities.

Over the past thirty years, earthquakes and the tsunamis they generate have caused the deaths of nearly a million people. If prediction as such of these events is impossible, warning systems have been put in place to limit the human and material cost of these disasters.

These systems do not predict the future, but try to detect earthquakes and estimate their magnitude as quickly as possible. Currently, they use seismic waves to try to warn populations a few seconds before the tremors, even if, unfortunately, the result is not always there.

In order to improve seismic and tsunami warning systems, we are currently working on an artificial intelligence (AI) algorithm, based on waves of gravitational origin, which estimates the magnitude of large earthquakes more reliably and more quickly. .

The earliest seismic signals recorded on seismometers are compression waves – called P waves. These waves propagate at about 6.5 km per second. If you are 65 km further from the epicenter than the nearest sensors, you will therefore feel the first tremors 10 seconds after these sensors recorded the first P waves. In practice, taking into account the transmission time and processing these waves, your 10 seconds will probably be reduced to 5 or 6.

Unfortunately, for both instrumental and fundamental reasons, P waves do not provide reliable information on the magnitude of very large earthquakes. Seismic warning systems, based on these waves, thus prove incapable of differentiating between a magnitude 8 earthquake and a magnitude 9 earthquake, posing a major problem for tsunami estimation, as illustrated the example of Fukushima in 2011. Indeed, a magnitude 9 earthquake is thirty times “bigger” than a magnitude 8 earthquake, the tsunami it generates is therefore considerably larger.

To more reliably estimate the magnitude of large earthquakes, warning systems based on another type of wave, called W phase, have been developed. The W phase has much better sensitivity to magnitude than P waves, but propagates much more slowly. It is recorded between ten and thirty minutes after the origin of the earthquake, or shortly before the arrival of the tsunami.

In 2017, previously unknown signals were discovered. These signals, called “Pegs” for “prompt elasto-gravity signals”, have provided a glimpse of a new possibility of estimating the magnitude of large earthquakes more quickly and more reliably.

Since gravity is an acceleration and seismometers record the acceleration of the ground, Pegs are recorded by our “classic” measuring instruments. In addition, these signals are very sensitive to magnitude, much more than P waves in the case of large events.

Pegs therefore have the ideal characteristics to power an alert system. However, their detection is made difficult by their very low amplitude – around a million times weaker than P waves. How can we exploit such weak signals to alert?

Emerging AI technology is proving highly effective at quickly extracting weak signals from large volumes of noisy data. We have developed an AI algorithm that estimates, every second, the magnitude of the current earthquake from Pegs, published very recently in Nature. As large earthquakes are rare, we simulated hundreds of thousands of possible earthquake scenarios along Japan’s major faults.

In each scenario, we calculated the expected Pegs on all seismometers in the region and trained the AI ​​to “find” the magnitude and location of the earthquake by giving it the answer each time. We then tested the performance of the AI ​​on the data recorded during the Fukushima earthquake.

The results indicate that we could have estimated the magnitude of the earthquake as soon as the rupture ended – i.e. 2 minutes after the origin of the event – ​​and therefore very quickly obtained a much better estimate of the height of the wave.

The results being encouraging, we are now moving on to the phase of implementing the algorithm in an operational alert system, starting with Peru where we are expecting a very big event, which could occur tomorrow or in three hundred or six hundred years.

We are also working to improve the algorithm’s performance for earthquakes of more moderate magnitude. It works in its current version for earthquakes of magnitude greater than 8.3, which already makes it very useful for estimating tsunamis – which only concern these very large earthquakes –, but greatly limits the possibilities for warning about tremors – these are felt in most cases before the earthquake reaches such magnitude.

Finally, we aim to develop a global version of this algorithm, which would use seismometers to alert on earthquakes occurring anywhere on Earth, thus offering a particularly interesting global alert “coverage” for poorly equipped regions.

*Quentin Bletery is a geophysicist, research fellow at the Géoazur laboratory of the Research Institute for Development (IRD)