Israeli research team shows how AI can help predict future earthquakes

A research team from an Israeli university recently published a report showing how artificial intelligence could be used to predict earthquakes in the future. 

The team of researchers from Ariel University’s Department of Physics, led by Dr. Yuval Reuveni, used AI to analyze ionospheric Total Electron Content (TEC) time series estimations from GPS satellites to identify precursors to an earthquake to help create more accurate predictions. 

Using a type of machine-learning algorithm called a support vector machine (SVM), the team looked at the connection between the TEC of the ionosphere and geodynamic activity. 

The results of the report were published in the peer-reviewed journal, Remote Sensing, which noted that “observational and modeling results have confirmed the existence and detectability of earthquake and tsunami signatures in the ionosphere caused by both acoustic and gravity waves.” 

The idea for the study came after researchers noticed ionospheric perturbations just before the 2011 earthquake and tsunami in Japan. 

The team analyzed GPS ionospheric TEC data between the years 1998 and 2021, and excluded any that had significant sunspots or solar flare activity in order to focus only on earth-originating ionospheric perturbations. 

“Our experimental results show that using GPS ionospheric TEC enhancement as an earthquake precursor predictor can be potentially useful for large earthquakes, with an accuracy of 83%,” according to the report.

“While this is not yet a foolproof method of predicting earthquakes, it is a promising step forward in our efforts to better understand and anticipate seismic activity," Reuveni added.

The ubiquity and low cost of GPS satellites in evaluating TEC make them an ideal choice for research over other more expensive methods. Those same GPS satellites can then be utilized to give warnings about upcoming earthquakes. 

Last week, research released by a team from the Hebrew University of Jerusalem demonstrated that fiber optics could detect some early signs of earthquakes. The research was similar in its use of existing communications equipment, particularly undersea fiber optic cables used for internet communication. 

Ionospheric TEC is a measure of the total number of free electrons in a column from the earth’s surface to the top of the ionosphere. The ionosphere is a region of the earth’s upper atmosphere which experiences significant ionization from solar radiation. This affects radio waves. Measuring TEC is an important parameter in satellite-based navigation systems, such as GPS (global-positioning systems). 

An SVM is a supervised machine learning algorithm used for classification tasks. It is often used in AI systems for image classification, text classification and bioinformatics.