The artificial intelligence model could predict an earthquake of magnitude 6 or more a day in advance by analyzing data from the previous 30 days

  • By Yang Yuan-ting and William Hetherington/staff reporter, with a staff editor

The National Center for High-Performance Computing (NCHC) and Academia Sinica have developed an artificial intelligence (AI) model that could help researchers predict earthquakes a day in advance.

The model could predict earthquakes based on precursors to tectonic activity, the researchers said.

The research team, led by Academia Sinica researcher Lee Lou-chuang (李羅權) and NCHC associate researcher Tsai Tsung-che (蔡宗哲), developed an AI model using total electronic content data (TEC) and the Taiwania 2 supercomputer.

Photo: Jameson Wu, Reuters

The model could predict an earthquake of magnitude 6 or greater a day in advance by analyzing data from the previous 30 days, they said.

Previous studies have also found that the atmospheric TEC within a radius of 50 km from an earthquake’s epicenter shows signs of change before a large earthquake, the Central Meteorological Bureau’s Seismological Center said, adding that the TEC over Taiwan proper was weak just before the 1999 Jiji earthquake.

National Taiwan University researcher Chuang Hao-kun (莊皓琨), who was also part of the research team, said on Saturday that the team analyzed TEC data from Europe covering the period 2003 to 2014. .

“By filtering out some information such as storm disturbance weather index, sunspot data and solar radiation index, we were able to accurately determine hourly changes in the TEC,” he said. .

The team also used data from 19 cases of TEC changes in which an earthquake did not occur to improve the accuracy of the AI ​​model, he said.

“The system can now predict when an earthquake of magnitude 6 or greater will occur, but we are still limited by the resolution of the ionospheric data, and we cannot say for sure where the epicenter will be,” he said. -he declares.

“We also have to work with a data transmission delay of around five days, since our global ionospheric data is provided by Europe,” he added.

The team also found that the concentration of radon levels in the ground changes before a major earthquake, said Academia Sinica researcher Fu Ching-chou (傅慶州), adding that the level of change increases with earthquake intensity and proximity to the epicenter.

“We hope that with all of these factors, we will be able to more accurately determine when a major earthquake will occur, so that we can inform people and keep them safe,” he said.

The team’s findings were published by the journal Earth and Space Science.

Comments will be moderated. Keep comments relevant to the article. Remarks containing abusive and obscene language, personal attacks of any kind or promotion will be removed and the user banned. The final decision will be at the discretion of the Taipei Times.