Researchers Say AI Model Could Be Used To Predict Earthquakes 24 Hours In Advance

The AI model may be able to predict earthquakes with a magnitude 6 or higher a full day in advance by analyzing earthquake data in the region from the previous 30 days. | Image enhanced by Donald Standeford

By Donald Standeford, SJ Founder/Publisher
October 25, 2022 02:00 pm UTC
Modified: 2022-10-25 02:00 pm

Top Stories | About | Early Access | Follow

TAIWAN - Joint research carried out by the NCHC, and Academia Sinica say that they have developed an artificial intelligence (AI) model that could predict earthquakes a day in advance.

The National Center for High-Performance Computing (NCHC) headquartered at Hsinchu Science and Industrial Park, Hsinchu City, Taiwan, and Academia Sinica headquartered in Nangang, Taipei, Taiwan have been jointly researching the artificial intelligence model, basing data on "precursors of tectonic activity," according to Taiwanese news, Taipei Times.

The research team is being led by led by Academia Sinica researcher Lee Lou-chuang (李羅權) and NCHC associate researcher Tsai Tsung-che (蔡宗哲) and is developing an AI model that uses total electron content (TEC) data which is then processed using a Taiwania 2 supercomputer.

According to the Taiwanese news site, the model may be able to predict earthquakes with a magnitude 6 or higher a full day in advance by analyzing earthquake data in the region from the previous 30 days, according to the team.

The team used the model to analyze TEC data from Europe from 2003 to 2014, and said that "By filtering out certain information such as the disturbance storm time index, sunspot data, and the solar radiation index, we were able to accurately determine hourly TEC changes".

They used data from 19 cases of TEC changes where an earthquake did not happen in order to improve the accuracy of the AI model," National Taiwan University researcher Chuang Hao-kun (莊皓琨) was cited by the Taipei Times as saying.

"The system can now predict when a magnitude 6 or higher earthquake will occur, but we are still limited by the resolution of ionospheric data, and we cannot say for sure where the epicenter will be."

"We also have to work with a data transmission delay of five days or so, since our global ionospheric data are provided by Europe,” he reportedly said.

The Taiwanese news agency also cited Academia Sinica researcher Fu Ching-chou (傅慶州) as saying that before a major earthquake happens, the concentration of radon levels in the ground changes. The levels increase as the intensity of the earthquake increases in relation to the proximity of the epicenter, or the very center of the earthquake's radius.

"We hope that through all of these factors we will be able to determine more accurately when a major quake will occur so that we can notify people and ensure their safety,” Taipei Times cited him as saying.

Artificial intelligence (AI) works by combining large amounts of data with complex algorithms and a fast processor/processors, usually a supercomputer, in order to analyze and recognize patterns in the data.

The amount of data that can be analyzed by artificial intelligence is only limited to the processing power of the computer that is running the algorithms.

Though there are some limitations as opposed to using a human brain to analyze information, artificial intelligence has grown more and more complex and efficient at analyzing data over recent years.