China pioneers AI model able to detect seismic signals

China is increasing its reliance on artificial intelligence (AI), the latest being the development of a large language model (LLM) designed to predict the occurrence of earthquakes.

Dubbed DiTing, the AI model can monitor seismic activity and identify minute signal changes, helping authorities recognize potential earthquake incidents. The model achieves its aim by scouring through data from several sources and processing them to make accurate predictions.

The bulk of the data comes from the China Earthquake Observation Network, which has a seismic monitoring network sprawled across Mainland China. DiTing will also use data from satellite technology and collaborate with neighboring countries to create a pool of seismic data.

“DiTing relies on massive amounts of data from the China Earthquake Observation Network and advanced artificial intelligence technology and has significantly improved the accuracy and speed of seismic signal recognition,” said Chen Shi, deputy director of the China Earthquake Administration’s Institute of Geophysics.

Compared to traditional seismic signal reading methods, DiTing can make faster predictions for earthquake incidents with less room for errors. Being able to spot earthquake incidents on time is expected to play a critical role in mitigating disasters and providing relief for survivors.

Trained on seven years of seismic data, the model is retrofitted with 100 million parameters, a decent number for a pioneering offering, with researchers hinting at future upgrades. Apart from predicting earthquake incidents, the researchers say the model could find new use cases in oil and gas exploration since the industry typically relies on seismic data.

“More than 95% of oil and gas fields discovered in the world mainly rely on seismic exploration,” said Wang Jianbo, deputy director at the China Earthquake Networks Centre. “DiTing can deduce whether the underground contains oil and gas by learning the waveform characteristics of oil storage areas.”

The AI model is the brainchild of the National Supercomputing Centre based out of Chengdu and researchers from Tsinghua University. The university has been at the bleeding edge of innovation in China, participating in blockchain technology and AI experiments since 2021.

Leaning on AI

Keen to become a global leader in AI, Chinese authorities are finding new public use cases for the technology, leading the way for private enterprises. A group of experts turned to AI to predict changes in weather conditions to mitigate climate disasters, noting higher levels of accuracy when compared with traditional methods.

Chinese-based AI models have seen myriad applications in the automobile manufacturing sector and robotics, showing little to no signs of slowing down. On the international stage, a Chinese-backed resolution has garnered support from United Nations member states as the Asian superpower attempts to limit United States influence in the emerging ecosystem.

In order for artificial intelligence (AI) to work right within the law and thrive in the face of growing challenges, it needs to integrate an enterprise blockchain system that ensures data input quality and ownership—allowing it to keep data safe while also guaranteeing the immutability of data. Check out CoinGeek’s coverage on this emerging tech to learn more why Enterprise blockchain will be the backbone of AI.

Watch: Transformative AI applications are coming