An artificial neural network is being developed to predict the timing and size of future destructive earthquakes, according to RIKEN researchers. Earthquakes typically occur when parts of the Earth’s crust suddenly shift around a fracture or fault in the rock, releasing a huge amount of strain energy.
Earthquake predictions could give people enough time to evacuate threatened areas, potentially saving many thousands of lives. But earthquake prediction is very difficult.
A team led by Naonori Ueda of the RIKEN Center for Advanced Intelligence Project are applying a neural network that learns physical laws, called a physics-informed neural network (PINN). Conventional neural networks learn functional relationships between inputs and outputs, whereas PINN’s learn to satisfy a physical model described by partial differential equations.
However, the team resolved that a PINN, which learns continuous functions, would be difficult to directly apply to cases such as crustal deformation models, where the displacement is discontinuous across a fault line.
Ueda and his team have overcome this difficulty by using a specially designed coordinate system to deal with discontinuity across faults. This allowed them to accurately model the deformation of the Earth’s crust, even in areas close to faults.
“The proposed modeling has the potential to realize a high-precision prediction,” said Ueda.
The researchers trained their neural networks using physical laws instead of data, which is ideal for applications where data acquisition can be difficult.
PINNs are a relatively new form of machine learning, and the researchers hope that their approach could be applied to many other problems involving crustal deformation.
https://phys.org/news/2023-03-neural-networks-destructive-earthquakes.html