Deep Learning Aids Quake And Tsunami Detection

Deep neural networks have been used to detect magnetic field anomalies, which could allow faster and more accurate detection of earthquakes and tsunamis.

AsianScientist (Oct. 23, 2018) – Researchers at the Tokyo Metropolitan University, Japan, have used machine learning techniques to achieve fast and accurate estimates of local geomagnetic fields, potentially allowing for the detection of earthquakes and tsunamis. They published their findings in IEICE Communications Express.

Scientists have known that earthquakes and tsunamis are accompanied by localized changes in the geomagnetic field. For earthquakes, the release of a massive amount of accumulated stress along a fault causes local changes in geomagnetic field. For tsunamis, the sudden, vast movement of the sea causes variations in atmospheric pressure, which in turn affects the ionosphere and changes the geomagnetic field.

Both can be detected by a network of observation points at various locations. The major benefit of such an approach is speed. Because electromagnetic waves travel at the speed of light, earthquakes and tsunamis should be instantaneously detectable based on changes in geomagnetic field. However, the geomagnetic field at various locations is a fluctuating signal, which makes it difficult to identify anomalies indicative of a seismic event.

To overcome this problem, researchers led by Associate Professor Kan Okubo of Tokyo Metropolitan University developed a method to take measurements at multiple locations around Japan and create an estimate of the geomagnetic field at different, specific observation points. Specifically, they applied a machine learning algorithm known as a deep neural network (DNN).

By feeding the algorithm a vast amount of inputs taken from historical measurements, they were able to create and optimize an extremely complex, multi-layered set of operations that most effectively maps the data to what was actually measured. Using half a million data points taken in 2015, they were able to create a network that can estimate the magnetic field at the observation point with high accuracy.

Given the relatively low computational cost of DNNs, the system may potentially be paired with a network of high sensitivity sensors to achieve lightning-fast detection of earthquakes and tsunamis, delivering an effective warning system that can minimize damage and save lives.

The article can be found at: Katori & Okubo (2018) Neural Network Based Geomagnetic Estimation for Multi-site Observation System.


Source: Tokyo Metropolitan University; Photo: Shutterstock.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Asian Scientist Magazine is an award-winning science and technology magazine that highlights R&D news stories from Asia to a global audience. The magazine is published by Singapore-headquartered Wildtype Media Group.

Related Stories from Asian Scientist