New methodology enables automatic detection of Earth deformation on a global scale – ScienceDaily

[ad_1]

Researchers at Los Alamos National Laboratory are applying machine learning algorithms to help interpret vast amounts of Earth deformation data collected using Synthetic Aperture Radar (InSAR) satellites; New algorithms will improve earthquake detection.

“Applying machine learning to InSAR data gives us a new way to understand the physics behind tectonic faults and earthquakes,” said Bertrand Roet-Leduc, a geophysicist with the Geophysics Group at Los Alamos. “This is crucial to understanding the full spectrum of earthquake behavior.”

New satellites, such as the Sentinel 1 Satellite Constellation and the upcoming NISAR satellite, are opening a new window on tectonic processes by allowing researchers to observe scales of length and time that were not possible in the past. However, current algorithms are not suitable for the huge amount of InSAR data streaming from these new satellites, and more data will be available in the near future.

In order to process all this data, the team at Los Alamos developed the first tool based on machine learning algorithms to extract ground deformation from InSAR data, which enables the detection of ground deformation automatically – without human intervention – on a global scale. Equipped with deformation-independent detection on faults, this tool can help bridge the gap in existing detection capabilities and form the foundations for a systematic exploration of active fault characteristics.

Systematic characterization of slip behavior on active faults is fundamental to unraveling the physics of tectonic faults, and will help researchers understand the interaction between slow earthquakes, which gently release stress, and fast earthquakes, which release stress quickly and can cause significant damage to surrounding communities.

The team’s new methodology makes it possible to automatically detect Earth deformation on a global scale, with temporal resolution much finer than current methods, and a detection threshold of a few millimeters. Previous detection thresholds were in the centimeter range.

In the preliminary results of the approach, applied to data on the North Anatolian Fault, the method reached a detection of 2 mm, revealing slow earthquakes twice their amplitude as previously recognized.

This work was funded by the Los Alamos National Laboratory’s Office of Research and Development.

Story source:

Materials provided by DOE/Los Alamos National Laboratory. Note: Content can be modified according to style and length.

.

[ad_2]