Dataset Information

Autonomous extraction of millimeter-scale deformation in InSAR time series using deep learning

ABSTRACT: Systematically characterizing slip behaviours on active faults is key to unraveling the physics of tectonic faulting and the interplay between slow and fast earthquakes. Interferometric Synthetic Aperture Radar (InSAR), by enabling measurement of ground deformation at a global scale every few days, may hold the key to those interactions. However, atmospheric propagation delays often exceed ground deformation of interest despite state-of-the art processing, and thus InSAR analysis requires expert interpretation and a priori knowledge of fault systems, precluding global investigations of deformation dynamics. Here, we show that a deep auto-encoder architecture tailored to untangle ground deformation from noise in InSAR time series autonomously extracts deformation signals, without prior knowledge of a fault’s location or slip behaviour. Applied to InSAR data over the North Anatolian Fault, our method reaches 2 mm detection, revealing a slow earthquake twice as extensive as previously recognized. We further explore the generalization of our approach to inflation/deflation-induced deformation, applying the same methodology to the geothermal field of Coso, California. A deep neural network is developed to automatically extract ground deformation from Interferometric Synthetic Aperture Radar time series. Applied to data over the North Anatolian Fault, the method can detect 2 mm deformation transients and reveals a slow earthquake twice as extensive as previously recognized.

SUBMITTER: Rouet-Leduc B

PROVIDER: S-EPMC8581022 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Glacier melting is one of the important causes of glacier morphology change and can provide basic parameters for calculating glacier volume change and glacier mass balance, which, in turn, is important for evaluating water resources. However, it is difficult to obtain large-scale time series of glacier changes due to the cloudy and foggy conditions which are typical of mountain areas. Gravity-measuring satellites and laser altimetry satellites can monitor changes in glacier volume over a wide area, while synthetic-aperture radar satellites can monitoring glacier morphology with a high spatial and temporal resolution. In this article, an interferometric method using a short temporal baseline and a short spatial baseline, called the Small Baseline Subsets (SBAS) Interferometric Synthetic-Aperture Radar (InSAR) method, was used to study the average rate of glacier deformation on Karlik Mountain, in the Eastern Tienshan Mountains, China, by using 19 Sentinel-1A images from November 2017 to December 2018. Thus, a time series analysis of glacier deformation was conducted. It was found that the average glacier deformation in the study region was -11.77 ± 9.73 mm/year, with the observation sites generally moving away from the satellite along the Line of Sight (LOS). Taking the ridge line as the dividing line, it was found that the melting rate of southern slopes was higher than that of northern slopes. According to the perpendicular of the mountain direction, the mountain was divided into an area in the northwest with large glaciers (Area I) and an area in the southeast with small glaciers (Area II). It was found that the melting rate in the southeast area was larger than that in the northwest area. Additionally, through the analysis of temperature and precipitation data, it was found that precipitation played a leading role in glacier deformation in the study region. Through the statistical analysis of the deformation, it was concluded that the absolute value of deformation is large at elevations below 4200 m while the absolute value of the deformation is very small at elevations above 4500 m; the direction of deformation is always away from the satellite along the LOS and the absolute value of glacier deformation decreases with increasing elevation.

Dataset Information

Autonomous extraction of millimeter-scale deformation in InSAR time series using deep learning

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets