Extraction of transient signal from GPS position time series by employing ICA

Abstract

Transient deformation, such as post-seismic slip, slow slip and pre-seismic slip events, is a limited low-frequency deformation that can last for hours to months, in contrast to a sudden slip on a fault caused by earthquakes. Continuous Global Positioning System (CGPS), one of the most common geodetic techniques for continuously monitoring crustal deformation, is capable of capturing transient deformation signals. A critical point in characterizing transient deformation signals is the development of extracting and deciphering transient deformation signals from a huge and messy data set of position time series. Principal Component Analysis (PCA), one of the data-driven methods, has been employed to derive transient deformation signals from position time series combing with Kalman filtering. Independent Component Analysis (ICA) performs well in recovering and separating the sources of observed data, however, it is rarely used in extracting transient deformation signals. We aim to decompose the transient deformation signals from the daily GPS observation deployed in Akutan Island from 2007 to 2015 with the ICA method and obtain the spatiotemporal responses to the source signals of transient deformation. Our results indicate that ICA method can also characterize effectively transient deformation signals spatially and temporally. Additionally, the independent relationship between sources obtained by ICA allows for flexibility in linearly combining different sources.