Extracting small deformation beyond individual station precision from dense Global Navigation Satellite System (GNSS) networks in France and western Europe

We use 2 decades of data from a dense geodetic network to extract regionally coherent velocities and deformation rates in France and neighboring western European countries. This analysis is combined with statistical tests on synthetic data to quantify the deformation detection thresholds and significance levels. By combining two distinct methods - Gaussian smoothing and k-means clustering - we extract horizontal deformations with a 95 % confidence level of ca. 0.1-0.2 mm yr(-1) (ca. 0.5-1 x 10(-9) yr(-1)) on spatial scales of 100-200 km or more. From these analyses, we show that the regionally average velocity and strain rate fields are statistically significant in most of our study area. The first-order deformation signal in France and neighboring western European countries is a belt of N-S to NE-SW shortening of ca. 0.2-0.4 mm yr(-1) (1-2 x 10(-9) yr(-1)) in central and eastern France. In addition to this large-scale signal, patterns of orogen-normal extension are observed in the Alps and the Pyrenees, but methodological biases, mainly related to GPS (Global Positioning System) solution combinations, limit the spatial resolution and preclude associations with specific geological structures. The patterns of deformation in western France show either tantalizing correlation (Brittany) or anticorrelation (Aquitaine Basin) with the seismicity. Overall, more detailed analyses are required to address the possible origin of these signals and the potential role of aseismic deformation.