EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Spatial and temporal screening of slope motion patterns in alpine environment via unsupervised analysis of large InSAR datasets

Davide Festa1, Alessandro Novellino2, Ekbal Hussain2, Luke Bateson2, Nicola Casagli1,3, Pierluigi Confuorto1, Matteo Del Soldato1, and Federico Raspini1
Davide Festa et al.
  • 1University of Firenze, Department of Earth Sciences, Firenze, Italy (
  • 2British Geological Survey, Keyworth, Nottinghamshire, UK
  • 3National Institute of Oceanography and Applied Geophysics, Trieste, Italy

The use of SAR interferometry is globally regarded as a powerful tool able to evaluate spatial and temporal patterns of slope motion in alpine areas. Accordingly, the availability of large multi-temporal interferometric datasets compels the scientific community to find efficient value-adding tools to boost the interpretation and management of radar-based information via automated routines in the framework of multi-hazard mapping and analysis. Here it is presented an unsupervised and automated approach based on Principal Component Analysis (PCA) and K-means clustering to detect patterns of natural or human-induced ground deformation from InSAR Time Series. For our proof-of-concept, the focus is placed on Valle d’Aosta region (Northwest Italy) where different landslide types, deep-seated gravitational slope deformations and permafrost creep interact with human activities and infrastructures. The large volumes of Sentinel-1 data produced allows for retrieving horizontal and vertical Time Series from multi-geometry data fusion of LOS InSAR measurements. Therefore, the added benefit of combining ascending/descending InSAR data and interpolating displacements in time at different time steps is here explored prior to data dimensionality reduction and feature extraction through PCA. The retrieved principal components serve as a continuous solution for cluster membership indicators in the K-means clustering method, allowing to define spatially and temporally coherent displacement phenomena. The signal of the ground deformation clusters is deconstructed into the underlying trend and seasonality components to enhance the interpretability of the classified satellite InSAR features. Using InSAR Time series data spanning 2014-2020, the proposed framework detects several mass wasting processes and anthropogenic deformations with both linear and seasonal displacement behaviours. The results demonstrate the potential applicability of the proposed transferable approach to the development of automated ground motion analysis systems.

How to cite: Festa, D., Novellino, A., Hussain, E., Bateson, L., Casagli, N., Confuorto, P., Del Soldato, M., and Raspini, F.: Spatial and temporal screening of slope motion patterns in alpine environment via unsupervised analysis of large InSAR datasets, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-14022,, 2023.