AvalCD

Read full text Summarise with VIRAT
Authors: Mattia Gatti
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This dataset provides the original georeferenced satellite data for bi-temporal avalanche change detection using Sentinel-1 SAR imagery. It includes avalanche inventories from four geographically diverse regions: Livigno (Italy), Nuuk (Greenland), Pish (Shughnon District, Tajikistan), and Tromsø (Norway). These names serve only as geographic anchors; some mapped avalanches extend beyond the administrative or colloquial boundaries of the listed regions. For the Livigno and Nuuk regions, multiple avalanche events are included across different acquisition dates to reflect temporal variability and enhance generalizability .For each event, the raw dataset includes pre- and post-event SAR intensity channels (VV and VH polarizations), local incidence angle (LIA), digital elevation model (DEM), terrain slope, aspect, avalanche masks, and a GeoPackage containing avalanche polygons. All layers are spatially aligned and provided in standard geospatial formats. To support patch-based deep learning workflows, a companion Python script is provided. This script allows users to generate their own dataset of image patches with configurable size and stride. Each generated patch includes the pre-event SAR channels (VV, VH) and post-event SAR channels (VV, VH), along with LIA, DEM, slope, aspect, and a binary avalanche mask. Instructions for setting up the environment and using this script are provided in the accompanying README file. This dataset includes data from the Sentinel-1 SAR mission and the Copernicus Digital Elevation Model (GLO-30), both provided by the European Space Agency (ESA) and the European Commission under the Copernicus Programme. Use of this data complies with the Copernicus Data and Information Access Policy, which allows free and open access for commercial and non-commercial use with appropriate attribution.

Fields of Study & Subjects

Landslides and related hazards Synthetic Aperture Radar (SAR) Applications and Techniques Cryospheric studies and observations

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
1 January 2026
Language
EN
Document type
Dataset