GLaD4CD: Global Landslide Dataset for Change Detection

This dataset constitutes one of the outcomes of the Master's Thesis titled 'Landslide identification using deep learning-based change detection and the DeepESDL collaborative cloud platform,' authored by Julia Anna Leonardi, conducted under the supervision of Prof. Maria Antonia Brove...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Leonardi, Julia Anna, Yordanov, Vasil, Brovelli, Maria Antonia
Format: Dataset
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This dataset constitutes one of the outcomes of the Master's Thesis titled 'Landslide identification using deep learning-based change detection and the DeepESDL collaborative cloud platform,' authored by Julia Anna Leonardi, conducted under the supervision of Prof. Maria Antonia Brovelli and Dr. Vasil Yordanov at Politecnico di Milano. The authors extracted the image patches through the DeepESDL platform, which the ESA NoR sponsorship provided access to.  The resource contains the .csv database containing landslide information of 174 events, such as the date, location, source, and the dates of the Sentinel-2 images from before and after the event. The sources of the data included in this inventory are: Inventario dei Fenomeni Franosi in Italia (IFFI) compiled by ISPRA NASA Global Landslide Catalog (GLC) [1],[2]. Copernicus Emergency Management Service (© European Union, 2012-2024) [3] Geological Survey Ireland | Geohazards | National Landslide Susceptibility Map Monsoon triggered landslides in Nepal timed with Sentinel-1 for 2015, 2017, 2018, and 2019, courtesy of Katy Burrows [4]  Landslides after 2023 earthquakes in Turkey compiled by the NASA GSFC team University of Twente online landslide course Manually extracted sources from [5], [6], [7], [8]. The .zip file contains the TRAIN dataset with the pre-event Sentinel-2 image patches in folder PRE and the post-event Sentinel-2 image patches in folder POST, and the TEST set with 17 bi-temporal pairs in the PRE and POST folders following the above convention and the labels in the form of change maps in the CM folder. In this updated version the full 13-band Sentinel-2 images are published. (In the previous version only 5 bands (B02, B03, B04, B08, and CLM) were available). All the image patches and the ground truth annotations are in the GeoTIFF format.  The authors developed the dataset for change detection workflows. Project supported by the ESA Network of Resources Initiative. This work is funded by the Italian Ministry of Foreign Affairs and International Cooperation within the project “Geoinformatics and Earth Observation for Landslide Monitoring” CUP D19C21000480001   [1]  Kirschbaum, D.B., Stanley, T., & Zhou, Y. (2015). Spatial and temporal analysis of a global landslide catalog. Geomorphology, 249, 4-15. doi:10.1016/j.geomorph.2015.03.016 [2] Kirschbaum, D.B., Adler, R., Hong, Y., Hill, S., & Lerner-Lam, A. (2010). A global landslide catalog for hazard applications: method, results, and limitations.
DOI:10.5281/zenodo.10800336