LSD4WSD VX: An Open Dataset for Wet Snow Detection with SAR Data and Physical Labelling - Full Analysis Version
- Citation Author(s):
-
Matthieu Gallet
(LISTIC, University Savoie Mont Blanc)
Fatima Karbou
(CEN, Centre National de Recherches Météorologiques)
Abdourrahmane Atto
(LISTIC, University Savoie Mont Blanc)
Emmanuel Trouvé
(LISTIC, University Savoie Mont Blanc)
- Submitted by:
- matthieu gallet
- Last updated:
- DOI:
- 10.21227/9ywp-1h32
- Data Format:
- Links:
325 views
- Categories:
- Keywords:
Abstract
Learning SAR Dataset for Wet Snow Detection - Full Analysis Version.
The aim of this dataset is to provide a basis for automatic learning to detect wet snow. It is based on Sentinel-1 SAR GRD satellite images acquired between August 2020 and August 2021 over the French Alps. The new version of this dataset is no longer simply restricted to a classification task, and provides a set of metadata for each sample. It consists of 2467516 samples of size 15 by 15 by 9 stored ins hdf5 file. For each sample, the 9 metadata are provided, using in particular the Crocus physical model:
- topography:
- elevation (meters) (average),
- orientation (degrees) (average),
- slope (degrees) (average),
- metadata:
- name of the alpine massif,
- date of acquisition,
- type of acquisition (ascending/descending),
- physics
- Liquid Water Content (km/m2),
- snow height (m),
- minimum snowpack temperature (Celsius degree).
An overview of the distribution and a summary of the sample statistics can be found in the file info.pdf. A more complete description can be found in the README.pdf file.
The processing chain is available at the following Github address.
Instructions:
- The README.pdf file gives details of the dataset of improvements compared with the first version,
- The info.pdf file gives an overview of the distribution and a summary of the sample statistics,
- The dataset_load.py allows to select a part or the whole dataset using requests on the metadata.
