Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
  Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben
Zeitschriftenartikel

S1S2-Water: A Global Dataset for Semantic Segmentation of Water Bodies From Sentinel-1 and Sentinel-2 Satellite Images

Urheber*innen
/persons/resource/mwieland

Wieland,  Marc
2.6 Seismic Hazard and Risk Dynamics, 2.0 Geophysics, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Fichtner,  Florian
External Organizations;

Martinis,  Sandro
External Organizations;

Groth,  Sandro
External Organizations;

Krullikowski,  Christian
External Organizations;

Plank,  Simon
External Organizations;

/persons/resource/motagh

Motagh,  M.
1.4 Remote Sensing, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Externe Ressourcen
Es sind keine externen Ressourcen hinterlegt
Volltexte (frei zugänglich)

5025702.pdf
(Verlagsversion), 6MB

Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Wieland, M., Fichtner, F., Martinis, S., Groth, S., Krullikowski, C., Plank, S., Motagh, M. (2024): S1S2-Water: A Global Dataset for Semantic Segmentation of Water Bodies From Sentinel-1 and Sentinel-2 Satellite Images. - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 1084-1099.
https://doi.org/10.1109/JSTARS.2023.3333969


Zitierlink: https://gfzpublic.gfz-potsdam.de/pubman/item/item_5025702
Zusammenfassung
This study introduces the S1S2-Water dataset—a global reference dataset for training, validation, and testing of convolutional neural networks (CNNs) for semantic segmentation of surface water bodies in publicly available Sentinel-1 and Sentinel-2 satellite images. The dataset consists of 65 triplets of Sentinel-1 and Sentinel-2 images with quality-checked binary water mask. Samples are drawn globally on the basis of the Sentinel-2 tile-grid (100 km × 100 km) under consideration of predominant landcover and availability of water bodies. Each sample is complemented with metadata and digital elevation model (DEM) raster from the Copernicus DEM. On the basis of this dataset, we carry out performance evaluation of CNN architectures to segment surface water bodies from Sentinel-1 and Sentinel-2 images. We specifically evaluate the influence of image bands, elevation features (slope) and data augmentation on the segmentation performance and identify best-performing baseline-models. The model for Sentinel-1 achieves an Intersection over Union (IoU) of 0.845, Precision of 0.932, and Recall of 0.896 on the test data. For Sentinel-2 the best model produces an IoU of 0.965, Precision of 0.989, and Recall of 0.951, respectively. We also evaluate the performance impact when a model is trained on permanent water data and applied to independent test scenes of floods.