TY - JOUR

T1 - S1S2-Water

T2 - A Global Dataset for Semantic Segmentation of Water Bodies From Sentinel- 1 and Sentinel-2 Satellite Images

AU - Wieland, Marc

AU - Fichtner, Florian

AU - Martinis, Sandro

AU - Groth, Sandro

AU - Krullikowski, Christian

AU - Plank, Simon

AU - Motagh, Mahdi

N1 - Funding Information: This work was supported in part by the German Federal Ministry of Education and Research (BMBF) through the project Künstliche Intelligenz zur Analyse von Erdbeobachtungs- und Internetdaten zur Entscheidungs-unterstützung im Katastrophenfall (AIFER) under Grant 13N15525 and in part by the Helmholtz Artificial Intelligence Cooperation Unit through the project AI for Near Real Time Satellite-Based Flood Response (AI4FLOOD) under Grant ZT-IPF-5-39.

PY - 2023/11/17

Y1 - 2023/11/17

N2 - 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.

AB - 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.

KW - Convolutional neural networks (CNNs)

KW - reference dataset

KW - semantic segmentation

KW - Sentinel-1

KW - Sentinel-2

KW - surface water monitoring

UR - http://www.scopus.com/inward/record.url?scp=85146151681&partnerID=8YFLogxK

U2 - 10.1109/JSTARS.2023.3333969

DO - 10.1109/JSTARS.2023.3333969

M3 - Article

AN - SCOPUS:85146151681

VL - 17

SP - 1084

EP - 1099

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

ER -