Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service

Krullikowski, Christian; Chow, Candace; Wieland, Marc; Martinis, Sandro; Bauer-Marschallinger, Bernhard; Roth, Florian; Matgen, Patrick; Chini, Marco; Hostache, Renaud; Liu, Yu; Salamon, Peter

doi:10.1109/jstars.2023.3292350

Cited by 3 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to conventional delineation maps, the ensemble procedure implemented in CEMS offers a pixel-level likelihood estimation of the flood area extent as well as an exclusion mask indicating the regions where the detection is prevented due to hampering factors, e.g., strong geometric distortions, urban areas, vegetation. An analysis of different ensemble approaches for likelihood estimation in CEMS products is carried out in [202].…”

Section: Cemsmentioning

confidence: 99%

Flood Detection with SAR: A Review of Techniques and Datasets

Amitrano,

Di Martino,

Di Simone

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Floods are among the most severe and impacting natural disasters. Their occurrence rate and intensity have been significantly increasing worldwide in the last years due to climate change and urbanization, bringing unprecedented effects on human lives and activities. Hence, providing a prompt response to flooding events is of crucial relevance for humanitarian, social and economic reasons. Satellite remote sensing using synthetic aperture radar (SAR) offers a great deal of support in facing flood events and mitigating their effects on a global scale. As opposed to multi-spectral sensors, SAR offers important advantages, as it enables Earth’s surface imaging regardless of weather and sunlight illumination conditions. In the last decade, the increasing availability of SAR data, even at no cost, thanks to the efforts of international and national space agencies, has been deeply stimulating research activities in every Earth observation field, including flood mapping and monitoring, where advanced processing paradigms, e.g., fuzzy logic, machine learning, data fusion, have been applied, demonstrating their superiority with respect to traditional classification strategies. However, a fair assessment of the performance and reliability of flood mapping techniques is of key importance for an efficient disasters response and, hence, should be addressed carefully and on a quantitative basis trough synthetic quality metrics and high-quality reference data. To this end, the recent development of open SAR datasets specifically covering flood events with related ground-truth reference data can support thorough and objective validation as well as reproducibility of results. Notwithstanding, SAR-based flood monitoring still suffers from severe limitations, especially in vegetated and urban areas, where complex scattering mechanisms can impair an accurate extraction of water regions. All such aspects, including classification methodologies, SAR datasets, validation strategies, challenges and future perspectives for SAR-based flood mapping are described and discussed.

show abstract

Section: Cemsmentioning

confidence: 99%

Flood Detection with SAR: A Review of Techniques and Datasets

Amitrano,

Di Martino,

Di Simone

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Surface water monitoring is an important topic in remote sensing and detailed reviews can be found in Huang et al (2018) [3] and Bentivoglio et al (2022) [4]. While rule-based algorithms have long dominated water mapping studies with multi-spectral and SAR satellite sensors [5]- [7], convolutional neural networks (CNNs) have seen a rapid development in recent years [8]- [11]. Liu et al (2019) [12] use a modified U-Net architecture to analyze bi-temporal and dual-polarized Sentinel-1 images of floods caused by Hurricane Harvey in the U.S. in 2017.…”

mentioning

confidence: 99%

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

Wieland,

Fichtner,

Martinis

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

This study introduces the S1S2-Water dataseta global reference dataset for training, validation and testing of convolutional neural networks 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 x 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 convolutional neural network 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 of 0.845, Precision of 0.932 and Recall of 0.896 on the test data. For Sentinel-2 the best model produces an Intersection Over Union 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.

show abstract

S1S2-Water: A global dataset for semantic segmentation of water bodies from Sentinel-1 and Sentinel-2 satellite images

Wieland,

Fichtner,

Martinis

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>This study introduces the S1S2-Water dataset – a global reference dataset for training, validation and testing of convolutional neural networks 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 x 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 convolutional neural network architectures to segment surface water bodies from Sentinel-1 and Sentinel-2 images. We specifically evaluate the influence of image bands, elevation features and data augmentation on the segmentation performance and identify best-performing baseline-models. The model for Sentinel-1 achieves an Intersection Over Union of 0.85, Precision of 0.93 and Recall of 0.90 on the test data. For Sentinel-2 the best model produces an Intersection Over Union of 0.96, Precision of 0.99 and Recall of 0.97 respectively. We also evaluate the performance impact when a model is trained on permanent water data and applied to independent test scenes of floods.</p>

show abstract

Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service

Cited by 3 publications

References 31 publications

Flood Detection with SAR: A Review of Techniques and Datasets

Flood Detection with SAR: A Review of Techniques and Datasets

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

S1S2-Water: A global dataset for semantic segmentation of water bodies from Sentinel-1 and Sentinel-2 satellite images

Contact Info

Product

Resources

About