Litcius/Paper detail

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

Marc Wieland, Florian Fichtner, Sandro Martinis, Sandro Groth, Christian Krullikowski, Simon Plank, Mahdi Motagh

2023IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing51 citationsDOIOpen Access PDF

Abstract

This study introduces the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S1S2-Water</i> 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 pre-dominant 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.

Topics & Concepts

Convolutional neural networkComputer scienceArtificial intelligenceIntersection (aeronautics)Digital elevation modelRemote sensingSegmentationDeep learningSatelliteRGB color modelPattern recognition (psychology)CartographyGeologyGeographyAerospace engineeringEngineeringFlood Risk Assessment and ManagementGroundwater and Watershed AnalysisHydrology and Watershed Management Studies