Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning

• Verfasst von: Li, Hao [VerfasserIn]
• Verfasst von: Zech, Johannes [VerfasserIn]
• Verfasst von: Ludwig, Christina [VerfasserIn]
• Verfasst von: Fendrich, Sascha [VerfasserIn]
• Verfasst von: Shapiro, Aurelie [VerfasserIn]
• Verfasst von: Schultz, Michael [VerfasserIn]
• Verfasst von: Zipf, Alexander [VerfasserIn]
• Titel: Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning
• Verf.angabe: Hao Li, Johannes Zech, Christina Ludwig, Sascha Fendrich, Aurelie Shapiro, Michael Schultz, AlexanderZipf
• E-Jahr: 2021
• Jahr: 15 December 2021
• Umfang: 16 S.
• Fussnoten: Gesehen am 28.04.2022
• Titel Quelle: Enthalten in: International journal of applied earth observation and geoinformation
• Ort Quelle: Amsterdam [u.a.] : Elsevier Science, 1999
• Jahr Quelle: 2021
• Band/Heft Quelle: 104(2021), Artikel-ID 102571, Seite 1-16
• ISSN Quelle: 1872-826X
• DOI: doi:10.1016/j.jag.2021.102571
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1800589603

Abstract

Large-scale mapping activities can benefit from the vastly increasing availability of earth observation (EO) data, especially when combined with volunteered geographical information (VGI) using machine learning (ML). High-resolution maps of inland surface water bodies are important for water supply and natural disaster mitigation as well as for monitoring, managing, and preserving landscapes and ecosystems. In this paper, we propose an automatic surface water mapping workflow by training a deep residual neural network (ResNet) based on OpenStreetMap (OSM) data and Sentinel-2 multispectral data, where the Simple Non-Iterative Clustering (SNIC) superpixel algorithm was employed for generating object-based training samples. As a case study, we produced an open surface water layer for Germany using a national ResNet model at a 10 m spatial resolution, which was then harmonized with OSM data for final surface water products. Moreover, we evaluated the mapping accuracy of our open water products via conducting expert validation campaigns, and comparing to existing water products, namely the WasserBLIcK and Global Surface Water Layer (GSWL). Using 4,600 validation samples in Germany, the proposed model (ResNet+SNIC) achieved an overall accuracy of 86.32% and competitive detection rates over the WasserBLIcK (87.47%) and GSWL (98.61%). This study provides comprehensive insights into how to best explore the synergy of VGI and ML of EO data in a large-scale surface water mapping task.