Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning [Research Data] (doi:10.11588/data/AAKAF9)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

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

doi:10.11588/data/AAKAF9

heiDATA

2021-10-12

1

Li, Hao; Zech, Johannes; Ludwig, Christina; Fendrich, Sascha; Shapiro, Aurelie; Schultz, Michael; Zipf, Alexander, 2021, "Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning [Research Data]", https://doi.org/10.11588/data/AAKAF9, heiDATA, V1

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

doi:10.11588/data/AAKAF9

Li, Hao (GIScience Chair, Institute of Geography, Heidelberg University, 69120 Heidelberg, Germany)

Zech, Johannes (GIScience Chair, Institute of Geography, Heidelberg University, 69120 Heidelberg, Germany)

Ludwig, Christina (GIScience Chair, Institute of Geography, Heidelberg University, 69120 Heidelberg, Germany)

Fendrich, Sascha (HeiGIT at Heidelberg University, Schloss-Wolfsbrunnenweg 33, 69118 Heidelberg, Germany)

Shapiro, Aurelie (Food and Agriculture Organization of the United Nations (FAO), Viale delle Terme di Caracalla, 00153 Rome, Italy)

Schultz, Michael (GIScience Chair, Institute of Geography, Heidelberg University, 69120 Heidelberg, Germany)

Zipf, Alexander (GIScience Chair, Institute of Geography, Heidelberg University, 69120 Heidelberg, Germany)

heiDATA

Li, Hao

https://doi.org/10.11588/data/AAKAF9

Earth and Environmental Sciences, Volunteered geographical information, Inland surface water, OpenStreetMap, Copernicus, SDG6, deep learning

DATASET FOR JOURNAL PAPER (<a href="https://doi.org/10.1016/j.jag.2021.102571">https://doi.org/10.1016/j.jag.2021.102571</a>) <br /> <br /> 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 10m 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.

Germany

country

The WasserBLIcK data was provided by the German Federal Institute of Hydrology (BfG) via the BfG INSPIRE Download Service.

Li, H. J. Zech, C. Ludwig, S. Fendrich, A. Shapiro, M. Schultz, A. Zipf (2021): Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning.. International Journal of Applied Earth Observation and Geoinformation, Vol 104, 2021, 102571.

https://doi.org/10.1016/j.jag.2021.102571

Li, H. J. Zech, C. Ludwig, S. Fendrich, A. Shapiro, M. Schultz, A. Zipf (2021): Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning.. International Journal of Applied Earth Observation and Geoinformation, Vol 104, 2021, 102571.

Label:

readme.txt

Text:

Description of the data structure and the meaning fo different files.

text/plain

Label:

Figure10_product_compare_part2.pdf

application/pdf

Label:

Figure2_overview_map.pdf

application/pdf

Label:

Figure7_sample_areas.pdf

application/pdf

Label:

Figure8_state_catchment_model.pdf

application/pdf

Label:

Figure9_product_compare_part1.pdf

application/pdf

Label:

Figure_SNIC_stepsize.pdf

application/pdf

Label:

agreement_OSM&predicted_10m_3035.tif

image/tiff

Label:

water_OSM_10m_3035.tif

image/tiff

Label:

water_predicted_10m_3035.tif

image/tiff

Label:

water_product_1_10m_3035.tif

image/tiff

Label:

water_product_2_10m_3035.tif

image/tiff

Label:

Chiemsee.geojson

application/octet-stream

Label:

Hamburg.geojson

application/octet-stream

Label:

Mainz.geojson

application/octet-stream

Label:

Mannheim.geojson

application/octet-stream

Label:

Wesenberg.geojson

application/octet-stream

Label:

10_river_catchment_Germany.geojson

application/octet-stream

Label:

16_federal_states_Germany.geojson

application/octet-stream

Label:

validation_samples.geojson

application/octet-stream