DATASET

GHS-BUILT-S2 R2020A - GHS built-up grid, derived from Sentinel-2 global image composite for reference year 2018 using Convolutional Neural Networks (GHS-S2Net) - OBSOLETE RELEASE

Collection: GHSL : Global Human Settlement Layer 

Description

This dataset corresponds to global map of built-up areas expressed in terms of a probability grid at 10 m spatial resolution derived from a Sentinel-2 global image composite (GHS_composite_S2_L1C_2017-2018_GLOBE_R2020A_UTM_10_v1_0) for reference year 2018. It builds on a new Deep Learning framework for pixel-wise large-scale classification of built-up areas named GHS-S2Net (GHS stands for Global Human Settlements, S2 refers to the Sentinel-2 satellite).

Contact

Email
jrc-ghsl-data (at) ec.europa.eu

Contributors

How to cite

Corbane, Christina; Sabo, Filip; Politis, Panagiotis; Syrris, Vasileios (2020): GHS-BUILT-S2 R2020A - GHS built-up grid, derived from Sentinel-2 global image composite for reference year 2018 using Convolutional Neural Networks (GHS-S2Net) - OBSOLETE RELEASE. European Commission, Joint Research Centre (JRC) [Dataset] doi: 10.2905/016D1A34-B184-42DC-B586-E10B915DD863 PID: http://data.europa.eu/89h/016d1a34-b184-42dc-b586-e10b915dd863

Keywords

Artificial Intelligence Big Data Built-up areas Copernicus GHS-BUILT GHSL Global Remote Sensing Sentinel-2

Data access

GHS_BUILT_S2comp2018_GLOBE_R2020A_UTM_10
URL 
  • This dataset corresponds to global map of built-up areas expressed in terms of a probability grid at 10 m spatial resolution derived from a Sentinel-2 global image composite (GHS_composite_S2_L1C_2017-2018_GLOBE_R2020A_UTM_10_v1_0) for reference year 2018. It builds on a new Deep Learning framework for pixel-wise large-scale classification of built-up areas named GHS-S2Net (GHS stands for Global Human Settlements, S2 refers to the Sentinel-2 satellite). Projection: Local UTM Data type:

    uint 8bit Built-up probability values rescaled in the range 0-100 Nodata value:

    255

Voilà - JRC Big Data Plaform JEODPP
Access conditions
Registration required 
URL 
  • Visualization of the layer on JRC Big Data Plaform JEODPP (under Products/LandCover)

GHS_BUILT_S2comp2018_GLOBE_R2020A WMS
URL 
  • Web Mapping Service

GHS_BUILT_S2comp2018_GLOBE_R2020A Metadata
Download 
  • GHS_BUILT_S2comp2018_GLOBE_R2020A products technical details

GHS_BUILT_S2comp2018_GLOBE_R2020A Tiles schema
Download 
  • Tiles schema used to produce the GHS_BUILT_S2comp2018_GLOBE_R2020A

Publications

Publication 2021
Convolutional Neural Networks for global human settlements mapping from Sentinel-2 satellite imagery
Corban, C., Syrris, V., Sabo, F., Politis, P., Melchiorri, M., Pesaresi, M., Soille, P. and Kemper, T., Convolutional Neural Networks for global human settlements mapping from Sentinel-2 satellite imagery, NEURAL COMPUTING and APPLICATIONS, ISSN 0941-0643 (online), 33, 2021, p. 6697–6720, JRC120622.
  • SPRINGER LONDON LTD, ENGLAND
Publication page 
  • Abstract

    Spatially consistent and up-to-date maps of human settlements are crucial for addressing policies related to urbanization and sustainability especially in the era of an increasingly urbanized world. The availability of open and free Sentinel-2 data of the Copernicus Earth Observation programme offers a new opportunity for wall-to-wall mapping of human settlements at a global scale. This paper presents a deep-learning-based

    framework for a fully automated extraction of built-up areas at a spatial resolution of 10 meters from a global composite of Sentinel-2 imagery. A multi-neuro modelling methodology, building on a simple Convolution Neural Networks architecture for pixel-wise image classification of built-up areas is developed. The deployment of the model on the global Sentinel-2 image composite provides the most detailed and complete map reporting about built-up areas for reference year 2018. The validation of the results with an independent reference dataset of building footprints covering 277 sites across the world,

    establishes the reliability of the built-up layer produced by the proposed framework and the model robustness. The results of this study contribute to cutting-edge research in the field of automated built-up

    areas mapping from remote sensing data and establish a new reference layer for the analysis of the spatial

    distribution of human settlements across the rural-urban continuum.

Publication
Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite Imagery
Corbane, C., V. Syrris, F. Sabo, P. Politis, Michele Melchiorri, M. Pesaresi, P. Soille, and T. Kemper. “Convolutional neural networks for global human settlements mapping from Sentinel-2 satellite imagery". Neural Comput & Applic (2020). https://doi.org/10.1007/s00521-020-05449-7
URL 

Geographic areas

World

Spatial coverage

Type Value
GML
<gml:Polygon xmlns:gml="http://www.opengis.net/gml">  <gml:outerBoundaryIs>    <gml:LinearRing>      <gml:coordinates>-179.99,84 179.99,84 179.99,-55.99 -179.99,-55.99 -179.99,84</gml:coordinates>    </gml:LinearRing>  </gml:outerBoundaryIs></gml:Polygon>
GML
<gml:Polygon xmlns:gml="http://www.opengis.net/gml/3.2">  <gml:exterior>    <gml:LinearRing>      <gml:posList>-179.99 84 179.99 84 179.99 -55.99 -179.99 -55.99 -179.99 84</gml:posList>    </gml:LinearRing>  </gml:exterior></gml:Polygon>
WKT
POLYGON ((-179.99 84, 179.99 84, 179.99 -55.99, -179.99 -55.99, -179.99 84))

Temporal coverage

From date To date
2017-01-01 2018-12-31

Additional information

Published by
European Commission, Joint Research Centre
Created date
2020-10-22
Modified date
2022-06-24
Issued date
2020-10-31
Landing page
http://ghsl.jrc.ec.europa.eu/ 
Language(s)
English
Data theme(s)
Regions and cities, Population and society, Science and technology
Update frequency
irregular
Identifier
http://data.europa.eu/89h/016d1a34-b184-42dc-b586-e10b915dd863
Popularity
26 Feb 2024: 1 visits