A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Application of the Symbolic Machine Learning to Copernicus VHR Imagery: The European Settlement Map
This letter introduces the new European Settlement Map (ESM) workflow, results and validation. Unlike the previous ESM versions, it uses the supervised learning combined with the textural and morphological features for built-up area extraction. Input data is the Copernicus very high resolution collection coming from a variety of sensors. The workflow is fully automated and it does not include any postprocessing. For the first time a new layer that classifies non-residential building is derived by using only remote sensing imagery and training data. The built-up area layer is delivered at 2m pixel resolution while the residential/non residential layer is delivered at 10m spatial resolution. More than 46000 scenes were processed and ~6 million km2 of Europe was mapped by using the Big Data infrastructure. Validation showed balanced accuracy of 0.81 and 0.91 for level 1 and 2 layers respectively and 0.70 for the non-residential layer. ; JRC.E.1-Disaster Risk Management
Application of the Symbolic Machine Learning to Copernicus VHR Imagery: The European Settlement Map
This letter introduces the new European Settlement Map (ESM) workflow, results and validation. Unlike the previous ESM versions, it uses the supervised learning combined with the textural and morphological features for built-up area extraction. Input data is the Copernicus very high resolution collection coming from a variety of sensors. The workflow is fully automated and it does not include any postprocessing. For the first time a new layer that classifies non-residential building is derived by using only remote sensing imagery and training data. The built-up area layer is delivered at 2m pixel resolution while the residential/non residential layer is delivered at 10m spatial resolution. More than 46000 scenes were processed and ~6 million km2 of Europe was mapped by using the Big Data infrastructure. Validation showed balanced accuracy of 0.81 and 0.91 for level 1 and 2 layers respectively and 0.70 for the non-residential layer. ; JRC.E.1-Disaster Risk Management
Application of the Symbolic Machine Learning to Copernicus VHR Imagery: The European Settlement Map
CORBAN CHRISTINA (author) / SABO FILIP (author) / SYRRIS VASILEIOS (author) / KEMPER THOMAS (author) / POLITIS PANAGIOTIS (author) / PESARESI MARTINO (author) / SOILLE PIERRE (author) / OSÉ KENJI (author)
2019-08-27
Miscellaneous
Electronic Resource
English
DDC:
710
| British Library Online Contents | 1994
Ground Truth and Automated Classification from Copernicus Sentinel-2 Imagery
| BASE | 2020
Photograph of Copernicus' Heliograph
| DataCite | 2017