Multi-temporal information layer on the presence of built-up surfaces derived from global Landsat satellite data collected from 1975 to 2014, at the native spatial resolution varying from 80 meters (Landsat MSS sensor), 30 meters (Landsat TM sensor), and 15/30 meters (Landsat ETM sensor). The image data collections
were prepared by the Global Land Survey (GLS1975, GLS1990, GLS2000) and by the JRC (Landsat 8 collection for 2014). The data was processed by fully automatic and reproducible methods based on statistical learning (Symbolic Machine Learning). No manual or ad-hoc rule-based editing of the results was applied in the post-processing. The product it is provided with a spatial resolution of 30 meters.
- Vasileios Syrris
How to cite
Corbane, Christina; Florczyk, Aneta; Pesaresi, Martino; Politis, Panagiotis; Syrris, Vasileios (2018): GHS-BUILT R2018A - GHS built-up grid, derived from Landsat, multitemporal (1975-1990-2000-2014). European Commission, Joint Research Centre (JRC) [Dataset] doi: 10.2905/jrc-ghsl-10007 PID: http://data.europa.eu/89h/jrc-ghsl-10007
The data are organised in several datasets. The main product (GHS_BUILT_LDSMT_GLOBE_R2018A_3857_30) is a multitemporal built-up grid (built-up classes: 1975, 1990, 2000, 2014 epoch), which has been produced at high resolution (30m).
Multi-temporal built-up area classification map: 0 = no data; 1 = water surface; 2 = land no built-up in any epoch; 3 = built-up from 2000 to 2014 epochs; 4 = built-up from 1990 to 2000 epochs; 5 = built-up from 1975 to 1990 epochs; 6 = built-up up to 1975 epoch. Data organisation: VRT file (with GeoTIFF tiles) or GeoTIFF files; pyramids ArcGIS users of the 30-m product: *ESRI.vrt.file. Resolution: 30m. Projection: Spherical Mercator (EPSG:3857). The 30m grid has been used to derive additional layers per each epoch, offered at middle and low resolution (250m in Mollweide and 1km in Mollweide). Each dataset is distributed in a compressed ZIP, that contains TIF file with pyramids and documentation.
- MDPI AG, BASEL, SWITZERLAND
This work introduces a new classification method in the remote sensing domain, suitably adapted to dealing with the challenges posed by the big data processing and analytics framework. The method is based on symbolic learning techniques, and it is designed to work in complex and information-abundant environments, where relationships among different data layers are assessed in model-free and computationally-effective modalities. The two main stages of the method are the data reduction-sequencing and the association analysis. The former refers to data representation; the latter searches for systematic relationships between data instances derived from images and spatial information encoded in supervisory signals. Subsequently, a new measure named the evidence-based normalized differential index, inspired by the probability-based family of objective interestingness measures, evaluates these associations. Additional information about the computational complexity of the classification algorithm and some critical remarks are briefly introduced. An application of land cover mapping where the input image features are morphological and radiometric descriptors demonstrates the capacity of the method; in this instructive application, a subset of eight classes from the Corine Land Cover is used as the reference source to guide the training phase.
|From date||To date|
- Published by
- European Commission, Joint Research Centre
- Created date
- Modified date
- Issued date
- Landing page
- Data theme(s)
- Regions and cities, Science and technology
- Update frequency