GHS-BUILT-S ARCTIC R2025A – gridded built-up surface estimates for the Arctic region (1975-2030)

Description

These spatial raster datasets depict the distribution of the built-up (BU) surface estimates between 1975 and 2030 in 5-year intervals and two functional use components: a) the total BU surface and b) the non-residential (NRES) BU surface. The data are made by spatial-temporal interpolation of five observed collections of multi-sensor, multi-platform satellite images: Landsat MSS, TM, and ETM sensors support the 1975, 1990, 2000, and 2014 epochs, and a Sentinel-2 (S-2) composite (GHS-composite-S2 R2020A) supports the 2018 epoch. The built-up surface fraction (BUFRAC) is estimated at 10m spatial resolution from the S-2 image data, using a composite of data from GHS-BUILT-S2 R2020A, Facebook, Microsoft, and Open Street Map (OSM) building delineations as training data. The BUFRAC inference is based on reflectance and morphological features through associative rule learning (Symbolic Machine Learning, SML). The non-residential domain is predicted from S-2 imagery using radiometric, textural, and morphological features in an object-oriented image processing framework. The multi-temporal dimension is provided by assessing the association between radiometric information collected by the Landsat imagery in past epochs, and the built-up and non-built-up class abstraction on image segments extracted from Sentinel-2 images. The spatial-temporal interpolation for intermediate epochs is solved by rank-optimal spatial allocation using explanatory variables related to the landscape (e.g., slope, elevation, distance to water and to vegetation) and is related to the observed dynamics of BU surfaces in past epochs. GHS-BUILT-S_ARCTIC_R2025A is a subset of the GHS-BUILT-S_GLOBE_R2023A product, and has been reprojected from World Mollweide projection (ESRI:54009) to the North Pole LAEA Europe reference system (EPSG:3575) using VectorCubeWarp, a tool for volume-preserving, gridded data cube resampling using areal interpolation.

Resources

Name Format Description Link
48
48

Tags

  • arctic
  • built-up-surface-grid
  • ghsl
  • functional-use-classification
  • global-map
  • ghs-built

Topics

  • REGI
  • TECH

Categories