Pflugmacher, Dirk; Rabe, Andreas; Peters, Mathias; Hostert, Patrick (2018): Pan-European land cover map of 2015 based on Landsat and LUCAS data [dataset]. PANGAEA, https://doi.org/10.1594/PANGAEA.896282,

---

Supplement to: Pflugmacher, D et al. (2019): Mapping pan-European land cover using Landsat spectral-temporal metrics and the European LUCAS survey. Remote Sensing of Environment, 221, 583-595, https://doi.org/10.1016/j.rse.2018.12.001

The pan-European land cover map of 2015 was produced by combining the large European-wide land survey LUCAS (Land Use/Cover Area frame Survey) and Landsat-8 data. We used annual and seasonal spectral-temporal metrics and environmental features to map 12 land cover and land use classes across Europe (artificial land, seasonal cropland, perennial cropland, broadleaved forest, coniferous forest, mixed forest, shrubland, grassland, barren, water, wetland, and permanent snow/ice). The classification was based on Landsat-8 data acquired over three years (2014-2016). Overall map accuracy was 75.1%. The spatial resolution and minimum mapping unit is 30 x 30 m. The map can be downloaded as a single GeoTiff file of 874Mbyte.

The produced pan-European land cover map compared favourably to the existing CORINE (Coordination of Information on the Environment) 2012 land cover dataset. The mapped country-wide area proportions strongly correlated with LUCAS-estimated area proportions (r=0.98). Differences between mapped and LUCAS sample-based area estimates were highest for broadleaved forest (map area was 9% higher). Grassland and seasonal cropland areas were 7% higher than the LUCAS estimate, respectively. In comparison, the correlation between LUCAS and CORINE area proportions was weaker (r=0.84) and varied strongly by country. CORINE substantially overestimated seasonal croplands by 63% and underestimated grassland proportions by 37%. Our study shows that combining current state-of-the-art remote sensing methods with the large LUCAS database imporves pan-European land cover mapping.