Land use and land cover (LULC) map for all-Fiji in 2020. The LULC map is generated from a year's worth of cloud masked Sentinel-2 surface reflectance data and topographic data from the SRTM using a random forests machine learning workflow. The map has a 10 m spatial resolution and a gap filling routine has been used to provide coverage in cloud affected areas where data permits. For more details on the methodology, please see this resource.
This dataset comprises a zipfile containing GeoTIFF files storing land cover data for each Tikina. Tikina's that span the anti-meridian are split into two geometries. Each 10 m x 10 m pixel can take on one of eight classes:
- water
- mangrove
- bare soil / rock
- urban / impervious
- cropland / agriculture
- grassland
- shrubland
- trees
The cropland / agriculture class is defined as any location where agricultural activities associated with cropping or livestock management were visible in high-resolution images. Land that is recently fallow, but where evidence of cropping or grazing activities is present, would be labelled as cropland. Grassland is defined as any low vegetation (e.g. below knee height) without a bush, shrub, or woody structure. Shrubland is defined as any vegetation that is below head height, does not form a closed canopy, and has a clearly visible bush, shrub, or woody structure. Trees are defined as any vegetation greater than head height forming a clear canopy.
This dataset was generated with support from a Climate Change AI Innovation Grant and the Australian Centre for International Agricultural Research.
![[Open Data]](/data/base/images/od_80x15_blue.png)