Skip to content
Login has been disabled on EnviDat Legacy. Please log in via https://envidat.ch first, then refresh this page.

Changes

View changes from to


On May 7, 2021 at 7:13:35 AM UTC, Gravatar Administrator:
  • Updated description of Forest Type NFI from

    This dataset presents an remote sensing based approach for a countrywide mapping of broadleaved and coniferous trees in Switzerland with a spatial resolution of 3 m x 3 m. The data available is a raster of 25 m x 25 m with the fraction of broadleaf trees. The classification approach incorporates a random forest classifier, explanatory variables from multispectral aerial imagery and a Digital Terrain Model (DTM) from Airborne Laser Scanning (ALS) data, digitized training polygons and independent validation data from the National Forest Inventory (NFI). Whereas high model overall accuracies (0.99) and kappa (0.98) were achieved, the comparison of the tree type map with independent NFI data revealed significant deviations that are related to underestimations of broadleaved trees (median of 3.17%).
    to
    This dataset presents an remote sensing based approach for a countrywide mapping of broadleaved and coniferous trees in Switzerland with a spatial resolution of 3 m x 3 m. The data available is a raster of 25 m x 25 m with the fraction of broadleaf trees. Two versions of the data are currently available: 2018 and 2016. The 2018 version presents a remote sensing-based approach for a countrywide mapping of the dominant leave type (DLT) with the two classes broadleaved and coniferous in Switzerland. The spatial resolution is 10 m with the fraction of the class broadleaf. The classification approach incorporates a random forest classifier, explanatory variables from multispectral Sentinel-2, multi-temporal Sentinel-1 data and a Digital Terrain Model (DTM) from Airborne Laser Scanning (ALS) data. The models were calibrated using digitized training polygons and independently validated data from the National Forest Inventory (NFI). Whereas high model overall accuracies (0.97) and kappa (0.96) were achieved, the comparison of the tree type map with independent NFI data revealed deviations in mixed stands. In the 2016 version, the classification approach incorporates a random forest classifier, explanatory variables from multispectral aerial imagery and a Digital Terrain Model (DTM) from Airborne Laser Scanning (ALS) data, digitized training polygons and independent validation data from the National Forest Inventory (NFI). Whereas high model overall accuracies (0.99) and kappa (0.98) were achieved, the comparison of the tree type map with independent NFI data revealed significant deviations that are related to underestimations of broadleaved trees (median of 3.17%).