Forest Type NFI

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%).

Citation:

Lars Waser; Christian Ginzler (2018). Forest Type NFI. National Forest Inventory (NFI). doi:10.16904/1000001.3.

DataCite ISO 19139 GCMD DIF README.txt BibTex RIS

Data and Resources

Metadata

Field Values
DOI 10.16904/1000001.3
Authors
  • Name: Lars Waser  Email: lars.waserfoo(at)wsl.ch  ORCID: D-5937-2011  Scheme: ResearcherID  Affiliation: Swiss Federal Institute for Forest, Snow and Landscape Research WSL
  • Name: Christian Ginzler  Email: christian.ginzlerfoo(at)wsl.ch  ORCID: E-9544-2012  Scheme: ResearcherID  Affiliation: Swiss Federal Institute for Forest, Snow and Landscape Research WSL
Contact Person Name: Lars Waser  Email: lars.waserfoo(at)wsl.ch  Affiliation: Swiss Federal Institute for Forest, Snow and Landscape Research WSL  ORCID: D-5937-2011  Scheme: ResearcherID
Subtitles
  • Subtitle: Waldmischungsgrad LFI  Type: Alternative Title  Language: German
Publication Publisher: National Forest Inventory (NFI)  Year: 2018
Dates
  • Type: Created  Date: 2018-03-06
Version 2016 (current)
Type Dataset
General Type Dataset
Language English
Location Switzerland
Content License Other (Not Open)
Last Updated April 3, 2018, 15:06 (CEST)
Created April 3, 2018, 12:38 (CEST)