Title: Categorizing grassland vegetation with full-waveform airborne laser scanning: a feasibility study for detecting Natura 2000 habitat types
Language: English
Authors: Zlinszky, András
Schroiff, Anke
Kania, Adam
Deák, Balázs 
Mücke, Werner 
Vári, Agnes 
Székely, Balázs 
Pfeifer, Norbert 
Category: Research Article
Issue Date: 2014
Journal: Remote sensing
ISSN: 2072-4292
There is increasing demand for reliable, high-resolution vegetation maps covering large areas. Airborne laser scanning data is available for large areas with high resolution and supports automatic processing, therefore, it is well suited for habitat mapping. Lowland hay meadows are widespread habitat types in European grasslands, and also have one of the highest species richness. The objective of this study was to test the applicability of airborne laser scanning for vegetation mapping of different grasslands, including the Natura 2000 habitat type lowland hay meadows. Full waveform leaf-on and leaf-off point clouds were collected from a Natura 2000 site in Sopron, Hungary, covering several grasslands. The LIDAR data were processed to a set of rasters representing point attributes including reflectance, echo width, vegetation height, canopy openness, and surface roughness measures, and these were fused to a multi-band pseudo-image. Random forest machine learning was used for classifying this dataset. Habitat type, dominant plant species and other features of interest were noted in a set of 140 field plots. Two sets of categories were used: five classes focusing on meadow identification and the location of lowland hay meadows, and 10 classes, including eight different grassland vegetation categories. For five classes, an overall accuracy of 75% was reached, for 10 classes, this was 68%. The method delivers unprecedented fine resolution vegetation maps for management and ecological research. We conclude that high-resolution full-waveform LIDAR data can be used to detect grassland vegetation classes relevant for Natura 2000.
Keywords: remote sensing; LIDAR; Natura 2000; machine learning; grasslands; lowland hay meadows; habitat mapping
DOI: 10.3390/rs6098056
Library ID: AC11360637
URN: urn:nbn:at:at-ubtuw:3-2334
Organisation: E120 - Department für Geodäsie und Geoinformation 
Publication Type: Article
Appears in Collections:Article

Files in this item:

Page view(s)

checked on Jul 22, 2021


checked on Jul 22, 2021

Google ScholarTM


This item is licensed under a Creative Commons License Creative Commons