Recursive Feature Elimination and Random Forest Classification of Natura 2000 Grasslands in Lowland River Valleys of Poland Based on Airborne Hyperspectral and LiDAR Data Fusion
Open Access
- 5 June 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (11), 1842
- https://doi.org/10.3390/rs12111842
Abstract
The use of hyperspectral (HS) and LiDAR acquisitions has a great potential to enhance mapping and monitoring practices of endangered grasslands habitats, beyond conventional botanical field surveys. In this study we assess the potentiality of recursive feature elimination (RFE) in combination with random forest (RF) classification in extracting the main HS and LiDAR features needed to map selected Natura 2000 grasslands along Polish lowland river valleys, in particular alluvial meadows 6440, lowland hay meadows 6510, and xeric and calcareous grasslands 6120. We developed an automated RFE-RF system capable to combine the potentials of both techniques and applied it to multiple acquisitions. Several LiDAR-based products and different spectral indices (SI) were computed and used as input in the system, with the aim of shedding light on the best-to-use features. Results showed a remarkable increase in classification accuracy when LiDAR and SI products are added to the HS dataset, strengthening in particular the importance of employing LiDAR in combination with HS. Using only the 24 optimal features selection generalized over the three study areas, strongly linked to the highly heterogeneous characteristics of the habitats and landscapes investigated, it was possible to achieve rather high classification results (K around 0.7–0.77 and habitats F1 accuracy around 0.8–0.85), indicating that the selected Natura 2000 meadows and dry grasslands habitats can be automatically mapped by airborne HS and LiDAR data. Similar approaches might be considered for future monitoring activities in the context of habitats protection and conservation.Keywords
Funding Information
- Narodowe Centrum Nauki (UMO-2017/25/B/ST10/02967)
This publication has 93 references indexed in Scilit:
- European grassland ecosystems: threatened hotspots of biodiversityBiodiversity and Conservation, 2013
- Assessment of grassland use intensity by remote sensing to support conservation schemesJournal for Nature Conservation, 2012
- Automatic Geographic Object Based Mapping of Streambed and Riparian Zone Extent from LiDAR Data in a Temperate Rural Urban Environment, AustraliaRemote Sensing, 2011
- Optimising the use of hyperspectral and LiDAR data for mapping reedbed habitatsRemote Sensing of Environment, 2011
- Succession of floodplain grasslands following reduction in land use intensity: the importance of environmental conditions, management and dispersalJournal of Applied Ecology, 2009
- A multiresolution index of valley bottom flatness for mapping depositional areasWater Resources Research, 2003
- Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extractionIEEE Transactions on Geoscience and Remote Sensing, 2002
- The photochemical reflectance index: an optical indicator of photosynthetic radiation use efficiency across species, functional types, and nutrient levelsOecologia, 1997
- Breakthrough in Statistics:Journal of the American Statistical Association, 1993
- A review of: “Image Interpretation in Geology”. By S. A. DRURY. (London: Allen & Unwin, 1987.) [Pp. 243.] Price £40·00 (hardback), £17·95 (paperback).International Journal of Remote Sensing, 1987