Upland vegetation mapping using Random Forests with optical and radar satellite data. Issue 4 (28th November 2016)

• Record Type: Journal Article
• Authors: Barrett, Brian; Raab, Christoph; Cawkwell, Fiona; Green, Stuart
• Editors: Nagendra, Harini; Horning, Ned
• Is Part Of: Remote sensing in ecology and conservation. Volume 2:Issue 4(2016)
• Page Start: 212
• Page End: 231
• Publication Date: 2016-11-28
• Subjects: Radar -- random forests -- remote sensing -- satellite data -- uplands -- vegetation mapping; Remote sensing -- Periodicals; Ecology -- Research -- Periodicals; Ecology -- Methodology -- Periodicals; Ecology -- Remote sensing -- Periodicals; Nature conservation -- Methodology -- Periodicals; 577.0723
• DOI: 10.1002/rse2.32
• Languages: English
• ISSNs: 2056-3485

Abstract

Abstract: Uplands represent unique landscapes that provide a range of vital benefits to society, but are under increasing pressure from the management needs of a diverse number of stakeholders (e.g. farmers, conservationists, foresters, government agencies and recreational users). Mapping the spatial distribution of upland vegetation could benefit management and conservation programmes and allow for the impacts of environmental change (natural and anthropogenic) in these areas to be reliably estimated. The aim of this study was to evaluate the use of medium spatial resolution optical and radar satellite data, together with ancillary soil and topographic data, for identifying and mapping upland vegetation using the Random Forests (RF) algorithm. Intensive field survey data collected at three study sites in Ireland as part of the National Parks and Wildlife Service (NPWS) funded survey of upland habitats was used in the calibration and validation of different RF models. Eight different datasets were analysed for each site to compare the change in classification accuracy depending on the input variables. The overall accuracy values varied from 59.8% to 94.3% across the three study locations and the inclusion of ancillary datasets containing information on the soil and elevation further improved the classification accuracies (between 5 and 27%, depending on the input classification dataset). The classification results were consistent across the three different study areas, confirming the applicability of the approach under different environmental contexts. Abstract : In this manuscript, we report on the results of an investigation into the potential of combining medium spatial resolution optical (10 m) and radar (15 m) satellite data for mapping vegetation in three different upland areas in Ireland. The analysis provides, for the first time, detailed EO‐derived vegetation maps for these study areas in Ireland and outlines a method that can be used with Sentinel‐1 (radar) and 2 (optical) data to provide contemporary map updates for these and other upland areas. The results demonstrate that multisource medium spatial resolution satellite data can be used for regular monitoring in upland regions in support of policy and management decision making, and for further understanding of the changes occurring in these areas and how best to respond to them.