Prediction of National Vegetation Classification communities in the British uplands using environmental data at multiple spatial scales, aerial images and the classifier random forest

Abstract

Summary1. High-resolution vegetation maps are a valuable resource for conservation, land management and research. In Great Britain, the National Vegetation Classification (NVC) is widely used to describe vegetation communities. NVC maps are typically produced from ground surveys which are prohibitively expensive for large areas. An approach to produce NVC maps more cost-effectively for large areas would be valuable. 2. Creation of vegetation community maps from aerial or satellite images has often had limited success as the clusters separable by spectral reflectance frequently do not correspond well to vegetation community classes. Such maps have also been produced by exploring correlations between community occurrence and environmental variables. The latter approach can have limitations where anthropogenic activities have altered the distribution of vegetation communities. We combined these two approaches and classified 24 common NVC classes of the Yorkshire Dales and an additional class 'wood' consisting of trees and bushes at a resolution of 5 m from mostly remotely sensed variables with the algorithm random forest. 3. Classification accuracy was highest when environmental variables at low and high resolution (50 and 5-10 m, respectively) were added to aerial image information aggregated to a resolution of 5 m. Low-resolution environmental variables are likely to be correlated with the dominant vegetation surrounding a location and thus could represent critical area requirements or local species pool effects, while high-resolution environmental variables represent the environmental conditions at the location. 4. Overall classification accuracy was 87-92%. The median producer's and user's class accuracies were 95% (58-100%) and 92% (67-100%), respectively. 5. Synthesis and applications. The classification accuracies achieved in this study, the number of classes differentiated, their level of detail and the resolution were high compared with those of other studies. This approach could allow the production of good-quality NVC maps for large areas. In contrast to existing maps of broad land cover types, such maps would provide more detailed vegetation community data for applications like the monitoring of vegetation in a changing climate, the study of animal-habitat relationships, conservation management or land use planning.

Impact of ecological redundancy on the performance of machine learning classifiers in vegetation mapping

“…For instance, ML has been successfully applied to predict species distribution (Liu, White, Newell, & Griffioen, 2013), land‐use change (Tayyebi & Pijanowski, 2014), and hydrological regimes (Cross et al., 2015) and has also been applied to vegetation mapping across a range of spatial scales using a variety of algorithms (e.g. Bradter, Thom, Altringham, Kunin, & Benton, 2011; Munyati, Ratshibvumo, & Ogola, 2013; Pesch, Schmidt, Schroeder, & Weustermann, 2011; Zhang & Xie, 2013). When applied to vegetation mapping, ML algorithms (hereafter referred to as ML classifiers) aim to create models that depict the relationships between the vegetation types identified within an area and environmental (e.g.…”

Upscaling CH4 Fluxes Using High-Resolution Imagery in Arctic Tundra Ecosystems

“…Bratsch et al [53] have used LDA previously to distinguish between different lowland tundra types and it has also been used by Gong et al [54] and Clark et al [55], for example, to map different vegetation types across other ecosystem types. Finally, Chapman et al [56] and Bradter et al [57] have used the RF classifier to successfully map upland vegetation.…”

Evidence of increase in woody vegetation in a river corridor, Northwest England, 1984–2007

“…Lillesand, Kiefer, & Chipman, 2007), but can have limitations in resolution and detection of subtle vegetation change. Large-scale aerial photography was used here as it is often better for delimiting certain categories of vegetation cover (Akasheh, Neale, & Jayanthi, 2008;Bradter, Thom, Altringham, Kunin, & Benton, 2011;Xie, Sha, & Yu, 2008). Moreover, for long-term comparisons various types of remote sensing, particularly high-resolution images, are not available for early dates.…”