Identifying European Old-Growth Forests using Remote Sensing: A Study in the Ukrainian Carpathians

Abstract

Old-growth forests are an important, rare and endangered habitat in Europe. The ability to identify old-growth forests through remote sensing would be helpful for both conservation and forest management. We used data on beech, Norway spruce and mountain pine old-growth forests in the Ukrainian Carpathians to test whether Sentinel-2 satellite images could be used to correctly identify these forests. We used summer and autumn 2017 Sentinel-2 satellite images comprising 10 and 20 m resolution bands to create 6 vegetation indices and 9 textural features. We used a Random Forest classification model to discriminate between dominant tree species within old-growth forests and between old-growth and other forest types. Beech and Norway spruce were identified with an overall accuracy of around 90%, with a lower performance for mountain pine (70%) and mixed forest (40%). Old-growth forests were identified with an overall classification accuracy of 85%. Adding textural features, band standard deviations and elevation data improved accuracies by 3.3%, 2.1% and 1.8% respectively, while using combined summer and autumn images increased accuracy by 1.2%. We conclude that Random Forest classification combined with Sentinel-2 images can provide an effective option for identifying old-growth forests in Europe.

Statistical Stability and Spatial Instability in Mapping Forest Tree Species by Comparing 9 Years of Satellite Image Time Series

“…This approach has been explored from various image datasets of different spatial and temporal resolutions based on spaceborne sensors such as MODIS [20,21], Landsat [22][23][24][25][26], RapidEye [27], WorldView [28], as airborne sensor [29,30] or unmanned aerial systems [31]. More recently, the potential of the new freely available high spatial resolution Sentinel-2 (S2) data has been investigated [32][33][34][35][36]. In general, the authors found it advantageous to combine images acquired in spring and autumn, at the key phenological stages of temperate forests, since it had a positive influence on the accuracy of the classification.…”

“…In general, the authors found it advantageous to combine images acquired in spring and autumn, at the key phenological stages of temperate forests, since it had a positive influence on the accuracy of the classification. Images acquired in summer are also frequently selected in features ranking procedures, particularly for conifer species [36], but also for deciduous species [30]. From a spectral point of view, red-edge bands and SWIR bands are reported to be important variables when S2 time series are used [32][33][34].…”

Remote Sensing Technology Applications in Forestry and REDD+

“…This Special Issue contains 12 studies that provided insight into new advances in the field of remote sensing for forest management and REDD+. This included developments into (1) algorithm development using satellite data [10][11][12][13][14][15][16]; (2) synthetic aperture radar (SAR) [11,17];…”

“…Zhao et al [10] use machine learning on both structural and spectral indices from QuickBird multispectral and panchromatic images to map forest canopy cover. Spracklen and Spracklen [14] demonstrate the use of machine learning with Sentinel-2 images for identifying old-growth forests in Europe. Gigovic et al [15] create a remote sensing (MODIS, Landsat-8 OLI and Worldview-2) derived forest inventory map to train a machine learning algorithm to predict forest fire susceptibility.…”

“…Random forest (RF) has been the most popular machine learning algorithm to link remote sensing data to forest structural attributes such as AGB [11,12], canopy cover [10] or forest fire susceptibility [15]. Spracklen and Spracklen [14] apply RF to identify old-growth forests using remote sensing data. Chen et al [11] and Gigovic et al [15] test different machine learning approaches for predicting AGB.…”