Application of airborne hyperspectral data for mapping of invasive alien Spiraea tomentosa L.: a serious threat to peat bog plant communities

Abstract

Remote sensing is increasingly widely used in nature conservation management. The research focuses on developing an optimal set of airborne raster data for the identification of the invasive alien species Spiraea tomentosa L. The plant species selected for the purposes of this study poses a serious threat to peat bog plant communities, moist coniferous forests, and meadows in Central Europe. The impact of the data acquisition time on the accuracy of classification and the percentage cover limit required for correct identification of a target species using the developed method were also investigated. The study area is located in the Lower Silesian forests in Poland and is protected as a Natura 2000 site. Airborne hyperspectral and laser scanning data were simultaneously acquired two times in the growing season (August and September 2016) parallel to on-ground reference data collection. The 1 m resolution HySpex images with spectral range of 0.4–2.5 μm were corrected atmospherically, radiometrically and geometrically. Airborne Laser Scanning (ALS) data acquired at 7 points/m2 were used to generate several products, e.g. Canopy Height Model (CHM), rasters representing morphometric features of the area (Multiresolution Index of the Ridge Top Flatness or Valley Bottom Flatness—MRRTF, MRVBF), wetness relations (Topographic Wetness Index—TWI) and the availability of light (Total Insolation—TI), intensity of laser pulse reflection and geometric relations of vegetation points (i.a. Vegetation Cover, Vegetation Mean Intensity). The Random Forest (RF) classification and different raster datasets were used to identify the target species. As a result, the highest accuracy was obtained for the scenario based on HySpex images acquired in September. The accuracy (f1 score) for the target species achieved 83%. The developed method for the identification of Spiraea tomentosa has a great potential for application and can be used for monitoring peat bogs threatened by invasion of alien plants.

Airborne HySpex Hyperspectral Versus Multitemporal Sentinel-2 Images for Mountain Plant Communities Mapping

“…In the case of the SVM classifier, MNF-based results were the worst (HySpex: 78.5%; and 69.7% for MNF). Similar observations were made by Kopeć et al [85], who used HySpex images as well. In this case, the MNF-based classifications identified invasive and expansive species.…”

Mapping Invasive Plant Species with Hyperspectral Data Based on Iterative Accuracy Assessment Techniques

“…Lower accuracies might be caused by using referenced data that included reference polygons with relatively low density of Calamagrostis epigejos (40%). In frame of the same project Kopeć et al [20] has shown that minimum density of abovementioned plant species should be no less than 70% in order to be properly identified. Moreover, past research of Sabat-Tomala et al [32] has also shown that SVM classifier is more suited for identification of Calamagrostis epigejos than random forest (SVM F1-score-0.91 and RF F1-score-0.83).…”

“…For example, The SVM algorithm and the recursive feature elimination (SVM-RFE) approach were used to map the species Solanum mauritianum in KwaZulu Natal (eastern parts of South Africa) with an overall accuracy (OA) of 93% on selected 17 hyperspectral bands of the AISA Eagle image [19]. The random forest algorithm and 25 MNF bands of HySpex images for mapping the species Spiraea tomentosa in the Lower Silesian forests in Poland was used to obtain an F1-score accuracy for the species of 83% (OA-99%) for September's images and an F1-score of 77% (OA-99%) for August's [20]. Most studies indicate the need for methods that reduce the spectral space of hyperspectral imaging, e.g., principal component analysis (PCA) and minimum noise fraction (MNF), in order to reduce the data volume and shorten the data processing time [21,22].…”

No place to hide: Rare plant detection through remote sensing

“…RS has become a widely applied tool in plant studies (e.g. Asner, Hughes, et al., 2008; Asner et al., 2008; Kopeć et al., 2020; Wan et al., 2020) with the increasing availability of RS products that capture a wide variety of environmental features (Corbane et al., 2015; Kerr & Ostrovsky, 2003; Turner et al., 2003). Studies using RS to focus specifically on rare plants remain uncommon, although their number has been growing in recent years (e.g.…”