Species-Level Vegetation Mapping in a Himalayan Treeline Ecotone Using Unmanned Aerial System (UAS) Imagery

Abstract

Understanding ecological patterns and response to climate change requires unbiased data on species distribution. This can be challenging, especially in biodiverse but extreme environments like the Himalaya. This study presents the results of the first ever application of Unmanned Aerial Systems (UAS) imagery for species-level mapping of vegetation in the Himalaya following a hierarchical Geographic Object Based Image Analysis (GEOBIA) method. The first level of classification separated green vegetated objects from the rest with overall accuracy of 95%. At the second level, seven cover types were identified (including four woody vegetation species). For this, the suitability of various spectral, shape and textural features were tested for classifying them using an ensemble decision tree algorithm. Spectral features alone yielded ~70% accuracy (kappa 0.66) whereas adding textural and shape features marginally improved the accuracy (73%) but at the cost of a substantial increase in processing time. Contrast in plant morphological traits was the key to distinguishing nearby stands as different species. Hence, broad-leaved versus fine needle leaved vegetation were mapped more accurately than structurally similar classes such as Rhododendron anthopogon versus non-photosynthetic vegetation. Results highlight the potential and limitations of the suggested UAS-GEOBIA approach for detailed mapping of plant communities and suggests future research directions.

Application of UAV-Based Methodology for Census of an Endangered Plant Species in a Fragile Habitat

“…Only one of their examples involved census of a rare species, Caicos pine, within an area. The few species successfully quantified with drone imagery have usually been trees [15][16][17][18]. Drones have been successfully used to map herbaceous invasive species infestations, but the species mapped are usually clonal species that can be quantified using vegetation mapping techniques; efforts to map invasive species individuals intermingled in other vegetation have been less successful [19][20][21][22].…”

Knowledge and Spatial Pyramid Distance-Based Gated Graph Attention Network for Remote Sensing Semantic Segmentation

“…Currently, the OBIA methods are widely applied in multi-scale research [15,16], change detection [17] and landslide detection [18]. To better understand ecological patterns, it is also expanded to the species-level mapping of vegetation [19]. Other research, like References [20,21], presented a comparative evaluation of the pixel-based method and the object-based; especially, Reference [21] compared the pixel-based support vector machine (SVM) classification and decision-tree-oriented geographic object-based image analysis (GEOBIA) classification, which indicated that the GEOBIA classification provided the highest accuracy.…”

“…Figure19. The classification results and the object masks in sample V. The yellow box presents the forest 1 object that will be analyzed in this section, and the red box presents the misclassified result.…”

Monitoring ecological characteristics of a tallgrass prairie using an unmanned aerial vehicle

“…For example, Hodgson et al (2018) found that counting the number of seabirds within colonies was more accurate when automated though UAV imagery than with trained field technicians. Mishra et al (2018) tested the ability to identify individual tree species along a tree line ecotone in Nepal and found approximately 70% accuracy using UAV imagery alone. Grassland applications have largely been limited to quantifying the presence of a single species, landcover and vegetation types, biomass, and disturbances such as prescribed burns (Zweig et al 2015; Cruzan et al 2016; Lorah 2018; Lussem et al 2019; Melville et al 2019).…”