Mapping of the Canopy Openings in Mixed Beech-Fir Forest at Sentinel-2 Subpixel level Using UAV and Machine Learning Approach

Abstract

The presented study demonstrates the bi-sensor approach suitable for rapid and precise up-to-date mapping of forest canopy gaps for the larger spatial extent. The approach makes use of UAV RGB images on smaller areas for highly precise forest canopy mask creation. Sentinel-2 was used as a scaling platform for transferring information from UAV to a wider spatial extent. The various approaches of the improvement of the predictive performance were examined: (I) the highest R2 of the single satellite index was up to 0.57, (II) the highest R2 using multiple features obtained from the single date, S-2 image was 0.624 and, (III) the highest R2 on the multi-temporal set of S-2 images, was 0.697. Satellite indices such as ARVI, IPVI, NDI45, PSSRa, MCARI, CI, RI, and NDTI were the dominant predictors in most of the ML algorithms. The more complex ML algorithms such as SVM, Random Forest, GBM, XGBoost, and Catboost that provided the best performance on the training set exhibited weaker generalization capabilities. Therefore, a simpler and more robust Elastic Net algorithm was chosen for the final map creation.

Automatic Forest Degradation Monitoring by Remote Sensing Methods and Copernicus Data

“…Therefore, the fundamental problem in determining the extent of damage (area, degree of damage, volume) is the inability to access such areas. Thus, physical access to areas of interest and field damage assessment is high risk, while on the other hand, remote sensing techniques are a fast and reliable way to assess forest damage (Mitchell et al 2017, Pilaš et al 2020. In this regard, drones, aerial and satellite imagery are available to users (Lechner et al 2020).…”

Classification of airborne multispectral imagery to quantify common vole impacts on an agricultural field

“…For example, classification methods can help differentiate fully vegetated areas from ‘bald’ areas created by voles 20 and also identify intermediate stages of damage. In pest damage evaluations, different classification approaches have been used, such as vegetation index thresholds, 21 automatic classification methods 26 and supervised classifications based on machine learning, and either pixel‐oriented (each pixel is classified independently) 27 or object‐oriented methods (all pixels within defined objects are included to define spectral behavior through an iterative classification process) 28 . Imagery segmentations of damaged areas from UASs also have been used in the diagnoses of precision applications of control measures by drones 29 .…”