Identification of species of the genus Populus L. based on the data of hyperspectral crown survey for climate change monitoring

Abstract

Solving the problem of global climate change requires an integrated approach, including the use of the phytochorological method. Remote sensing is the best option for monitoring changes in the boundaries of plant ranges. However, the problem of species identification based on RS data has not yet been solved. Therefore, the aim of the study was to assess the possibility of using vegetation indices (VIs) calculated from the data of hyperspectral imaging (HSI) of crowns of woody plants to determine their species. The objects of the study were samples of the species Populus tremula L., P. alba L., P. simonii Carriere. The survey was carried out with a Cubert UHD-185 hyperspectral camera in five periods with an interval of 7–10 days. 80 VIs were calculated. Sample sets were analyzed using Analysis of Variance (ANOVA), Principal component analysis (PCA), Decision Tree (DT) and Random Forest (RF) methods. The PCA and RF methods consistently distinguish all three species from each other throughout all five periods of the experiment. The most informative VIs are: Double Peak Index (DPI), Derivative index 1 (D1), Datt index 3 (Datt3) and Vogelmann index (Vogelmann).