Identification of species of the genus Quercus L. with different responses to soil and climatic conditions according to hyperspectral survey data

Abstract

Soil standing may be studied indirectly using remote sensing through an assessment of state of the plants growing on it. The ability to evaluate the physiological state of plants using the hyperspectral survey data also provides a tool to characterize vegetation cover and individual samples of woody plants. In the present work the hyperspectral imaging was applied to identify the species of the woody plants evaluating the differences in their physiological state. Samples of Quercus macrocarpa Michx., Q. robur L. and Q. rubra L. were studied using Cubert UHD-185 hyperspectral camera over five periods with an interval of 7-10 days. In total, 80 vegetation indices (VIs) were calculated. Sample sets of values of VIs were analyzed using analysis of variance (ANOVA), principal component analysis (PCA), decision tree (DT), random forest (RF) methods. It was shown using the ANOVA, that the following VIs are the most dependent on the species affiliation of the samples: Carter2, Carter3, Carter4, CI, CI2, CRI4, Datt, Datt2, GMI2, Maccioni, mSR2, MTCI, NDVI2, OSAVI2, PRI, REP_Li, SR1, SR2, SR6, Vogelmann, Vogelmann2, Vogelmann4. VIs that are effective for the separation of oak species, were also revealed using the DT method – these are Boochs, Boochs2, CARI, CRI1, CRI3, D1, D2, Datt, Datt3; Datt4, Datt5, DD, DDn, EGFN, Gitelson, MCARI2, MTCI, MTVI, NDVI3, PRI, PSND, PSRI, RDVI, REP_Li, SPVI, SR4, Vogelmann, Vogelmann2, Vogelmann3. PCA and RF methods reliably differentiated Q. rubra from Q. robur and Q. macrocarpa. Q. rubra, unlike other species, was under stress from the impact of soil pH against the background of drought. This was manifested in leaf chlorosis. Influence of the environmental stress factors on the reliability and efficiency of species identification was demonstrated. Q. robur and Q. macrocarpawere were poorly separated by PCA and RF methods all over the five periods of the experiment.

Keywords

• hyperspectral imaging
• vegetation indices
• quercus macrocarpa
• quercus robur
• quercus rubra
• environmental stress
• drought stress
• reflection spectra