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

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