An Integration of Linear Model and ‘Random Forest’ Techniques for Prediction of Norway Spruce Vitality: A Case Study of the Hemiboreal Forest, Latvia

The increasing extreme weather and climate events have a significant impact on the resistance resilience of Norway spruce trees. responses adaptation individual trees to certain factors can be assessed through tree breeding programmes. Tree programmes combined with multispectral unmanned aircraft vehicle (UAV) platforms may assist in acquiring regular information traits from large areas progeny trials. Therefore, aim this study was investigate vegetation indices (VI) detect early stages stress stands under prolonged drought summer heatwave. Eight plots within four throughout season 2021 were monitored by assessing spectral differences health classes (Healthy, Crown damage, New crown Dead trees, Stem Root rot). From all tested VI, our models showed moderate marginal R2 total explanatory power—for Normalized Difference Red-edge Index (NDRE), 0.26, conditional 0.49 (p < 0.001); for Vegetation (NDVI), 0.34, 0.60 Red Green (RGI), 0.36, 0.55 while Chlorophyll (CI), 0.27, 0.001). reliability identification selected VI weak fair (overall classification accuracy ranged 34.4% 56.8%, kappa coefficients 0.09 0.34) if six assessed, substantial 71.1% 89.6% coefficient 0.39 0.71) two (Crown damage Healthy trees) tested.