Mechanical Property Prediction of Larix gmelinii Wood Based on Vis-Near-Infrared Spectroscopy

Larix gmelinii is the major tree species in Northeast China. The wood properties of different are quite and under strong genetic controls, so it can be better improved through oriented breeding. In order to detect longitudinal compressive strength (LCS), modulus rupture (MOR) elasticity (MOE) real-time, fast non-destructively, a prediction model mechanical with high precision stability constructed based on visible-near-infrared spectroscopy (Vis-NIRS) technology. featured wavelengths were selected algorithms competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), uninformative variable elimination (UVE), synergy interval partial least squares (SiPLS) their combinations. models then developed square regression (PLSR). predictive ability was evaluated coefficient determination (R2) root mean error (RMSE). It indicated that CARS performed best among four methods examined terms wavelength-variable selection. combined wavelength selecting method SiPLS-CARS showed performance than single selection method. optimal LCS, MOR MOE SiPLS-CARS-PLSR model, R2 calibration set validation both greater 0.99, RMSE smallest. NIR for predictions has accuracy good robustness.