Rapid Prediction of Bending Properties of Catalpa Bungei Wood by Near-Infrared Spectroscopy

Catalpa bungei has the advantages of straight texture, excellent material, and versatility characteristics and it is a precious wood species unique to China. Bending property, an important mechanical property of wood, research on its rapid determination method can provide a scientific basis for genetic improvement, processing, and utilization of Catalpa wood. The Luoqiu 1, Luoqiu 4 and Tianqiu 2 of the new C. bungei clones were used as the experiment materials. The modulus of rupture (MOR) and modulus of elasticity (MOE) was determined according to the national standard bending property test method. Near-infrared spectroscopy (NIRs) combined with the partial least squares (PLS) method was used to predict the bending properties of three newly bred C. bungei clones. The best modeling method based on different wood sections, pretreatment methods, and the number of sampling points were explored. The results indicated that the maximum R-p and RDP of the MOR model based on the average spectra of two sections were 0.843 and 1.88, and the maximum R-p and RDP of the MOE prediction model were 0.846 and 1.88. In descending order of accuracy of MOR models based on average sections, pretreatments were: MSC+S-G, 2(nd)Der+S-G, and 1(st)Der+S-G. In descending order of accuracy of MOE models based on average sections, pretreatments were: MSC+S-G, 1(st)Der+S-G, and 2(nd)Der+S-G. In conclusion, NIRs can be used to predict the MOR and MOE of valuable C. bungei wood. Models established with different sections, pretreatments, and the number of sampling points have certain differences in modeling results. This paper obtained the best modeling methods for the MOR and MOE of C. bungei wood. NIR models of MOR and MOE based on average spectra of radial and tangential sections were the best. MSC+S-G was the most suitable pretreatment method for the bending properties of C. bungei wood. The five-point sampling method has the highest model accuracy. The number of sampling points can be reduced to quickly estimate the bending property of a large number of samples. It is possible to collect only one spectra point in the middle part, the loading position, to reduce the workload of collecting spectra and improve the efficiency of rapid evaluation of the bending property of C. bungei wood.