Search

In this paper, an integration of BP neural network and PCA for modeling wood water content of larch combined with NIRS was investigated. The original spectra were collected and pretreated with 9 point smoothing and multiplicative scatter correction (MSC). Five typical principal components were extracted from PCA with the application of establishing prediction model. Full cross-validation approach was applied to achieve desirable modeling performance. The prediction correlation coefficient (R) was 0.952 while the mean square error of prediction (MSEP) was 38.27. This study indicated that NIR is a useful tool for rapid and accurate prediction of wood water content.

Microfibril angle (MFA) was determined at each growth ring from disks at breast height (1.3 m) from four scots pine (Pinus sylvestris) trees grown in northeastern China. Significant variation in microfibril angle was observed among growth rings. MFA at breast height showed a decreasing trend from pith to bark for each tree. The modified logistic model with nonlinear mixed-effects was used for modeling earlywood MFA. The NLME procedure in S-Plus is used to fit the mixed-effects models for the MFA data. The results showed that logistic model with two random parameters and could significantly improve the model performance. The CS, AR(1), MA(1), and ARMA(1,1) correlation structures were incorporated into mixed-effects models. The mixed model with the AR(1), MA(1), and ARMA(1,1) correlation structures improved model performance (P

Earlywood microfibril angle (MFA) was determined at each growth ring from disks at breast height (1.3 m) from 6 dahurian larch (Larix gmelinii. Rupr.) trees grown in northeastern China. Significant variation in microfibril angle was observed among growth rings. MFA at breast height varied from 7.5°to 21.5°between growth rings and showed a descreasing trend from pith to bark for each tree. A second order polynomial equation with linear mixed-effects was used for modeling earlywood MFA. The LME procedure in S-Plus is used to fit the mixed-effects models for the MFA data. The results showed that the polynomial model with three random parameters could significantly improve the model performance. The fitted mixed-effects model was also evaluated using a separate dataset. The mixed model was found to predict MFA better than the original model fitted using ordinary least-squares based on absolute and relative errors.

Water content of Korean pine samples was studied using near infrared spectrascopy (NIR) combinded with parial least squares regression (PLS) analysis. Seven typical wave lengths were selceted to characterize the wood water content of Korean pine. Prediction models of wood water content were developed based on the original NIR spectra at seven varied wave lengths. The best model was showed between wavelengths from 1000 to 2100 nm with correlation coefficient (R) of 0.9871, standard error of calibration (SEC) and root mean square error of calibration (RMSEC) of 0.0337 and 0.0334, respectively. The correlation coefficient（R） for model validation was 0.9817 with standard error of prediction (SEP) and root mean square error of prediction (RMSEP) of 0.0470 and 0.0465, respectively. This study indicated that NIR is a useful tool for fast prediction of wood water content of Korean pine. The modeling proficiency could be improved significantly for some certain wave length. It could be a research focus for future related studies.

Application of BP neural network and NIRS for larch wood density prediction was investigated in this paper. The original spectra were collected and pretreated with the first derivative and 9 point smoothing. Eleven typical wave lengths were selected as BP network inputs to establish prediction model for wood density. Model was validated using cross-validation approach. The prediction correlation coefficient (R) is 0.916 while the root mean square error of prediction (RMSEP) is 0.0221. The results showed that using BP neural network in near-infrared spectroscopy calibration could significantly improve the model performance in order to rapidly and accurately predict wood density.