1. Comparison of three multivariate methods of inferential modeling of soil organic matter using hyper spectra
- Author
-
Li-Xin Chen, Lu Qiao, Xiu-Feng Wang, Wen-Biao Duan, and Rui-Qing Song
- Subjects
Multivariate statistics ,Coefficient of determination ,Mean squared error ,Soil test ,Soil organic matter ,Partial least squares regression ,Statistics ,Linear regression ,Regression analysis ,Mathematics - Abstract
The paper investigated the feasibility of Hyper spectra to determine the concentration of soil organic matter (SOM) in Harbin. The 95 soil samples were collected to a depth from 0 to 20cm. Reflectance measurements from 350nm to 2500nm were collected in a controlled laboratory environment. Three multivariate techniques (stepwise multiple linear regression(SMLR), artificial neural network(ANN), partial least-squares regression(PLSR)) and pre-processing transform nations of spectral data were compared with the aim of identifying the best combination to predict soil organic matter. The coefficient of determination (R2), the root mean square error (RMSE) were used to evaluate the models. compared three multivariate methods of inferential modeling, based on R2 and RMSE, partial least-squares regression performed best (the highest averageR2=0.826, the lowest average RMSE = 0.161).
- Published
- 2011