期刊
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
卷 107, 期 1, 页码 139-146出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.chemolab.2011.02.008
关键词
Soil organic matter; NIR spectroscopy; Waveband selection; SG smoothing; MWPLS; Stability
类别
资金
- NSFC [10771087, 61078040]
- Science and Technology Project of Guangdong Province [2007A020905001, 2009B030801239]
Savitzky-Golay (SG) smoothing and moving window partial least square (MWPLS) methods were applied to the model optimization and the waveband selection for near-infrared (NIR) spectroscopy analysis of soil organic matter. The optimal single wavelength prediction bias (OSWPB) was used to evaluate the similarity of calibration set and prediction set, and a new division method for calibration set and prediction set was proposed. SG smoothing modes were expanded to 540 kinds. The specific computer algorithm platforms for optimization of SG smoothing mode combined with PLS factor and for MWPLS method with changeable parameters were built up. The optimal waveband for soil organic matter was 1926-2032 nm, the optimal smoothing mode was the 2nd order derivative, 6th degree polynomial, 45 smoothing points, the PLS factor, RMSEP and R(P) were 8, 0.260 (%) and 0.877 respectively. The prediction effect was obviously better than that in the whole spectral collecting region. To get stable results, all the optimization processes were based on the average prediction effect on 50 different divisions of calibration set and prediction set. (C) 2011 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据