期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 9, 期 9, 页码 4011-4021出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2016.2572879
关键词
Bagging-PLSR; local calibration; multivariate calibration; soil organic matter (SOM); spectral variable selection; VIS-NIR-SWIR
类别
资金
- Deutsche Forschungsgemeinschaft DFG [VO 1509/3-1, TH 678/12-1]
Estimation accuracies obtained for soil properties from spectroradiometer data markedly depend on the individual sample set. The choice of the statistical method to sample a calibration set and the extension of the multivariate modeling approach with bagging and/or spectral variable selection may optimize predictions. We studied this with a set of 172 arable topsoils from a region near Trier (Germany) that covered-as often typical for medium to large-scale applications of soil spectroscopy-a wide range of different soil situations. Yet, differences concerning target variables-organic carbon (OC), nitrogen (N), microbial biomass (Cmic) and thermostable carbon (C-inert)-were small. Based on a split of calibration and validation data with the Kennard-Stone algorithm, we found only moderate improvements towards partial least squares regression (PLSR) when combining PLSR with bagging and, for spectral variable selection, with competitive adaptive reweighted sampling (CARS). R-2 improved for OC (from 0.75 to 0.79), N(from 0.72 to 0.77) andC(inert) (from 0.66 to 0.68) in the validation. Additionally, we used individual calibration sets for each validation sample. In this local approach, we clustered calibration samples in the spectral feature space and selected individually the most similar sample from each cluster. Combining bagging-CARS-PLSR with this local approach improved R-2 markedly to 0.76 for C-inert, and slightly to 0.82 for OC and to 0.76 (previously 0.73) for Cmic. Effects of the local approach were twofold, as it removed improper samples from the calibration and balanced skewness in the data distribution.
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