Waveband selection using a phased regression with a bootstrap procedure for estimating legume content in a mixed sown pasture
Waveband selection using a phased regression with a bootstrap procedure for estimating legume content in a mixed sown pasture
复制标题
使用分阶段回归和引导程序进行波段选择，用于估计混合播种牧场中的豆类含量
DOI：
10.1111/j.1744-697x.2011.00212.x
复制
发表时间：
2011
影响因子：
1.3
通讯作者：
Y.
中科院分区：
文献类型：
--
作者：
Kawamura K.;Watanabe N.;Sakanoue S.;Lee H.-J.;Inou;Y.
豆科牧草混播中的豆科牧草含量是决定牧草品质和牧草施肥量的关键参数。为了估计北海道的草-白色三叶草（WC）混合牧场中的豆类含量，我们在400-2350 nm范围内搜索了来自situcanopy反射光谱的稳健高光谱波段，并将阶段回归与自助程序（PHR-BS）（Ferwerdaet al.2006）和前向逐步多元线性回归（FS-MLR）进行了比较。 冠层反射率数据和植物样本，从50个选定的网站在两个季节（n=100），春季（5月）和夏季（7月）2007年。虽然PHR-BS和FS-MLR中选择的波段相似，但PHR-BS的预测准确率（44-74%）高于FS-MLR（35-73%）。最终模型中选择的波段是可见光波段的蓝色（400-456 nm）和红色（659-670 nm），红边区域（704-724 nm），近红外区域（813，937和1121 nm）和短波红外区域（2303-2344 nm），主要与已知的生物化学成分如叶绿素，N，木质素和纤维素有关。 这些结果表明，豆科牧草混合物中的豆科植物含量可以通过原位反射率进行预测，并且可以通过使用PHR-BS方法的波长选择来提高模型的预测能力。
Legume content in grass–legume mixtures is a key parameter for deciding the forage quality and the amount of fertilizer application to the pasture due to nitrogen (N) fixation. To estimate legume content in a grass‐white clover (WC) mixed pasture in Hokkaido, we searched for robust hyperspectral wavebands fromin situcanopy reflectance spectra over the 400–2350 nm range comparing a phased regression with a bootstrap procedure (PHR‐BS) (Ferwerdaet al.2006) and forward stepwise multiple linear regression (FS‐MLR). Canopy reflectance data and plant samples were obtained from 50 selected sites during two seasons (n=100); spring (May) and summer (July) 2007. Although selected wavebands were similar in the PHR‐BS and FS‐MLR, PHR‐BS gave a higher predictive accuracy (44–74%) than FS‐MLR (35–73%). Selected wavebands in the final models were blue (400–456 nm) and red bands (659–670 nm) in visible wavelength, red‐edge region (704–724 nm), near infrared regions (813, 937, and 1121 nm), and shortwave infrared regions (2303–2344 nm) that are mainly linked to known biochemical components such as chlorophyll, N, lignin and cellulose. These results suggest that legume content in grass–legume mixtures can be predicted byin situcanopy reflectance, and that the predictive ability of the model can be improved by wavelength selection using the PHR‐BS method.