首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat
Authors:Clement Atzberger  Martine Guérif  Willy Werner
Institution:a Joint Research Centre of the European Commission, JRC, Institute for the Protection and Security of the Citizen, IPSC, MARS Unit, Via Enrico Fermi 2749, 21027 Ispra, Italy
b Institute Nationale de la Recherche Agronomique (INRA), 84000 Avignon, France
c University of Trier, Dept. of Geobotanics, Geozentrum, 54290 Trier, Germany
Abstract:Hyperspectral data sets contain useful information for characterizing vegetation canopies not previously available from multi-spectral data sources. However, to make full use of the information content one has to find ways for coping with the strong multi-collinearity in the data. The redundancy directly results from the fact that only a few variables effectively control the vegetation signature. This low dimensionality strongly contrasts with the often more than 100 spectral channels provided by modern spectroradiometers and through imaging spectroscopy. With this study we evaluated three different chemometric techniques specifically designed to deal with redundant (and small) data sets. In addition, a widely used 2-band vegetation index was chosen (NDVI) as a baseline approach. A multi-site and multi-date field campaign was conducted to acquire the necessary reference observations. On small subplots the total canopy chlorophyll content was measured and the corresponding canopy signature (450-2500 nm) was recorded (nobs = 42). Using this data set we investigated the predictive power and noise sensitivity of stepwise multiple linear regression (SMLR) and two ‘full spectrum’ methods: principal component regression (PCR) and partial least squares regression (PLSR). The NDVI was fitted to the canopy chlorophyll content using an exponential relation. For all techniques, a jackknife approach was used to obtain cross-validated statistics. The PLSR clearly outperformed all other techniques. PLSR gave a cross-validated RMSE of 51 mg m−2View the MathML source for canopy chlorophyll contents ranging between 38 and 475 mg m−2 (0.99 ≤ LAI ≤ 8.74 m2 m−2). The lowest accuracy was achieved using PCR (RMSEcv = 82 mg m−2 and View the MathML source). The NDVI, even using chlorophyll optimized band settings, could not reach the accuracy of PLSR. Regarding the sensitivity to artificially created (white) noise, PCR showed some advantages, whereas SMLR was the most sensitive chemometric technique. For relatively small, highly multi-collinear data sets the use of partial least square regression is recommended. PLSR makes full use of the rich spectral information while being relatively insensitive to sensor noise. PLSR provides a regression model where the entire spectral information is taken - in a weighted form - into account. This method seems therefore much better adapted to deal with potentially confounding factors compared to any 2-band vegetation index which can only avoid the most harmful factor of variation.
Keywords:Data redundancy  Partial least squares regression  Principal component regression  Stepwise multiple linear regression  Canopy chlorophyll content  Noise sensitivity
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号