A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra

Cai, Wensheng; Li, Yankun; Shao, Xueguang

doi:10.1016/j.chemolab.2007.10.001

Cited by 478 publications

(195 citation statements)

References 34 publications

Supporting

Mentioning

194

Contrasting

Unclassified

Order By: Relevance

“…We used uninformative variable elimination PLS (UVE PLS; Cai et al, 2008;Centner et al, 1996) to identify the most informative spectral regions of the hyperspectral data. This method has been used previously to find informative spectral bands for leaf chlorophyll and carotenoid content estimation (Kira et al, 2015).…”

Section: Discussionmentioning

confidence: 99%

Informative spectral bands for remote green LAI estimation in C3 and C4 crops

Kira

Nguy-Robertson

Arkebauer

et al. 2016

Agricultural and Forest Meteorology

View full text Add to dashboard Cite

Informative spectral bands for remote green LAI estimation in C3 and C4 crops" (2016). Papers in Natural Resources. 669. https://digitalcommons.unl.edu/natrespapers/669 K i r a e t a l . i n A g r i c u l t u r a l a n d F o r e s t M e t e o r o l o g y2 1 8 -2 1 9 ( 2 0 1 6 ) AbstractGreen leaf area index (LAI) provides insight into the productivity, physiological and phenological status of vegetation. Measurement of spectral reflectance offers a fast and nondestructive estimation of green LAI. A number of methods have been used for the estimation of green LAI; however, the specific spectral bands employed varied widely among the methods and data used. Our objectives were (i) to find informative spectral bands retained in three types of methods, neural network (NN), partial least squares (PLS) regression and vegetation indices (VI), for estimating green LAI in maize (a C4 species) and soybean (a C3 species); (ii) to assess the accuracy of the algorithms estimating green LAI using a minimal number of bands for each crop and generic algorithms for the two crops combined. Hyperspectral reflectance and green LAI of irrigated and rainfed maize and soybean were taken during eight years of observations (altogether 24 field-years) in very different weather conditions. The bands retained in the best NN, PLS and VI methods were in close agreement. The validity of these bands was further confirmed via the uninformative variable elimination PLS technique. The red edge and the NIR bands were selected in all models and were found the most informative. Identifying informative spectral bands across all four techniques provided insight into spectral features of reflectance specific for each species as well as those that are common to species with different leaf structures, canopy architectures and photosynthetic pathways. The analyses allowed development of algorithms for estimating green LAI in soybean and maize with no re-parameterization. These findings lay a strong foundation for the development of generic algorithms which is crucial for remote sensing of vegetation biophysical parameters.Keywords: Remote sensing, Reflectance, Neural network, Partial least squares, Vegetation index, Maize, Soybean digitalcommons.unl.edu K i r a e t a l . i n A g r i c u l t u r a l a n d F o r e s t M e t e o r o l o g y2 1 8 -2 1 9 ( 2 0 1 6 ) 2

show abstract

Section: Discussionmentioning

confidence: 99%

Informative spectral bands for remote green LAI estimation in C3 and C4 crops

Kira

Nguy-Robertson

Arkebauer

et al. 2016

Agricultural and Forest Meteorology

View full text Add to dashboard Cite

show abstract

“…Each spectral band has a reliability value c ρ calculated on the basis of its regression coefficient in the model. The uninformative bands are the ones with a lower absolute reliability coefficient [21,[44][45][46]. The reliability parameter c ρ is obtained by dividing the mean regression coefficient (b ρ ) by the standard deviation of the regression coefficient vector (std(b ρ )):…”

Section: Techniques and Analysismentioning

confidence: 99%

Toward Generic Models for Green LAI Estimation in Maize and Soybean: Satellite Observations

et al. 2017

View full text Add to dashboard Cite

Abstract:Informative spectral bands for green leaf area index (LAI) estimation in two crops were identified and generic models for soybean and maize were developed and validated using spectral data taken at close range. The objective of this paper was to test developed models using Aqua and Terra MODIS, Landsat TM and ETM+, ENVISAT MERIS surface reflectance products, and simulated data of the recently-launched Sentinel 2 MSI and Sentinel 3 OLCI. Special emphasis was placed on testing generic models which require no re-parameterization for these species. Four techniques were investigated: support vector machines (SVM), neural network (NN), multiple linear regression (MLR), and vegetation indices (VI). For each technique two types of models were tested based on (a) reflectance data, taken at close range and resampled to simulate spectral bands of satellite sensors; and (b) surface reflectance satellite products. Both types of models were validated using MODIS, TM/ETM+, and MERIS data. MERIS was used as a prototype of OLCI Sentinel-3 data which allowed for assessment of the anticipated accuracy of OLCI. All models tested provided a robust and consistent selection of spectral bands related to green LAI in crops representing a wide range of biochemical and structural traits. The MERIS observations had the lowest errors (around 11%) compared to the remaining satellites with observational data. Sentinel 2 MSI and OLCI Sentinel 3 estimates, based on simulated data, had errors below 8%. However the accuracy of these models with actual MSI and OLCI surface reflectance products remains to be determined.

show abstract

“…25,26 Up to now, there are many e®ective methods for variable selection. [27][28][29][30][31][32] CSMWPLS, 18 as one of them, is a strategy to search for an optimized subregion in spectral regions for producing better results. The superiorities of this method are: the window size is changeable and the window moves through the whole spectral region with¯xed step.…”

Section: Changeable Size Moving Window Partial Least Squaresmentioning

confidence: 99%

Geographical classification of Nanfeng mandarin by near infrared spectroscopy coupled with chemometrics methods

Zhang

Tong

et al. 2014

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

Near infrared spectroscopy (NIRS), coupled with principal component analysis and wavelength selection techniques, has been used to develop a robust and reliable reduced-spectrum classi¯-cation model for determining the geographical origins of Nanfeng mandarins. The application of the changeable size moving window principal component analysis (CSMWPCA) provided a notably improved classi¯cation model, with correct classi¯cation rates of 92.00%, 100.00%, 90.00%, 100.00%, 100.00%, 100.00% and 100.00% for Fujian, Guangxi, Hunan, Baishe, Baofeng, Qiawan, Sanxi samples, respectively, as well as, a total classi¯cation rate of 97.52% in the wavelength range from 1007 to 1296 nm. To test and apply the proposed method, the procedure was applied to the analysis of 59 samples in an independent test set. Good identi¯cation results (correct rate of 96.61%) were also received. The improvement achieved by the application of CSMWPCA method was particularly remarkable when taking the low complexities of the¯nal model (290 variables) into account. The results of the study showed the great potential of NIRS as a fast, nondestructive and environmentally acceptable method for the rapid and reliable determination for geographical classi¯cation of Nanfeng mandarins.

show abstract

A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra

Cited by 478 publications

References 34 publications

Informative spectral bands for remote green LAI estimation in C3 and C4 crops

Informative spectral bands for remote green LAI estimation in C3 and C4 crops

Toward Generic Models for Green LAI Estimation in Maize and Soybean: Satellite Observations

Geographical classification of Nanfeng mandarin by near infrared spectroscopy coupled with chemometrics methods

Contact Info

Product

Resources

About