A selective review and comparison for interval variable selection in spectroscopic modeling

Wang, Lili; Lin, You-Wu; Wang, Xufei; Xiao, Nan; Xu, Yulong; Li, Hongdong; Xu, Qingsong

doi:10.1016/j.chemolab.2017.11.008

Cited by 54 publications

(18 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of variable selection methods such as elastic net is not restricted to regression purposes but can also improve standard methods such as partial least squares regression (Höskuldsson 2001;Wang et al 2017). Therefore, sparse PLS (SPLS), which…”

Section: Discussionmentioning

confidence: 99%

Hyperspectral VNIR-spectroscopy and imagery as a tool for monitoring herbicide damage in wilding conifers

et al. 2019

View full text Add to dashboard Cite

Wilding conifers, the naturally regenerated scions of exotic conifer species, are a major ecological and economic issue in New Zealand. Hyperspectral imagery could provide a useful means of monitoring the efficacy of wilding control measures but little research has examined this possibility. Data were collected from an experiment, that included thirty-nine young Pinus contorta (Douglas) trees allocated to a control and two herbicide treatments (triclopyr butoxyethyl ester and diquat dibromide monohydrate). The objectives of this research were to examine the temporal impacts of herbicide on needle discolouration, spectral properties and tree physiology and to develop models to predict photosynthetic parameters from hyperspectral data. In accordance with obvious discolouration on the first day after treatment, values of net photosynthesis rate (A), electron transport rate (ETR), stomatal conductance (G) and optimal quantum yield of photosystem II (F v /F m) declined rapidly for plants treated with diquat. Discolouration following application of triclopyr was not evident before the second week, and values of A, ETR, G and F v /F m declined slower than those of diquat. Of the tested narrow-band spectral indices calculated from needle spectra photochemical reflectance index (PRI) exhibited the strongest correlation with the four photosynthetic parameters and R 2 values between PRI and A, F v / F m , ETR and G were, respectively, 0.53, 0.46, 0.68 and 0.29. Models that used raw spectra as inputs showed that sparse partial least squares (SPLS) outperformed the three other approaches tested (PLS, Support Vector Machines, Elastic Net) and R 2 values using this approach for A, F v /F m , ETR and G were, respectively, 0.64, 0.62, 0.65 and 0.42.

show abstract

Section: Discussionmentioning

confidence: 99%

Hyperspectral VNIR-spectroscopy and imagery as a tool for monitoring herbicide damage in wilding conifers

et al. 2019

View full text Add to dashboard Cite

show abstract

“…There are mainly four chosen regions in the two screening methods, including the 1756‐1668, 1468‐1456, 1310‐1296, and 1176‐1172 (nm). These ATR‐FTIR spectra regions represent the C═O carbonyl stretching of saturated aliphatic esters, C−O stretching of carboxylic acids, and so on.…”

Section: Resultsmentioning

confidence: 99%

High‐dimensional spectral data classification with nonparametric feature screening

2019

Journal of Chemometrics

View full text Add to dashboard Cite

Two nonparametric feature screening methods, namely, the Kolmogorov filter and model free, marginally measure the relationship between categorical response and predictor variables without the parametrical assumption. And they can select important variables in the high‐dimensional classification data. Random forest, as a classical nonparametric method, can solve various classification problems. In this paper, we combine the two nonparametric feature screening methods with random forest to handle with spectral data classification. And then other conventional classification methods are compared with ours on three spectral datasets. The comparison results illustrated that our methods have more desirable ability about classification performance and variable selection than other methods.

show abstract

“…In this approach, the observed absorption is related to a reference measurement (typically gravimetric mass) of the compounds on the substrate. In this way, calibration of nitrate and sulfate salts (Cunningham et al, 1974;Cunningham and Johnson, 1976;Bogard et al, 1982;McClenny et al, 1985;McClenny, 1992, 1994;Pollard et al, 1990;Tsai and Kuo, 2006;Reff et al, 2007), silica dust (Foster and Walker, 1984;Weakley et al, 2014;Wei et al, 2017), and organic functional groups (Allen and Palen, 1989;Paulson et al, 1990;Pickle et al, 1990;Mylonas et al, 1991;Palen et al, 1992Palen et al, , 1993Holes et al, 1997;Blando et al, 1998;Maria et al, 2002Maria et al, , 2003Sax et al, 2005;Gilardoni et al, 2007;Reff et al, 2007;Coury and Dillner, 2008;Day et al, 2010;Takahama et al, 2013;Faber et al, 2017) has been studied. The organic carbon and organic aerosol mass reconstructed has typically ranged between 70 % and 100 % when compared with collocated evolved-gas analysis or mass spectrometry measurements (Russell et al, 2009;Corrigan et al, 2013), though many model uncertainties remain.…”

Section: Limits Of Conventional Approaches To Calibrationmentioning

confidence: 99%

“…The essential principle of wrapper methods is to apply variable filters successively or iteratively to sample data until only a desirable subset of quintessential variables remain for PLS modeling (Leardi, 2000;Leardi and Nørgaard, 2004;Weakley et al, 2014 (Leardi, 2000;Leardi and Nørgaard, 2004). Wrapper methods generally perform better than simple filter methods and have an additional benefit of considering both variables and PLS components simultaneously during optimization.…”

Section: Wavenumber Selectionmentioning

confidence: 99%

Atmospheric particulate matter characterization by Fourier transform infrared spectroscopy: a review of statistical calibration strategies for carbonaceous aerosol quantification in US measurement networks

et al. 2019

View full text Add to dashboard Cite

Abstract. Atmospheric particulate matter (PM) is a complex mixture of many different substances and requires a suite of instruments for chemical characterization. Fourier transform infrared (FT-IR) spectroscopy is a technique that can provide quantification of multiple species provided that accurate calibration models can be constructed to interpret the acquired spectra. In this capacity, FT-IR spectroscopy has enjoyed a long history in monitoring gas-phase constituents in the atmosphere and in stack emissions. However, application to PM poses a different set of challenges as the condensed-phase spectrum has broad, overlapping absorption peaks and contributions of scattering to the mid-infrared spectrum. Past approaches have used laboratory standards to build calibration models for prediction of inorganic substances or organic functional groups and predict their concentration in atmospheric PM mixtures by extrapolation. In this work, we review recent studies pursuing an alternate strategy, which is to build statistical calibration models for mid-IR spectra of PM using collocated ambient measurements. Focusing on calibrations with organic carbon (OC) and elemental carbon (EC) reported from thermal–optical reflectance (TOR), this synthesis serves to consolidate our knowledge for extending FT-IR spectroscopy to provide TOR-equivalent OC and EC measurements to new PM samples when TOR measurements are not available. We summarize methods for model specification, calibration sample selection, and model evaluation for these substances at several sites in two US national monitoring networks: seven sites in the Interagency Monitoring of Protected Visual Environments (IMPROVE) network for the year 2011 and 10 sites in the Chemical Speciation Network (CSN) for the year 2013. We then describe application of the model in an operational context for the IMPROVE network for samples collected in 2013 at six of the same sites as in 2011 and 11 additional sites. In addition to extending the evaluation to samples from a different year and different sites, we describe strategies for error anticipation due to precision and biases from the calibration model to assess model applicability for new spectra a priori. We conclude with a discussion regarding past work and future strategies for recalibration. In addition to targeting numerical accuracy, we encourage model interpretation to facilitate understanding of the underlying structural composition related to operationally defined quantities of TOR OC and EC from the vibrational modes in mid-IR deemed most informative for calibration. The paper is structured such that the life cycle of a statistical calibration model for FT-IR spectroscopy can be envisioned for any substance with IR-active vibrational modes, and more generally for instruments requiring ambient calibrations.

show abstract

A selective review and comparison for interval variable selection in spectroscopic modeling

Cited by 54 publications

References 65 publications

Hyperspectral VNIR-spectroscopy and imagery as a tool for monitoring herbicide damage in wilding conifers

Hyperspectral VNIR-spectroscopy and imagery as a tool for monitoring herbicide damage in wilding conifers

High‐dimensional spectral data classification with nonparametric feature screening

Atmospheric particulate matter characterization by Fourier transform infrared spectroscopy: a review of statistical calibration strategies for carbonaceous aerosol quantification in US measurement networks

Contact Info

Product

Resources

About