fulltext.study @t Gmail

Gaussian processes retrieval of leaf parameters from a multi-species reflectance, absorbance and fluorescence dataset

Paper ID Volume ID Publish Year Pages File Format Full-Text
29409 44389 2014 12 PDF Available
Title
Gaussian processes retrieval of leaf parameters from a multi-species reflectance, absorbance and fluorescence dataset
Abstract

•Gaussian Processes (GP) regression on spectra is used for leaf parameter retrieval.•A wide range in each leaf variable (e.g. chlorophyll 15.9–189 μg cm−2) is covered.•GP ranks the relevant hyperspectral wavelengths from the full range spectra.•Distinctive bands in the VIS, NIR and SWIR are chosen for each parameter estimation.•Broadly applicable estimation models avoiding saturation problems are delivered.

Biochemical and structural leaf properties such as chlorophyll content (Chl), nitrogen content (N), leaf water content (LWC), and specific leaf area (SLA) have the benefit to be estimated through nondestructive spectral measurements. Current practices, however, mainly focus on a limited amount of wavelength bands while more information could be extracted from other wavelengths in the full range (400–2500 nm) spectrum. In this research, leaf characteristics were estimated from a field-based multi-species dataset, covering a wide range in leaf structures and Chl concentrations. The dataset contains leaves with extremely high Chl concentrations (>100 μg cm−2), which are seldom estimated. Parameter retrieval was conducted with the machine learning regression algorithm Gaussian Processes (GP), which is able to perform adaptive, nonlinear data fitting for complex datasets. Moreover, insight in relevant bands is provided during the development of a regression model. Consequently, the physical meaning of the model can be explored. Best estimates of SLA, LWC and Chl yielded a best obtained normalized root mean square error of 6.0%, 7.7%, 9.1%, respectively. Several distinct wavebands were chosen across the whole spectrum. A band in the red edge (710 nm) appeared to be most important for the estimation of Chl. Interestingly, spectral features related to biochemicals with a structural or carbon storage function (e.g. 1090, 1550, 1670, 1730 nm) were found important not only for estimation of SLA, but also for LWC, Chl or N estimation. Similar, Chl estimation was also helped by some wavebands related to water content (950, 1430 nm) due to correlation between the parameters. It is shown that leaf parameter retrieval by GP regression is successful, and able to cope with large structural differences between leaves.

Keywords
Machine learning algorithm; Spectral features; Hyperspectral; Parameter retrieval; Chlorophyll; Leaf structure; Specific leaf area; Leaf water content
First Page Preview
Gaussian processes retrieval of leaf parameters from a multi-species reflectance, absorbance and fluorescence dataset
Get Full-Text Now
Don't Miss Today's Special Offer
Price was $35.95
You save - $31
Price after discount Only $4.95
100% Money Back Guarantee
Full-text PDF Download
Online Support
Any Questions? feel free to contact us
Publisher
Database: Elsevier - ScienceDirect
Journal: Journal of Photochemistry and Photobiology B: Biology - Volume 134, 5 May 2014, Pages 37–48
Authors
, , , , , ,
Subjects
Physical Sciences and Engineering Chemical Engineering Bioengineering
Get Full-Text Now
Don't Miss Today's Special Offer
Price was $35.95
You save - $31
Price after discount Only $4.95
100% Money Back Guarantee
Full-text PDF Download
Online Support
Any Questions? feel free to contact us