Open Access Repository

Retrieval of hyperspectral information from multispectral data for perennial ryegrass biomass estimation

Downloads

Downloads per month over past year

Togeiro de Alckmin, G, Kooistra, L, Rawnsley, R ORCID: 0000-0001-5381-0208, de Bruin, S and Lucieer, A ORCID: 0000-0002-9468-4516 2020 , 'Retrieval of hyperspectral information from multispectral data for perennial ryegrass biomass estimation' , Sensors, vol. 20, no. 24 , pp. 1-20 , doi: 10.3390/s20247192.

[img]
Preview
PDF (Published version)
148022 - Retrie...pdf | Download (1MB)

| Preview

Abstract

The use of spectral data is seen as a fast and non-destructive method capable of monitoringpasture biomass. Although there is great potential in this technique, both end users and sensormanufacturers are uncertain about the necessary sensor specifications and achievable accuracies inan operational scenario. This study presents a straightforward parametric method able to accuratelyretrieve the hyperspectral signature of perennial ryegrass (Lolium perenne) canopies from multispectraldata collected within a two-year period in Australia and the Netherlands. The retrieved hyperspectraldata were employed to generate optimal indices and continuum-removed spectral features availablein the scientific literature. For performance comparison, both these simulated features and a set ofcurrently employed vegetation indices, derived from the original band values, were used as inputsin a random forest algorithm and accuracies of both methods were compared. Our results haveshown that both sets of features present similar accuracies (root mean square error (RMSE) ≈490and 620 kg DM/ha) when assessed in cross-validation and spatial cross-validation, respectively.These results suggest that for pasture biomass retrieval solely from top-of-canopy reflectance (rangingfrom 550 to 790 nm), better performing methods do not rely on the use of hyperspectral or, yet, in alarger number of bands than those already available in current sensors.

Item Type: Article
Authors/Creators:Togeiro de Alckmin, G and Kooistra, L and Rawnsley, R and de Bruin, S and Lucieer, A
Keywords: vegetation indices, spectral resampling, continuum-removal, parametric-regression, spectral simulation, machine learning, random-forest
Journal or Publication Title: Sensors
Publisher: MDPI AG
ISSN: 1424-8220
DOI / ID Number: 10.3390/s20247192
Copyright Information:

Copyright: © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons 4.0 International (CC BY 4.0) license (https://creativecommons.org/licenses/by/4.0/).

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP