Gustavo Togeiro de Alckmin1,2, Lammert Kooistra2, Richard Rawnsley3, Sytze de Bruin2, Arko Lucieer1. 1. School of Technology, Environments & Design, University of Tasmania-Geography and Spatial Sciences, Hobart, TAS 7001, Australia. 2. Laboratory of Geo-Information Science and Remote Sensing, Wageningen University & Research, P.O. Box 47, 6700 AA Wageningen, The Netherlands. 3. Centre for Dairy, Grains and Grazing, Tasmanian Institute of Agriculture, Cradle Coast Campus, 16-20 Mooreville Road, Burnie, TAS 7320, Australia.
Abstract
The use of spectral data is seen as a fast and non-destructive method capable of monitoring pasture biomass. Although there is great potential in this technique, both end users and sensor manufacturers are uncertain about the necessary sensor specifications and achievable accuracies in an operational scenario. This study presents a straightforward parametric method able to accurately retrieve the hyperspectral signature of perennial ryegrass (Lolium perenne) canopies from multispectral data collected within a two-year period in Australia and the Netherlands. The retrieved hyperspectral data were employed to generate optimal indices and continuum-removed spectral features available in the scientific literature. For performance comparison, both these simulated features and a set of currently employed vegetation indices, derived from the original band values, were used as inputs in a random forest algorithm and accuracies of both methods were compared. Our results have shown that both sets of features present similar accuracies (root mean square error (RMSE) ≈490 and 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 (ranging from 550 to 790 nm), better performing methods do not rely on the use of hyperspectral or, yet, in a larger number of bands than those already available in current sensors.
The use of spectral data is seen as a fast and non-destructive method capable of monitoring pasture biomass. Although there is great potential in this technique, both end users and sensor manufacturers are uncertain about the necessary sensor specifications and achievable accuracies in an operational scenario. This study presents a straightforward parametric method able to accurately retrieve the hyperspectral signature of pan class="Species">perennial ryegrass (n>n class="Species">Lolium perenne) canopies from multispectral data collected within a two-year period in Australia and the Netherlands. The retrieved hyperspectral data were employed to generate optimal indices and continuum-removed spectral features available in the scientific literature. For performance comparison, both these simulated features and a set of currently employed vegetation indices, derived from the original band values, were used as inputs in a random forest algorithm and accuracies of both methods were compared. Our results have shown that both sets of features present similar accuracies (root mean square error (RMSE) ≈490 and 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 (ranging from 550 to 790 nm), better performing methods do not rely on the use of hyperspectral or, yet, in a larger number of bands than those already available in current sensors.
Authors: Jonas Anderegg; Kang Yu; Helge Aasen; Achim Walter; Frank Liebisch; Andreas Hund Journal: Front Plant Sci Date: 2020-01-28 Impact factor: 5.753