Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level

Remote Sensing

Lammert Kooistra¹  GustavoTogeiro de Alckmin²  Arko Lucieer²  Richard Rawnsley³  Gerbert Roerink⁴  Idse Hoving⁵ 

[1] Laboratory of Geo-Information Science and Remote Sensing, Wageningen University, Droevendaalsesteeg 3, 6708 PB Wageningen, The Netherlands;School of Technology, Environments and Design, University of Tasmania-Discipline of Geography and Spatial Sciences, Hobart, TAS 7005, Australia;Tasmanian Institute of Agriculture-Centre for Dairy, Grains and Grazing, 16-20 Mooreville Rd, Burnie, TAS 7320, Australia;Wageningen Environmental Research-Earth Informatics, Droevendaalsesteeg 3, 6708 PB Wageningen, The Netherlands;Wageningen Livestock Research-Livestock and Environment, De Elst 1, 6700 AH Wageningen, The Netherlands;

关键词: perennial ryegrass;    hyperspectral;    machine learning;    crude protein;    partial least squares;    feature selection;   

DOI  :  10.3390/rs12182958

来源: DOAJ

【 摘 要 】

Crude protein estimation is an important parameter for perennial ryegrass ($\mathit{Loliumperenne}$) management. This study aims to establish an effective and affordable approach for a non-destructive, near-real-time crude protein retrieval based solely on top-of-canopy reflectance. The study contrasts different spectral ranges while selecting a minimal number of bands and analyzing achievable accuracies for crude protein expressed as a dry matter fraction or on a weight-per-area basis. In addition, the model’s prediction performance in known and new locations is compared. This data collection comprised 266 full-range (350–2500 nm) proximal spectral measurements and corresponding ground truth observations in Australia and the Netherlands from May to November 2018. An exhaustive-search (based on a genetic algorithm) successfully selected band subsets within different regions and across the full spectral range, minimizing both the number of bands and an error metric. For field conditions, our results indicate that the best approach for crude protein estimation relies on the use of the visible to near-infrared range (400–1100 nm). Within this range, eleven sparse broad bands (of 10 nm bandwidth) provide performance better than or equivalent to those of previous studies that used a higher number of bands and narrower bandwidths. Additionally, when using top-of-canopy reflectance, our results demonstrate that the highest accuracy is achievable when estimating crude protein on its weight-per-area basis (RMSEP 80 kg.ha${}^{-1}$). These models can be employed in new unseen locations, resulting in a minor decrease in accuracy (RMSEP 85.5 kg.ha${}^{-1}$). Crude protein as a dry matter fraction presents a bottom-line accuracy (RMSEP) ranging from 2.5–3.0 percent dry matter in optimal models (requiring ten bands). However, these models display a low explanatory ability for the observed variability (R2 > 0.5), rendering them only suitable for qualitative grading.

【 授权许可】

Unknown