Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level
Crude protein estimation is an important parameter for perennial ryegrass (<inline-formula><math display="inline"><semantics><mi mathvariant="italic">Loliumperenne</mi></semantics></math></inline-formula>) management. This study aim...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/18/2958 |
id |
doaj-db2170f862864600826cdadf054e76c5 |
---|---|
record_format |
Article |
spelling |
doaj-db2170f862864600826cdadf054e76c52020-11-25T03:48:07ZengMDPI AGRemote Sensing2072-42922020-09-01122958295810.3390/rs12182958Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy LevelGustavo Togeiro de Alckmin0Arko Lucieer1Gerbert Roerink2Richard Rawnsley3Idse Hoving4Lammert Kooistra5School of Technology, Environments and Design, University of Tasmania-Discipline of Geography and Spatial Sciences, Hobart, TAS 7005, AustraliaSchool of Technology, Environments and Design, University of Tasmania-Discipline of Geography and Spatial Sciences, Hobart, TAS 7005, AustraliaWageningen Environmental Research-Earth Informatics, Droevendaalsesteeg 3, 6708 PB Wageningen, The NetherlandsTasmanian Institute of Agriculture-Centre for Dairy, Grains and Grazing, 16-20 Mooreville Rd, Burnie, TAS 7320, AustraliaWageningen Livestock Research-Livestock and Environment, De Elst 1, 6700 AH Wageningen, The NetherlandsLaboratory of Geo-Information Science and Remote Sensing, Wageningen University, Droevendaalsesteeg 3, 6708 PB Wageningen, The NetherlandsCrude protein estimation is an important parameter for perennial ryegrass (<inline-formula><math display="inline"><semantics><mi mathvariant="italic">Loliumperenne</mi></semantics></math></inline-formula>) 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<inline-formula><math display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula>). These models can be employed in new unseen locations, resulting in a minor decrease in accuracy (RMSEP 85.5 kg.ha<inline-formula><math display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula>). 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.https://www.mdpi.com/2072-4292/12/18/2958perennial ryegrasshyperspectralmachine learningcrude proteinpartial least squaresfeature selection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Gustavo Togeiro de Alckmin Arko Lucieer Gerbert Roerink Richard Rawnsley Idse Hoving Lammert Kooistra |
spellingShingle |
Gustavo Togeiro de Alckmin Arko Lucieer Gerbert Roerink Richard Rawnsley Idse Hoving Lammert Kooistra Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level Remote Sensing perennial ryegrass hyperspectral machine learning crude protein partial least squares feature selection |
author_facet |
Gustavo Togeiro de Alckmin Arko Lucieer Gerbert Roerink Richard Rawnsley Idse Hoving Lammert Kooistra |
author_sort |
Gustavo Togeiro de Alckmin |
title |
Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level |
title_short |
Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level |
title_full |
Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level |
title_fullStr |
Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level |
title_full_unstemmed |
Retrieval of Crude Protein in Perennial Ryegrass Using Spectral Data at the Canopy Level |
title_sort |
retrieval of crude protein in perennial ryegrass using spectral data at the canopy level |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-09-01 |
description |
Crude protein estimation is an important parameter for perennial ryegrass (<inline-formula><math display="inline"><semantics><mi mathvariant="italic">Loliumperenne</mi></semantics></math></inline-formula>) 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<inline-formula><math display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula>). These models can be employed in new unseen locations, resulting in a minor decrease in accuracy (RMSEP 85.5 kg.ha<inline-formula><math display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula>). 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. |
topic |
perennial ryegrass hyperspectral machine learning crude protein partial least squares feature selection |
url |
https://www.mdpi.com/2072-4292/12/18/2958 |
work_keys_str_mv |
AT gustavotogeirodealckmin retrievalofcrudeproteininperennialryegrassusingspectraldataatthecanopylevel AT arkolucieer retrievalofcrudeproteininperennialryegrassusingspectraldataatthecanopylevel AT gerbertroerink retrievalofcrudeproteininperennialryegrassusingspectraldataatthecanopylevel AT richardrawnsley retrievalofcrudeproteininperennialryegrassusingspectraldataatthecanopylevel AT idsehoving retrievalofcrudeproteininperennialryegrassusingspectraldataatthecanopylevel AT lammertkooistra retrievalofcrudeproteininperennialryegrassusingspectraldataatthecanopylevel |
_version_ |
1724500159725830144 |