Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat
Hyperspectral imaging (HSI) is an emerging rapid and non-destructive technology that has promising application within feed mills and processing plants in poultry and other intensive animal industries. HSI may be advantageous over near infrared spectroscopy (NIRS) as it scans entire samples, which en...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/6/1128 |
| _version_ | 1827697566855200768 |
|---|---|
| author | Iman Tahmasbian Natalie K. Morgan Shahla Hosseini Bai Mark W. Dunlop Amy F. Moss |
| author_facet | Iman Tahmasbian Natalie K. Morgan Shahla Hosseini Bai Mark W. Dunlop Amy F. Moss |
| author_sort | Iman Tahmasbian |
| collection | DOAJ |
| description | Hyperspectral imaging (HSI) is an emerging rapid and non-destructive technology that has promising application within feed mills and processing plants in poultry and other intensive animal industries. HSI may be advantageous over near infrared spectroscopy (NIRS) as it scans entire samples, which enables compositional gradients and sample heterogenicity to be visualised and analysed. This study was a preliminary investigation to compare the performance of HSI with that of NIRS for quality measurements of ground samples of Australian wheat and to identify the most important spectral regions for predicting carbon (C) and nitrogen (N) concentrations. In total, 69 samples were scanned using an NIRS (400–2500 nm), and two HSI cameras operated in 400–1000 nm (VNIR) and 1000–2500 nm (SWIR) spectral regions. Partial least square regression (PLSR) models were used to correlate C and N concentrations of 63 calibration samples with their spectral reflectance, with 6 additional samples used for testing the models. The accuracy of the HSI predictions (full spectra) were similar or slightly higher than those of NIRS (NIRS <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi mathvariant="normal">R</mi><mi mathvariant="normal">c</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> for C = 0.90 and N = 0.96 vs. HSI <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi mathvariant="normal">R</mi><mi mathvariant="normal">c</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> for C (VNIR) = 0.97 and N (SWIR) = 0.97). The most important spectral region for C prediction identified using HSI reflectance was 400–550 nm with R<sup>2</sup> of 0.93 and RMSE of 0.17% in the calibration set and R<sup>2</sup> of 0.86, RMSE of 0.21% and ratio of performance to deviation (RPD) of 2.03 in the test set. The most important spectral regions for predicting N concentrations in the feed samples included 1451–1600 nm, 1901–2050 nm and 2051–2200 nm, providing prediction with R<sup>2</sup> ranging from 0.91 to 0.93, RMSE ranging from 0.06% to 0.07% in the calibration sets, R<sup>2</sup> from 0.96 to 0.99, RMSE of 0.06% and RPD from 3.47 to 3.92 in the test sets. The prediction accuracy of HSI and NIRS were comparable possibly due to the larger statistical population (larger number of pixels) that HSI provided, despite the fact that HSI had smaller spectral range compared with that of NIRS. In addition, HSI enabled visualising the variability of C and N in the samples. Therefore, HSI is advantageous compared to NIRS as it is a multifunctional tool that poses many potential applications in data collection and quality assurance within feed mills and poultry processing plants. The ability to more accurately measure and visualise the properties of feed ingredients has potential economic benefits and therefore additional investigation and development of HSI in this application is warranted. |
| first_indexed | 2024-03-10T13:11:46Z |
| format | Article |
| id | doaj.art-8e0f965347334775ad3d780f90269cbe |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T13:11:46Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8e0f965347334775ad3d780f90269cbe2023-11-21T10:44:12ZengMDPI AGRemote Sensing2072-42922021-03-01136112810.3390/rs13061128Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in WheatIman Tahmasbian0Natalie K. Morgan1Shahla Hosseini Bai2Mark W. Dunlop3Amy F. Moss4Department of Agriculture and Fisheries, Queensland Government, Toowoomba, QLD 4350, Australia; Scopus affiliation ID: 60028929School of Environmental and Rural Science, University of New England, Armidale, NSW 2351, AustraliaCentre for Planetary Health and Food Security, School of Environment and Science, Griffith University, Brisbane, QLD 4111, AustraliaDepartment of Agriculture and Fisheries, Queensland Government, Toowoomba, QLD 4350, Australia; Scopus affiliation ID: 60028929School of Environmental and Rural Science, University of New England, Armidale, NSW 2351, AustraliaHyperspectral imaging (HSI) is an emerging rapid and non-destructive technology that has promising application within feed mills and processing plants in poultry and other intensive animal industries. HSI may be advantageous over near infrared spectroscopy (NIRS) as it scans entire samples, which enables compositional gradients and sample heterogenicity to be visualised and analysed. This study was a preliminary investigation to compare the performance of HSI with that of NIRS for quality measurements of ground samples of Australian wheat and to identify the most important spectral regions for predicting carbon (C) and nitrogen (N) concentrations. In total, 69 samples were scanned using an NIRS (400–2500 nm), and two HSI cameras operated in 400–1000 nm (VNIR) and 1000–2500 nm (SWIR) spectral regions. Partial least square regression (PLSR) models were used to correlate C and N concentrations of 63 calibration samples with their spectral reflectance, with 6 additional samples used for testing the models. The accuracy of the HSI predictions (full spectra) were similar or slightly higher than those of NIRS (NIRS <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi mathvariant="normal">R</mi><mi mathvariant="normal">c</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> for C = 0.90 and N = 0.96 vs. HSI <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi mathvariant="normal">R</mi><mi mathvariant="normal">c</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> for C (VNIR) = 0.97 and N (SWIR) = 0.97). The most important spectral region for C prediction identified using HSI reflectance was 400–550 nm with R<sup>2</sup> of 0.93 and RMSE of 0.17% in the calibration set and R<sup>2</sup> of 0.86, RMSE of 0.21% and ratio of performance to deviation (RPD) of 2.03 in the test set. The most important spectral regions for predicting N concentrations in the feed samples included 1451–1600 nm, 1901–2050 nm and 2051–2200 nm, providing prediction with R<sup>2</sup> ranging from 0.91 to 0.93, RMSE ranging from 0.06% to 0.07% in the calibration sets, R<sup>2</sup> from 0.96 to 0.99, RMSE of 0.06% and RPD from 3.47 to 3.92 in the test sets. The prediction accuracy of HSI and NIRS were comparable possibly due to the larger statistical population (larger number of pixels) that HSI provided, despite the fact that HSI had smaller spectral range compared with that of NIRS. In addition, HSI enabled visualising the variability of C and N in the samples. Therefore, HSI is advantageous compared to NIRS as it is a multifunctional tool that poses many potential applications in data collection and quality assurance within feed mills and poultry processing plants. The ability to more accurately measure and visualise the properties of feed ingredients has potential economic benefits and therefore additional investigation and development of HSI in this application is warranted.https://www.mdpi.com/2072-4292/13/6/1128feed ingredientshyperspectral imagingmachine learningNIR spectroscopynon-destructivequality monitoring |
| spellingShingle | Iman Tahmasbian Natalie K. Morgan Shahla Hosseini Bai Mark W. Dunlop Amy F. Moss Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat Remote Sensing feed ingredients hyperspectral imaging machine learning NIR spectroscopy non-destructive quality monitoring |
| title | Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat |
| title_full | Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat |
| title_fullStr | Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat |
| title_full_unstemmed | Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat |
| title_short | Comparison of Hyperspectral Imaging and Near-Infrared Spectroscopy to Determine Nitrogen and Carbon Concentrations in Wheat |
| title_sort | comparison of hyperspectral imaging and near infrared spectroscopy to determine nitrogen and carbon concentrations in wheat |
| topic | feed ingredients hyperspectral imaging machine learning NIR spectroscopy non-destructive quality monitoring |
| url | https://www.mdpi.com/2072-4292/13/6/1128 |
| work_keys_str_mv | AT imantahmasbian comparisonofhyperspectralimagingandnearinfraredspectroscopytodeterminenitrogenandcarbonconcentrationsinwheat AT nataliekmorgan comparisonofhyperspectralimagingandnearinfraredspectroscopytodeterminenitrogenandcarbonconcentrationsinwheat AT shahlahosseinibai comparisonofhyperspectralimagingandnearinfraredspectroscopytodeterminenitrogenandcarbonconcentrationsinwheat AT markwdunlop comparisonofhyperspectralimagingandnearinfraredspectroscopytodeterminenitrogenandcarbonconcentrationsinwheat AT amyfmoss comparisonofhyperspectralimagingandnearinfraredspectroscopytodeterminenitrogenandcarbonconcentrationsinwheat |