Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging
Hyperspectral imaging is an emerging non-invasive technology with potential for early nutrient stress detection in plants prior to visible symptoms. This study evaluated hyperspectral imaging for early identification of nitrogen, phosphorus, and potassium (NPK) deficiencies across three greenhouse-g...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/1/187 |
| _version_ | 1797358179900719104 |
|---|---|
| author | Alireza Sanaeifar Ce Yang An Min Colin R. Jones Thomas E. Michaels Quinton J. Krueger Robert Barnes Toby J. Velte |
| author_facet | Alireza Sanaeifar Ce Yang An Min Colin R. Jones Thomas E. Michaels Quinton J. Krueger Robert Barnes Toby J. Velte |
| author_sort | Alireza Sanaeifar |
| collection | DOAJ |
| description | Hyperspectral imaging is an emerging non-invasive technology with potential for early nutrient stress detection in plants prior to visible symptoms. This study evaluated hyperspectral imaging for early identification of nitrogen, phosphorus, and potassium (NPK) deficiencies across three greenhouse-grown industrial hemp plant cultivars (<i>Cannabis sativa</i> L.). Visible and near-infrared spectral data (380–1022 nm) were acquired from hemp samples subjected to controlled NPK stresses at multiple developmental timepoints using a benchtop hyperspectral camera. Robust principal component analysis was developed for effective screening of spectral outliers. Partial least squares discriminant analysis (PLS-DA) and support vector machines (SVM) were developed and optimized to classify nutrient deficiencies using key wavelengths selected by variable importance in projection (VIP) and interval partial least squares (iPLS). The 16-wavelength iPLS-C-SVM model achieved the highest precision of 0.75 to 1 on the test dataset. Key wavelengths for effective nutrient deficiency detection spanned the visible range, underscoring the hyperspectral imaging sensitivity to early changes in leaf pigment levels prior to any visible symptom development. The emergence of wavelengths related to chlorophyll, carotenoid, and anthocyanin absorption as optimal for classification, highlights the technology’s capacity to detect subtle impending biochemical perturbations linked to emerging deficiencies. Identifying stress at this pre-visual stage could provide hemp producers with timely corrective action to mitigate losses in crop quality and yields. |
| first_indexed | 2024-03-08T14:58:10Z |
| format | Article |
| id | doaj.art-30c8a590b4dc47d7b761dcaeff2aebd6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T14:58:10Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-30c8a590b4dc47d7b761dcaeff2aebd62024-01-10T15:07:53ZengMDPI AGRemote Sensing2072-42922024-01-0116118710.3390/rs16010187Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral ImagingAlireza Sanaeifar0Ce Yang1An Min2Colin R. Jones3Thomas E. Michaels4Quinton J. Krueger5Robert Barnes6Toby J. Velte7Department of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USADepartment of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USADepartment of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USADepartment of Horticultural Science, University of Minnesota, 1970 Folwell Ave, Saint Paul, MN 55108, USADepartment of Horticultural Science, University of Minnesota, 1970 Folwell Ave, Saint Paul, MN 55108, USAVerilytix Inc., 2975 Klondike Avenue N, Lake Elmo, MN 55042, USAVerilytix Inc., 2975 Klondike Avenue N, Lake Elmo, MN 55042, USAVerilytix Inc., 2975 Klondike Avenue N, Lake Elmo, MN 55042, USAHyperspectral imaging is an emerging non-invasive technology with potential for early nutrient stress detection in plants prior to visible symptoms. This study evaluated hyperspectral imaging for early identification of nitrogen, phosphorus, and potassium (NPK) deficiencies across three greenhouse-grown industrial hemp plant cultivars (<i>Cannabis sativa</i> L.). Visible and near-infrared spectral data (380–1022 nm) were acquired from hemp samples subjected to controlled NPK stresses at multiple developmental timepoints using a benchtop hyperspectral camera. Robust principal component analysis was developed for effective screening of spectral outliers. Partial least squares discriminant analysis (PLS-DA) and support vector machines (SVM) were developed and optimized to classify nutrient deficiencies using key wavelengths selected by variable importance in projection (VIP) and interval partial least squares (iPLS). The 16-wavelength iPLS-C-SVM model achieved the highest precision of 0.75 to 1 on the test dataset. Key wavelengths for effective nutrient deficiency detection spanned the visible range, underscoring the hyperspectral imaging sensitivity to early changes in leaf pigment levels prior to any visible symptom development. The emergence of wavelengths related to chlorophyll, carotenoid, and anthocyanin absorption as optimal for classification, highlights the technology’s capacity to detect subtle impending biochemical perturbations linked to emerging deficiencies. Identifying stress at this pre-visual stage could provide hemp producers with timely corrective action to mitigate losses in crop quality and yields.https://www.mdpi.com/2072-4292/16/1/187chemometricshyperspectral imagingindustrial hempnutrient deficienciespre-visual detectionvariable selection |
| spellingShingle | Alireza Sanaeifar Ce Yang An Min Colin R. Jones Thomas E. Michaels Quinton J. Krueger Robert Barnes Toby J. Velte Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging Remote Sensing chemometrics hyperspectral imaging industrial hemp nutrient deficiencies pre-visual detection variable selection |
| title | Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging |
| title_full | Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging |
| title_fullStr | Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging |
| title_full_unstemmed | Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging |
| title_short | Noninvasive Early Detection of Nutrient Deficiencies in Greenhouse-Grown Industrial Hemp Using Hyperspectral Imaging |
| title_sort | noninvasive early detection of nutrient deficiencies in greenhouse grown industrial hemp using hyperspectral imaging |
| topic | chemometrics hyperspectral imaging industrial hemp nutrient deficiencies pre-visual detection variable selection |
| url | https://www.mdpi.com/2072-4292/16/1/187 |
| work_keys_str_mv | AT alirezasanaeifar noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT ceyang noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT anmin noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT colinrjones noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT thomasemichaels noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT quintonjkrueger noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT robertbarnes noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging AT tobyjvelte noninvasiveearlydetectionofnutrientdeficienciesingreenhousegrownindustrialhempusinghyperspectralimaging |