Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models
Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amoun...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/4/641 |
id |
doaj-f9bda53d225f41678dd8485540a21d76 |
---|---|
record_format |
Article |
spelling |
doaj-f9bda53d225f41678dd8485540a21d762021-02-11T00:05:10ZengMDPI AGRemote Sensing2072-42922021-02-011364164110.3390/rs13040641Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning ModelsGopal Ramdas Mahajan0Bappa Das1Dayesh Murgaokar2Ittai Herrmann3Katja Berger4Rabi N. Sahoo5Kiran Patel6Ashwini Desai7Shaiesh Morajkar8Rahul M. Kulkarni9Natural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaNatural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaNatural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaThe Plant Sensing Laboratory, The Robert H. Smith Institute for Plant Sciences and Genetics in Agriculture, The Robert H. Smith Faculty of Agriculture, Food and Environment, The Hebrew University of Jerusalem, P.O. Box 12, Rehovot 7610001, IsraelDepartment of Geography & Remote Sensing Ludwig-Maximilians-Universität München, 80333 Munich, GermanyDivision of Agricultural Physics, ICAR–Indian Agricultural Research Institute, New Delhi 110012, IndiaNatural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaNatural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaNatural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaNatural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, IndiaConventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R<sup>2</sup> ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R<sup>2</sup> ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R<sup>2</sup> ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.https://www.mdpi.com/2072-4292/13/4/641chemometricshyperspectral remote sensingmultivariate modelingprecision nutrient managementVNIR spectroscopy |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Gopal Ramdas Mahajan Bappa Das Dayesh Murgaokar Ittai Herrmann Katja Berger Rabi N. Sahoo Kiran Patel Ashwini Desai Shaiesh Morajkar Rahul M. Kulkarni |
spellingShingle |
Gopal Ramdas Mahajan Bappa Das Dayesh Murgaokar Ittai Herrmann Katja Berger Rabi N. Sahoo Kiran Patel Ashwini Desai Shaiesh Morajkar Rahul M. Kulkarni Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models Remote Sensing chemometrics hyperspectral remote sensing multivariate modeling precision nutrient management VNIR spectroscopy |
author_facet |
Gopal Ramdas Mahajan Bappa Das Dayesh Murgaokar Ittai Herrmann Katja Berger Rabi N. Sahoo Kiran Patel Ashwini Desai Shaiesh Morajkar Rahul M. Kulkarni |
author_sort |
Gopal Ramdas Mahajan |
title |
Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models |
title_short |
Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models |
title_full |
Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models |
title_fullStr |
Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models |
title_full_unstemmed |
Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models |
title_sort |
monitoring the foliar nutrients status of mango using spectroscopy-based spectral indices and plsr-combined machine learning models |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-02-01 |
description |
Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R<sup>2</sup> ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R<sup>2</sup> ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R<sup>2</sup> ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients. |
topic |
chemometrics hyperspectral remote sensing multivariate modeling precision nutrient management VNIR spectroscopy |
url |
https://www.mdpi.com/2072-4292/13/4/641 |
work_keys_str_mv |
AT gopalramdasmahajan monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT bappadas monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT dayeshmurgaokar monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT ittaiherrmann monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT katjaberger monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT rabinsahoo monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT kiranpatel monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT ashwinidesai monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT shaieshmorajkar monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels AT rahulmkulkarni monitoringthefoliarnutrientsstatusofmangousingspectroscopybasedspectralindicesandplsrcombinedmachinelearningmodels |
_version_ |
1724274795589140480 |