Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models

Remote sensing estimation of crop nitrogen content allows real-time monitoring of growth to develop scientific methods. However, most of the current remote sensing estimates of crop nitrogen contents have limitations in accurately reflecting the vertical distribution of nutrients in plants. Firstly,...

Full description

Bibliographic Details
Main Authors: Chunyan Ma, Liting Zhai, Changchun Li, Yilin Wang
Format: Article
Language:English
Published: MDPI AG 2022-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/12/15/7427
_version_ 1797414737166729216
author Chunyan Ma
Liting Zhai
Changchun Li
Yilin Wang
author_facet Chunyan Ma
Liting Zhai
Changchun Li
Yilin Wang
author_sort Chunyan Ma
collection DOAJ
description Remote sensing estimation of crop nitrogen content allows real-time monitoring of growth to develop scientific methods. However, most of the current remote sensing estimates of crop nitrogen contents have limitations in accurately reflecting the vertical distribution of nutrients in plants. Firstly, the original hyperspectrum is first-order differential (FD), second-order differential (SD), and continuous removal (CR), and the corresponding sensitive bands were screened by correlation analysis in this paper. Then, the spectral reflectance, vegetation indices, and wavelet coefficients were used as input features to construct models for estimating nitrogen content of flag leaf, upper 1 leaf, upper 2 leaf, upper 3 leaf, and upper 4 leaf based on partial least squares regression (PLSR), support vector machine (SVM), random forest (RF), and multiple linear regression (MLR), respectively. The results showed that the accuracy of nitrogen content prediction based on wavelet coefficients was the highest. The combination of MLR and SVM with wavelet coefficients had high accuracy and robustness in the prediction of nitrogen content at different leaf positions. Additionally, the prediction accuracy of nitrogen gradually increased as the leaf position of winter wheat increased. The study can provide technical support for remote sensing estimation of nutrient elements at vertical leaf position of crops. The study can provide a reference for prediction of other crops.
first_indexed 2024-03-09T05:37:53Z
format Article
id doaj.art-9d83493c79cc438ab903b0babd7a86e9
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-09T05:37:53Z
publishDate 2022-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-9d83493c79cc438ab903b0babd7a86e92023-12-03T12:27:08ZengMDPI AGApplied Sciences2076-34172022-07-011215742710.3390/app12157427Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning ModelsChunyan Ma0Liting Zhai1Changchun Li2Yilin Wang3School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaRemote sensing estimation of crop nitrogen content allows real-time monitoring of growth to develop scientific methods. However, most of the current remote sensing estimates of crop nitrogen contents have limitations in accurately reflecting the vertical distribution of nutrients in plants. Firstly, the original hyperspectrum is first-order differential (FD), second-order differential (SD), and continuous removal (CR), and the corresponding sensitive bands were screened by correlation analysis in this paper. Then, the spectral reflectance, vegetation indices, and wavelet coefficients were used as input features to construct models for estimating nitrogen content of flag leaf, upper 1 leaf, upper 2 leaf, upper 3 leaf, and upper 4 leaf based on partial least squares regression (PLSR), support vector machine (SVM), random forest (RF), and multiple linear regression (MLR), respectively. The results showed that the accuracy of nitrogen content prediction based on wavelet coefficients was the highest. The combination of MLR and SVM with wavelet coefficients had high accuracy and robustness in the prediction of nitrogen content at different leaf positions. Additionally, the prediction accuracy of nitrogen gradually increased as the leaf position of winter wheat increased. The study can provide technical support for remote sensing estimation of nutrient elements at vertical leaf position of crops. The study can provide a reference for prediction of other crops.https://www.mdpi.com/2076-3417/12/15/7427hyperspectral remote sensingmachine learningnitrogenwheat
spellingShingle Chunyan Ma
Liting Zhai
Changchun Li
Yilin Wang
Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models
Applied Sciences
hyperspectral remote sensing
machine learning
nitrogen
wheat
title Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models
title_full Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models
title_fullStr Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models
title_full_unstemmed Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models
title_short Hyperspectral Estimation of Nitrogen Content in Different Leaf Positions of Wheat Using Machine Learning Models
title_sort hyperspectral estimation of nitrogen content in different leaf positions of wheat using machine learning models
topic hyperspectral remote sensing
machine learning
nitrogen
wheat
url https://www.mdpi.com/2076-3417/12/15/7427
work_keys_str_mv AT chunyanma hyperspectralestimationofnitrogencontentindifferentleafpositionsofwheatusingmachinelearningmodels
AT litingzhai hyperspectralestimationofnitrogencontentindifferentleafpositionsofwheatusingmachinelearningmodels
AT changchunli hyperspectralestimationofnitrogencontentindifferentleafpositionsofwheatusingmachinelearningmodels
AT yilinwang hyperspectralestimationofnitrogencontentindifferentleafpositionsofwheatusingmachinelearningmodels