Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP

Abstract Leaf chlorophyll content (LCC) is a key indicator for assessing the growth of grapes. Hyperspectral techniques have been applied to LCC research. However, quantitative prediction of grape LCC using this technique remains challenging due to baseline drift, spectral peak overlap, and ambiguit...

Full description

Saved in:
Bibliographic Details
Main Authors: YaFeng Li, XinGang Xu, WenBiao Wu, Yaohui Zhu, LuTao Gao, XiangTai Jiang, Yang Meng, GuiJun Yang, HanYu Xue
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-84977-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850029852473688064
author YaFeng Li
XinGang Xu
WenBiao Wu
Yaohui Zhu
LuTao Gao
XiangTai Jiang
Yang Meng
GuiJun Yang
HanYu Xue
author_facet YaFeng Li
XinGang Xu
WenBiao Wu
Yaohui Zhu
LuTao Gao
XiangTai Jiang
Yang Meng
GuiJun Yang
HanYu Xue
author_sort YaFeng Li
collection DOAJ
description Abstract Leaf chlorophyll content (LCC) is a key indicator for assessing the growth of grapes. Hyperspectral techniques have been applied to LCC research. However, quantitative prediction of grape LCC using this technique remains challenging due to baseline drift, spectral peak overlap, and ambiguity in the sensitive spectral range. To address these issues, two typical crop leaf hyperspectral data were collected to reveal the spectral response characteristics of grape LCC using standardization by variables (SNV) and multiple far scattering correction (MSC) preprocessing variations. The sensitive spectral range is determined by Pearson’s algorithm, and sensitive features are further extracted within that range using Extreme Gradient Boosting (XGBoost), Recursive Feature Elimination (RFE), and Principal components analysis (PCA). Comparison of the prediction ability of Random Forest Regression (RFR) algorithm, Support Vector Machine Regression (SVR) model, and Genetic Algorithm-Based Neural Network (GA-BP) on grape LCC based on sensitive features. A SNV-RFE-GA-BP framework for predicting hyperspectral LCC in grapes is proposed, where $$\:{R}^{2}$$ =0.835 and NRMSE = 0.091. The analysis results show that SNV and MSC treatments improve the correlation between spectral reflectance and LCC, and different feature screening methods have a greater impact on the model prediction accuracy. It was shown that SNV-based processed hyperspectral data combined with GA-BP has great potential for efficient chlorophyll monitoring in grapevine. This method provides a new framework theory for constructing a hyperspectral analytical model of grapevine key growth indicators.
format Article
id doaj-art-262620650e3f4edea502b3da5de2b27b
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-262620650e3f4edea502b3da5de2b27b2025-08-20T02:59:24ZengNature PortfolioScientific Reports2045-23222025-03-0115111310.1038/s41598-024-84977-xHyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BPYaFeng Li0XinGang Xu1WenBiao Wu2Yaohui Zhu3LuTao Gao4XiangTai Jiang5Yang Meng6GuiJun Yang7HanYu Xue8Key Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesKey Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesKey Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesSchool of Agricultural Engineering, Jiangsu UniversityCollege of Big Data, Yunnan Agricultural UniversityKey Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesKey Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesKey Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesKey Laboratory of Quantitative Remote Sensing in Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agricultural and Forestry SciencesAbstract Leaf chlorophyll content (LCC) is a key indicator for assessing the growth of grapes. Hyperspectral techniques have been applied to LCC research. However, quantitative prediction of grape LCC using this technique remains challenging due to baseline drift, spectral peak overlap, and ambiguity in the sensitive spectral range. To address these issues, two typical crop leaf hyperspectral data were collected to reveal the spectral response characteristics of grape LCC using standardization by variables (SNV) and multiple far scattering correction (MSC) preprocessing variations. The sensitive spectral range is determined by Pearson’s algorithm, and sensitive features are further extracted within that range using Extreme Gradient Boosting (XGBoost), Recursive Feature Elimination (RFE), and Principal components analysis (PCA). Comparison of the prediction ability of Random Forest Regression (RFR) algorithm, Support Vector Machine Regression (SVR) model, and Genetic Algorithm-Based Neural Network (GA-BP) on grape LCC based on sensitive features. A SNV-RFE-GA-BP framework for predicting hyperspectral LCC in grapes is proposed, where $$\:{R}^{2}$$ =0.835 and NRMSE = 0.091. The analysis results show that SNV and MSC treatments improve the correlation between spectral reflectance and LCC, and different feature screening methods have a greater impact on the model prediction accuracy. It was shown that SNV-based processed hyperspectral data combined with GA-BP has great potential for efficient chlorophyll monitoring in grapevine. This method provides a new framework theory for constructing a hyperspectral analytical model of grapevine key growth indicators.https://doi.org/10.1038/s41598-024-84977-xData preprocessingFeature selectionMachine learningHyperspectral monitoring.
spellingShingle YaFeng Li
XinGang Xu
WenBiao Wu
Yaohui Zhu
LuTao Gao
XiangTai Jiang
Yang Meng
GuiJun Yang
HanYu Xue
Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP
Scientific Reports
Data preprocessing
Feature selection
Machine learning
Hyperspectral monitoring.
title Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP
title_full Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP
title_fullStr Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP
title_full_unstemmed Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP
title_short Hyperspectral estimation of chlorophyll content in grapevine based on feature selection and GA-BP
title_sort hyperspectral estimation of chlorophyll content in grapevine based on feature selection and ga bp
topic Data preprocessing
Feature selection
Machine learning
Hyperspectral monitoring.
url https://doi.org/10.1038/s41598-024-84977-x
work_keys_str_mv AT yafengli hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT xingangxu hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT wenbiaowu hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT yaohuizhu hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT lutaogao hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT xiangtaijiang hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT yangmeng hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT guijunyang hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp
AT hanyuxue hyperspectralestimationofchlorophyllcontentingrapevinebasedonfeatureselectionandgabp