Remote sensing inversion of nitrogen content in silage maize plants based on feature selection

Excessive nitrogen application and low nitrogen use efficiency have been major issues in China’s agricultural development, posing significant challenges for field management. Nitrogen is a critical nutrient for crop growth, playing an indispensable role in crop development, yield formation, and qual...

Full description

Saved in:
Bibliographic Details
Main Authors: Kejing Cheng, Jixuan Yan, Guang Li, Weiwei Ma, Zichen Guo, Wenning Wang, Haolin Li, Qihong Da, Xuchun Li, Yadong Yao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1554842/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706007537647616
author Kejing Cheng
Kejing Cheng
Jixuan Yan
Jixuan Yan
Guang Li
Guang Li
Weiwei Ma
Weiwei Ma
Zichen Guo
Zichen Guo
Wenning Wang
Wenning Wang
Haolin Li
Qihong Da
Qihong Da
Xuchun Li
Xuchun Li
Yadong Yao
Yadong Yao
author_facet Kejing Cheng
Kejing Cheng
Jixuan Yan
Jixuan Yan
Guang Li
Guang Li
Weiwei Ma
Weiwei Ma
Zichen Guo
Zichen Guo
Wenning Wang
Wenning Wang
Haolin Li
Qihong Da
Qihong Da
Xuchun Li
Xuchun Li
Yadong Yao
Yadong Yao
author_sort Kejing Cheng
collection DOAJ
description Excessive nitrogen application and low nitrogen use efficiency have been major issues in China’s agricultural development, posing significant challenges for field management. Nitrogen is a critical nutrient for crop growth, playing an indispensable role in crop development, yield formation, and quality enhancement. Therefore, precisely controlling nitrogen application rates can reduce environmental pollution caused by excessive fertilization and improve nitrogen use efficiency. This study employs multispectral remote sensing images, combined with field-measured nitrogen content, to develop canopy nitrogen content inversion models for maize using three algorithms: backpropagation neural network (BP), support vector machine (SVM), and partial least squares regression (PLSR). The results reveal that there is a degree of redundancy in the information contained in various spectral indices. Feature selection effectively eliminates correlated and redundant spectral information, thereby improving modeling efficiency. The spectral indices Green Index (GI) and Nitrogen Reflectance Index (NRI) exhibit strong correlations with nitrogen content in the maize canopy, suggesting that the green and red spectral bands are crucial for retrieving maize’s biophysical and biochemical parameters. In studies on nitrogen content inversion in the maize canopy, the random forest (RF) algorithm, coupled with PLSR, demonstrated superior predictive performance. Compared to the standalone PLSR model, accuracy improved by 3.5%–6.5%, providing a scientific foundation and technical support for precise nitrogen diagnosis and fertilizer management in maize cultivation.
format Article
id doaj-art-de30fc3f0a964ee6a02b5e114f5599e3
institution DOAJ
issn 1664-462X
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-de30fc3f0a964ee6a02b5e114f5599e32025-08-20T03:16:19ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-03-011610.3389/fpls.2025.15548421554842Remote sensing inversion of nitrogen content in silage maize plants based on feature selectionKejing Cheng0Kejing Cheng1Jixuan Yan2Jixuan Yan3Guang Li4Guang Li5Weiwei Ma6Weiwei Ma7Zichen Guo8Zichen Guo9Wenning Wang10Wenning Wang11Haolin Li12Qihong Da13Qihong Da14Xuchun Li15Xuchun Li16Yadong Yao17Yadong Yao18College of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Forestry, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Forestry, Gansu Agricultural University, Lanzhou, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Environmental Science and Engineering, Beijing University of Technology, Beijing, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, ChinaState Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, ChinaExcessive nitrogen application and low nitrogen use efficiency have been major issues in China’s agricultural development, posing significant challenges for field management. Nitrogen is a critical nutrient for crop growth, playing an indispensable role in crop development, yield formation, and quality enhancement. Therefore, precisely controlling nitrogen application rates can reduce environmental pollution caused by excessive fertilization and improve nitrogen use efficiency. This study employs multispectral remote sensing images, combined with field-measured nitrogen content, to develop canopy nitrogen content inversion models for maize using three algorithms: backpropagation neural network (BP), support vector machine (SVM), and partial least squares regression (PLSR). The results reveal that there is a degree of redundancy in the information contained in various spectral indices. Feature selection effectively eliminates correlated and redundant spectral information, thereby improving modeling efficiency. The spectral indices Green Index (GI) and Nitrogen Reflectance Index (NRI) exhibit strong correlations with nitrogen content in the maize canopy, suggesting that the green and red spectral bands are crucial for retrieving maize’s biophysical and biochemical parameters. In studies on nitrogen content inversion in the maize canopy, the random forest (RF) algorithm, coupled with PLSR, demonstrated superior predictive performance. Compared to the standalone PLSR model, accuracy improved by 3.5%–6.5%, providing a scientific foundation and technical support for precise nitrogen diagnosis and fertilizer management in maize cultivation.https://www.frontiersin.org/articles/10.3389/fpls.2025.1554842/fullvegetation indicesmultispectralunmanned aerial vehicle (UAV)feature importance scoresmachine learning
spellingShingle Kejing Cheng
Kejing Cheng
Jixuan Yan
Jixuan Yan
Guang Li
Guang Li
Weiwei Ma
Weiwei Ma
Zichen Guo
Zichen Guo
Wenning Wang
Wenning Wang
Haolin Li
Qihong Da
Qihong Da
Xuchun Li
Xuchun Li
Yadong Yao
Yadong Yao
Remote sensing inversion of nitrogen content in silage maize plants based on feature selection
Frontiers in Plant Science
vegetation indices
multispectral
unmanned aerial vehicle (UAV)
feature importance scores
machine learning
title Remote sensing inversion of nitrogen content in silage maize plants based on feature selection
title_full Remote sensing inversion of nitrogen content in silage maize plants based on feature selection
title_fullStr Remote sensing inversion of nitrogen content in silage maize plants based on feature selection
title_full_unstemmed Remote sensing inversion of nitrogen content in silage maize plants based on feature selection
title_short Remote sensing inversion of nitrogen content in silage maize plants based on feature selection
title_sort remote sensing inversion of nitrogen content in silage maize plants based on feature selection
topic vegetation indices
multispectral
unmanned aerial vehicle (UAV)
feature importance scores
machine learning
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1554842/full
work_keys_str_mv AT kejingcheng remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT kejingcheng remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT jixuanyan remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT jixuanyan remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT guangli remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT guangli remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT weiweima remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT weiweima remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT zichenguo remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT zichenguo remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT wenningwang remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT wenningwang remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT haolinli remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT qihongda remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT qihongda remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT xuchunli remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT xuchunli remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT yadongyao remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection
AT yadongyao remotesensinginversionofnitrogencontentinsilagemaizeplantsbasedonfeatureselection