• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于特征选择的青贮玉米植株氮含量遥感反演

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

作者信息

Cheng Kejing, Yan Jixuan, Li Guang, Ma Weiwei, Guo Zichen, Wang Wenning, Li Haolin, Da Qihong, Li Xuchun, Yao Yadong

机构信息

College of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou, China.

State Key Laboratory of Crop Science in Arid Habitat Co-constructed by Province and Ministry, Gansu Agricultural University, Lanzhou, China.

出版信息

Front Plant Sci. 2025 Mar 6;16:1554842. doi: 10.3389/fpls.2025.1554842. eCollection 2025.

DOI:10.3389/fpls.2025.1554842
PMID:40115941
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11922896/
Abstract

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.

摘要

过量施氮和低氮利用效率一直是中国农业发展中的主要问题,给田间管理带来了重大挑战。氮是作物生长的关键养分,在作物发育、产量形成和品质提升中发挥着不可或缺的作用。因此,精确控制施氮量可以减少过量施肥造成的环境污染,提高氮利用效率。本研究利用多光谱遥感影像,结合田间实测氮含量,采用反向传播神经网络(BP)、支持向量机(SVM)和偏最小二乘回归(PLSR)三种算法建立玉米冠层氮含量反演模型。结果表明,各种光谱指数所包含的信息存在一定程度的冗余。特征选择有效地消除了相关和冗余的光谱信息,从而提高了建模效率。光谱指数绿度指数(GI)和氮素反射率指数(NRI)与玉米冠层氮含量表现出很强的相关性,表明绿色和红色光谱带对于反演玉米的生物物理和生化参数至关重要。在玉米冠层氮含量反演研究中,随机森林(RF)算法与PLSR相结合表现出优异的预测性能。与单独的PLSR模型相比,精度提高了3.5%-6.5%,为玉米种植中的精确氮诊断和肥料管理提供了科学依据和技术支持。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/dc70d38889fa/fpls-16-1554842-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/6dc274342ae2/fpls-16-1554842-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/9b4e98c1f7d5/fpls-16-1554842-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/09d859308fd5/fpls-16-1554842-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/9125c0e7631f/fpls-16-1554842-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/6780f5dc8761/fpls-16-1554842-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/aa7ff762a96f/fpls-16-1554842-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/636f6c53c52d/fpls-16-1554842-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/dc70d38889fa/fpls-16-1554842-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/6dc274342ae2/fpls-16-1554842-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/9b4e98c1f7d5/fpls-16-1554842-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/09d859308fd5/fpls-16-1554842-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/9125c0e7631f/fpls-16-1554842-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/6780f5dc8761/fpls-16-1554842-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/aa7ff762a96f/fpls-16-1554842-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/636f6c53c52d/fpls-16-1554842-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/aec1/11922896/dc70d38889fa/fpls-16-1554842-g008.jpg

相似文献

1
Remote sensing inversion of nitrogen content in silage maize plants based on feature selection.基于特征选择的青贮玉米植株氮含量遥感反演
Front Plant Sci. 2025 Mar 6;16:1554842. doi: 10.3389/fpls.2025.1554842. eCollection 2025.
2
Inversion of Nitrogen Concentration in Apple Canopy Based on UAV Hyperspectral Images.基于无人机高光谱图像的苹果冠层氮浓度反演。
Sensors (Basel). 2022 May 4;22(9):3503. doi: 10.3390/s22093503.
3
Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms.基于敏感变量选择和机器学习算法的苜蓿农田土壤盐渍化反演模型。
PeerJ. 2024 Sep 26;12:e18186. doi: 10.7717/peerj.18186. eCollection 2024.
4
Non-destructive monitoring of maize LAI by fusing UAV spectral and textural features.通过融合无人机光谱和纹理特征对玉米叶面积指数进行无损监测。
Front Plant Sci. 2023 Mar 31;14:1158837. doi: 10.3389/fpls.2023.1158837. eCollection 2023.
5
Estimating Summer Maize Biomass by Integrating UAV Multispectral Imagery with Crop Physiological Parameters.结合无人机多光谱影像与作物生理参数估算夏玉米生物量
Plants (Basel). 2024 Oct 31;13(21):3070. doi: 10.3390/plants13213070.
6
Using UAV image data to monitor the effects of different nitrogen application rates on tea quality.利用无人机图像数据监测不同施氮量对茶叶品质的影响。
J Sci Food Agric. 2022 Mar 15;102(4):1540-1549. doi: 10.1002/jsfa.11489. Epub 2021 Sep 9.
7
Utilizing Spectral, Structural and Textural Features for Estimating Oat Above-Ground Biomass Using UAV-Based Multispectral Data and Machine Learning.利用基于无人机的多光谱数据和机器学习的光谱、结构和纹理特征估算燕麦地上生物量。
Sensors (Basel). 2023 Dec 8;23(24):9708. doi: 10.3390/s23249708.
8
Precision Estimation of Rice Nitrogen Fertilizer Topdressing According to the Nitrogen Nutrition Index Using UAV Multi-Spectral Remote Sensing: A Case Study in Southwest China.基于无人机多光谱遥感的水稻氮营养指数精准估算氮肥追肥研究:以中国西南地区为例
Plants (Basel). 2025 Apr 11;14(8):1195. doi: 10.3390/plants14081195.
9
Retrieval of Crop Variables from Proximal Multispectral UAV Image Data Using PROSAIL in Maize Canopy.利用PROSAIL从玉米冠层近端多光谱无人机图像数据中反演作物变量
Remote Sens (Basel). 2022 Mar 3;14(5):1247. doi: 10.3390/rs14051247.
10
UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping.UAV 多源数据融合与多任务深度学习在高通量玉米表型分析中的应用。
Sensors (Basel). 2023 Feb 6;23(4):1827. doi: 10.3390/s23041827.

本文引用的文献

1
Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms.基于敏感变量选择和机器学习算法的苜蓿农田土壤盐渍化反演模型。
PeerJ. 2024 Sep 26;12:e18186. doi: 10.7717/peerj.18186. eCollection 2024.
2
Determination of leaf nitrogen content in apple and jujube by near-infrared spectroscopy.近红外光谱法测定苹果和枣树叶中的氮含量。
Sci Rep. 2024 Sep 6;14(1):20884. doi: 10.1038/s41598-024-71590-1.
3
Comparing CNNs and PLSr for estimating wheat organs biophysical variables using proximal sensing.
比较卷积神经网络(CNNs)和偏最小二乘回归(PLSr)在利用近地遥感估算小麦器官生物物理变量方面的表现。
Front Plant Sci. 2023 Nov 20;14:1204791. doi: 10.3389/fpls.2023.1204791. eCollection 2023.
4
An evolutionary deep learning soft sensor model based on random forest feature selection technique for penicillin fermentation process.基于随机森林特征选择技术的青霉素发酵过程进化深度学习软测量模型。
ISA Trans. 2023 May;136:139-151. doi: 10.1016/j.isatra.2022.10.044. Epub 2022 Nov 2.
5
Evaluation of Random Forests (RF) for Regional and Local-Scale Wheat Yield Prediction in Southeast Australia.评估随机森林(RF)在澳大利亚东南部地区和局地尺度的小麦产量预测中的应用。
Sensors (Basel). 2022 Jan 18;22(3):717. doi: 10.3390/s22030717.
6
High-throughput field phenotyping using hyperspectral reflectance and partial least squares regression (PLSR) reveals genetic modifications to photosynthetic capacity.利用高光谱反射率和偏最小二乘回归(PLSR)进行高通量田间表型分析揭示了光合能力的遗传修饰。
Remote Sens Environ. 2019 Sep 15;231:111176. doi: 10.1016/j.rse.2019.04.029.