基于多叶位置高光谱信息的棉叶钾含量估算模型

IF 4.6 1区 农林科学 Q1 AGRICULTURE, MULTIDISCIPLINARY
Qiushuang Yao, Huihan Wang, Ze Zhang, Shizhe Qin, Lulu Ma, Xiangyu Chen, Hongyu Wang, Lu Wang, Xin Lv
{"title":"基于多叶位置高光谱信息的棉叶钾含量估算模型","authors":"Qiushuang Yao, Huihan Wang, Ze Zhang, Shizhe Qin, Lulu Ma, Xiangyu Chen, Hongyu Wang, Lu Wang, Xin Lv","doi":"10.1016/j.jia.2024.03.012","DOIUrl":null,"url":null,"abstract":"Potassium (K) is a highly mobile nutrient element that continuously adjusts its demand strategy among and within cotton leaves through redistribution. This indirectly leads to variations in the leaf potassium content (LKC, %) at different leaf positions. However, owing to the interaction between light and leaf age, leaf sensitivity at different positions to this change varies, including the reflection and absorption of the spectrum. How to selecting the optimal monitoring leaf position is an important factor in quickly and accurately evaluation of cotton LKC using spectral remote sensing technology. Therefore, this study proposes a comprehensive multileaf position estimation model based on the vertical distribution characteristics of LKC from top to bottom. This is aimed at achieving an accurate estimation of cotton LKC and optimizing the strategy for selecting the monitored leaf position. Between 2020 and 2021, we collected hyperspectral imaging data of the main stem leaves at different positions from top to bottom (Li, =1, 2, 3, …, ), during the cotton budding, flowering, and boll setting stages. Vertical distribution characteristics, sensitivity differences, and spectral correlations of LKC at different leaf positions were investigated. Additionally, the optimal range of the dominant leaf position for monitoring was determined. Partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), and the entropy weight method (EWM) were used to establish LKC estimation models for single leaf and multileaf positions. The results showed a vertical heterogeneous distribution of cotton LKC, with LKC initially increasing and then gradually decreasing from top to bottom, and the average LKC of cotton reaches its maximum value at flowering stage. The upper leaf position demonstrated greater sensitivity to K and exhibited a stronger correlation with the spectrum. The selected dominant leaf positions for the three growth stages were L1–L5, L1–L4, and L1–L2, respectively. Based on the dominant leaf position monitoring range, the optimal single leaf position models for estimating LKC during the three growth stages were PLSR-L4, PLSR-L1, and SVR-L2, with The coefficient of determination of the validation set (Rval) of 0.786, 0.580, and 0.768, and the root-mean-square error of the validation set (RMSEval) of 0.168, 0.197, and 0.191, respectively. The multileaf position LKC estimation model was constructed by EWM with Rval of 0.887, 0.728, and 0.703, and RMSEval of 0.134, 0.172, and 0.209, respectively. In contrast, the newly developed multileaf position comprehensive estimation model yielded superior results, improving the stability of the model on the basis of high accuracy, especially during the budding and flowering stages. These findings hold significant importance for investigating cotton LKC spectral models and selecting suitable leaf positions for field monitoring.","PeriodicalId":16305,"journal":{"name":"Journal of Integrative Agriculture","volume":"52 1","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Estimation model of potassium content in cotton leaves based on hyperspectral information of multileaf position\",\"authors\":\"Qiushuang Yao, Huihan Wang, Ze Zhang, Shizhe Qin, Lulu Ma, Xiangyu Chen, Hongyu Wang, Lu Wang, Xin Lv\",\"doi\":\"10.1016/j.jia.2024.03.012\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Potassium (K) is a highly mobile nutrient element that continuously adjusts its demand strategy among and within cotton leaves through redistribution. This indirectly leads to variations in the leaf potassium content (LKC, %) at different leaf positions. However, owing to the interaction between light and leaf age, leaf sensitivity at different positions to this change varies, including the reflection and absorption of the spectrum. How to selecting the optimal monitoring leaf position is an important factor in quickly and accurately evaluation of cotton LKC using spectral remote sensing technology. Therefore, this study proposes a comprehensive multileaf position estimation model based on the vertical distribution characteristics of LKC from top to bottom. This is aimed at achieving an accurate estimation of cotton LKC and optimizing the strategy for selecting the monitored leaf position. Between 2020 and 2021, we collected hyperspectral imaging data of the main stem leaves at different positions from top to bottom (Li, =1, 2, 3, …, ), during the cotton budding, flowering, and boll setting stages. Vertical distribution characteristics, sensitivity differences, and spectral correlations of LKC at different leaf positions were investigated. Additionally, the optimal range of the dominant leaf position for monitoring was determined. Partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), and the entropy weight method (EWM) were used to establish LKC estimation models for single leaf and multileaf positions. The results showed a vertical heterogeneous distribution of cotton LKC, with LKC initially increasing and then gradually decreasing from top to bottom, and the average LKC of cotton reaches its maximum value at flowering stage. The upper leaf position demonstrated greater sensitivity to K and exhibited a stronger correlation with the spectrum. The selected dominant leaf positions for the three growth stages were L1–L5, L1–L4, and L1–L2, respectively. Based on the dominant leaf position monitoring range, the optimal single leaf position models for estimating LKC during the three growth stages were PLSR-L4, PLSR-L1, and SVR-L2, with The coefficient of determination of the validation set (Rval) of 0.786, 0.580, and 0.768, and the root-mean-square error of the validation set (RMSEval) of 0.168, 0.197, and 0.191, respectively. The multileaf position LKC estimation model was constructed by EWM with Rval of 0.887, 0.728, and 0.703, and RMSEval of 0.134, 0.172, and 0.209, respectively. In contrast, the newly developed multileaf position comprehensive estimation model yielded superior results, improving the stability of the model on the basis of high accuracy, especially during the budding and flowering stages. These findings hold significant importance for investigating cotton LKC spectral models and selecting suitable leaf positions for field monitoring.\",\"PeriodicalId\":16305,\"journal\":{\"name\":\"Journal of Integrative Agriculture\",\"volume\":\"52 1\",\"pages\":\"\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-03-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Integrative Agriculture\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1016/j.jia.2024.03.012\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Integrative Agriculture","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1016/j.jia.2024.03.012","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

钾(K)是一种流动性很强的营养元素,它会通过再分配在棉花叶片之间和叶片内部不断调整其需求策略。这间接导致了不同叶片位置上叶片钾含量(LKC,%)的变化。然而,由于光照和叶龄之间的相互作用,不同位置的叶片对这种变化的敏感度不同,包括对光谱的反射和吸收。如何选择最佳监测叶片位置,是利用光谱遥感技术快速准确评估棉花 LKC 的重要因素。因此,本研究根据棉花叶绿素从上到下的垂直分布特征,提出了一种综合的多叶位置估算模型。旨在实现对棉花 LKC 的精确估算,优化监测叶片位置的选择策略。2020 年至 2021 年期间,我们采集了棉花蕾期、花期和结铃期主茎叶片从上到下不同位置(Li, =1, 2, 3, ..., )的高光谱成像数据。研究了不同叶片位置上 LKC 的垂直分布特征、灵敏度差异和光谱相关性。此外,还确定了监测主要叶片位置的最佳范围。利用偏最小二乘法回归(PLSR)、随机森林回归(RFR)、支持向量机回归(SVR)和熵权法(EWM)建立了单叶和多叶位置的 LKC 估算模型。结果表明,棉花 LKC 呈垂直异质性分布,LKC 从上到下先增加后逐渐减少,棉花平均 LKC 在开花期达到最大值。上部叶片位置对 K 的敏感性更高,与光谱的相关性也更强。三个生长阶段选定的优势叶片位置分别为 L1-L5、L1-L4 和 L1-L2。根据优势叶片位置监测范围,估计三个生长阶段 LKC 的最佳单叶位置模型为 PLSR-L4、PLSR-L1 和 SVR-L2,验证集决定系数(Rval)分别为 0.786、0.580 和 0.768,验证集均方根误差(RMSEval)分别为 0.168、0.197 和 0.191。用 EWM 建立的多叶位置 LKC 估计模型的 Rval 分别为 0.887、0.728 和 0.703,RMSEval 分别为 0.134、0.172 和 0.209。相比之下,新开发的多叶位置综合估计模型结果更优,在高精度的基础上提高了模型的稳定性,尤其是在萌芽期和开花期。这些发现对研究棉花 LKC 光谱模型和选择合适的叶片位置进行田间监测具有重要意义。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Estimation model of potassium content in cotton leaves based on hyperspectral information of multileaf position
Potassium (K) is a highly mobile nutrient element that continuously adjusts its demand strategy among and within cotton leaves through redistribution. This indirectly leads to variations in the leaf potassium content (LKC, %) at different leaf positions. However, owing to the interaction between light and leaf age, leaf sensitivity at different positions to this change varies, including the reflection and absorption of the spectrum. How to selecting the optimal monitoring leaf position is an important factor in quickly and accurately evaluation of cotton LKC using spectral remote sensing technology. Therefore, this study proposes a comprehensive multileaf position estimation model based on the vertical distribution characteristics of LKC from top to bottom. This is aimed at achieving an accurate estimation of cotton LKC and optimizing the strategy for selecting the monitored leaf position. Between 2020 and 2021, we collected hyperspectral imaging data of the main stem leaves at different positions from top to bottom (Li, =1, 2, 3, …, ), during the cotton budding, flowering, and boll setting stages. Vertical distribution characteristics, sensitivity differences, and spectral correlations of LKC at different leaf positions were investigated. Additionally, the optimal range of the dominant leaf position for monitoring was determined. Partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), and the entropy weight method (EWM) were used to establish LKC estimation models for single leaf and multileaf positions. The results showed a vertical heterogeneous distribution of cotton LKC, with LKC initially increasing and then gradually decreasing from top to bottom, and the average LKC of cotton reaches its maximum value at flowering stage. The upper leaf position demonstrated greater sensitivity to K and exhibited a stronger correlation with the spectrum. The selected dominant leaf positions for the three growth stages were L1–L5, L1–L4, and L1–L2, respectively. Based on the dominant leaf position monitoring range, the optimal single leaf position models for estimating LKC during the three growth stages were PLSR-L4, PLSR-L1, and SVR-L2, with The coefficient of determination of the validation set (Rval) of 0.786, 0.580, and 0.768, and the root-mean-square error of the validation set (RMSEval) of 0.168, 0.197, and 0.191, respectively. The multileaf position LKC estimation model was constructed by EWM with Rval of 0.887, 0.728, and 0.703, and RMSEval of 0.134, 0.172, and 0.209, respectively. In contrast, the newly developed multileaf position comprehensive estimation model yielded superior results, improving the stability of the model on the basis of high accuracy, especially during the budding and flowering stages. These findings hold significant importance for investigating cotton LKC spectral models and selecting suitable leaf positions for field monitoring.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Integrative Agriculture
Journal of Integrative Agriculture AGRICULTURE, MULTIDISCIPLINARY-
CiteScore
7.90
自引率
4.20%
发文量
4817
审稿时长
3-6 weeks
期刊介绍: Journal of Integrative Agriculture publishes manuscripts in the categories of Commentary, Review, Research Article, Letter and Short Communication, focusing on the core subjects: Crop Genetics & Breeding, Germplasm Resources, Physiology, Biochemistry, Cultivation, Tillage, Plant Protection, Animal Science, Veterinary Science, Soil and Fertilization, Irrigation, Plant Nutrition, Agro-Environment & Ecology, Bio-material and Bio-energy, Food Science, Agricultural Economics and Management, Agricultural Information Science.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信