[1]宋子怡,常庆瑞,郑智康,等.基于高光谱和连续投影算法的猕猴桃叶片氮平衡指数的估测[J].江苏农业学报,2024,(07):1260-1267.[doi:doi:10.3969/j.issn.1000-4440.2024.07.012]
　SONG Ziyi,CHANG Qingrui,ZHENG Zhikang,et al.Estimation of kiwifruit leaf nitrogen balance index based on hyperspectral and successive projections algorithm[J].,2024,(07):1260-1267.[doi:doi:10.3969/j.issn.1000-4440.2024.07.012]
点击复制

基于高光谱和连续投影算法的猕猴桃叶片氮平衡指数的估测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年07期
页码:
1260-1267
栏目:
农业信息工程
出版日期:
2024-07-30

文章信息/Info

Title:
Estimation of kiwifruit leaf nitrogen balance index based on hyperspectral and successive projections algorithm
作者:
宋子怡; 常庆瑞; 郑智康; 唐国强; 孟怡凡
(西北农林科技大学资源环境学院,陕西杨凌712100)
Author(s):
SONG Ziyi; CHANG Qingrui; ZHENG Zhikang; TANG Guoqiang; MENG Yifan
(College of Natural Resources and Environment, Northwest A&F University, Yangling 712100, China)
关键词:
猕猴桃; 叶片氮平衡指数; 高光谱; 光谱变换; 连续投影算法; 支持向量机回归
Keywords:
kiwifruit; leaf nitrogen balance index; hyperspectral; spectral transformation; successive projections algorithm; support vector regression
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2024.07.012
文献标志码:
A
摘要:
通过研究猕猴桃叶片氮平衡指数(Nitrogen balance index,NBI)与高光谱反射率之间的关系,建立合适的遥感估算模型,以期为指导陕西咸阳地区猕猴桃生长监测及田间精准施氮奠定理论基础。以陕西省咸阳市杨凌区的徐香猕猴桃为主要研究对象,测定其高光谱反射率、叶片氮平衡指数,通过一阶导数、二阶导数、连续统去除和标准正态分布光谱变换,分析包含原始光谱在内的5种不同光谱与叶片氮平衡指数之间的关系；进一步通过连续投影算法,剔除冗余信息,筛选出特征波长,并基于不同光谱的特征波长,使用单因素回归模型、随机森林回归(Random forest regression, RF)模型、支持向量机回归(Support vector regression, SVR)模型和偏最小二乘回归(Partial least square regression, PLSR)模型进行建模,比较模型精度。结果表明,当NBI值不同时,猕猴桃叶片相关指标的变化趋势类似:可见光波段的反射率随NBI值的增加呈现下降的趋势,而近红外波段反射率的变化趋势则与之相反,表现出随NBI值的增加而上升的趋势；部分光谱变换可以增加通过0.01水平显著性检验的波段数,提升与NBI值的相关性,其中连续统去除光谱的敏感波段数增加得最多,增加了190个,一阶导数光谱相关系数的绝对值最大值为0.77；连续投影算法可最大限度地减少数据的冗余,最高降维比达99%,在大幅提高计算效率的同时提高了模型的精度；与单因素回归模型相比,多因素机器学习模型对猕猴桃氮平衡指数的估算能力较高,其中SNV-SVR的表现最好,决定系数(R2)为0.82,相对百分比差异(RPD)为2.34。在今后对猕猴桃氮平衡指数的估测中,可优先考虑本研究模型。
Abstract:
By investigating the relationship between kiwifruit leaf nitrogen balance index (NBI) and hyperspectral reflectance, this study established a suitable remote sensing estimation model to provide a theoretical foundation for guiding precise nitrogen management and growth monitoring of kiwifruit in the Xianyang region. Taking Xuxiang kiwifruit in Yangling of Xianyang City, Shaanxi province as the main research object, the hyperspectral reflectance and leaf nitrogen balance index were measured. Through the first derivative, second derivative, continuum removal and standard normal distribution spectral transformation, the relationship between five different spectra including the original spectrum and leaf nitrogen balance index was analyzed. Furthermore, through the successive projections algorithm, the redundant information was eliminated and the characteristic wavelengths were screened out. Based on the characteristic wavelengths of different spectra, single factor regression model, random forest regression (RF) model, support vector regression (SVR) model and partial least square regression (PLSR) model were used for modeling, and the model accuracy was compared. The results showed that when the NBI value was different, the change trend of the related indices of kiwifruit leaves was similar. The reflectivity of the visible light band showed a downward trend with the increase of the NBI value, while the change trend of the reflectivity of the near-infrared band was opposite, showing an upward trend with the increase of the NBI value. Partial spectral transformation increased the number of bands passing the 0.01 level significance test and improved the correlation with NBI values. The number of sensitive bands of continuum removal spectra increased by 190, and the maximum absolute value of the first derivative spectral correlation coefficient was 0.77. The successive projections algorithm could minimize the redundancy of data, and the highest dimensionality reduction ratio was as high as 99%. It greatly improved the computational efficiency and the accuracy of the model. Compared with the single-factor regression model, the multi-factor machine learning model had a higher ability to estimate the kiwifruit nitrogen balance index. SNV-SVR performed best, with a coefficient of determination (R2) of 0.82 and a relative percentage difference (RPD) of 2.34. In the future estimation of kiwifruit nitrogen balance index, the model constructed in this study can be given priority.

参考文献/References:

[1]孙小香,王芳东,赵小敏,等. 基于冠层光谱和BP神经网络的水稻叶片氮素浓度估算模型[J]. 中国农业资源与区划,2019,40(3):35-44.
[2]李容榕,盛观星,林小艳. 凯氏定氮法测定青海省不同地区羌活中全氮含量[J]. 山西大同大学学报(自然科学版),2020,36(2):8-9,17.
[3]杨小秋,王欣,郭敬. 纳氏试剂分光光度法测定烟草样品中总氮含量[J]. 理化检验-化学分册,2013,49(6):755-756.
[4]李长春,陈鹏,陆国政,等. 基于无人机高清数码影像和高光谱遥感数据反演大豆典型生育期氮平衡指数[J]. 应用生态学报,2018,29(4):1225-1232.
[5]MARTINS J A, FIORIO P R, DA SILVA BARROS P P, et al. Potential use of hyperspectral data to monitor sugarcane nitrogen status[J]. Acta Scientiarum Agronomy,2020,43:e47632.
[6]张文旭,佟炫梦,周天航,等. 基于高光谱成像的棉花叶片氮素含量遥感估测[J]. 沈阳农业大学学报,2021,52(5):586-596.
[7]邹德秋,王家强,张冬冬,等. 基于光谱指数的胡杨叶片氮含量估算[J]. 森林与环境学报,2022,42(6):623-630.
[8]FAN K, LI F L, CHEN X K, et al. Nitrogen balance index prediction of winter wheat by canopy hyperspectral transformation and machine learning[J]. Remote Sensing,2022,14(14):3504.
[9]郭松,常庆瑞,张佑铭,等. 连续投影与SSA-ELM结合的玉米氮平衡指数高光谱估测[J]. 西北农业学报,2023,32(1):130-138.
[10]JIANG X P, ZHEN J N, MIAO J, et al. Assessing mangrove leaf traits under different pest and disease severity with hyperspectral imaging spectroscopy[J]. Ecological Indicators,2021,129:107901.
[11]朱红芳,李晓锋,奚丹丹,等. 利用高通量表型平台分析紫叶紫菜薹新组合19-520的表型特征[J]. 江苏农业学报,2021,37(2):465-470.
[12]高雯婷,廖秀芬,黄权龙,等. 一阶导数光谱法同时测定水样中的罗丹明B和活性艳红X-3B[J]. 分析试验室,2021,40(5):523-528.
[13]冯蕾,陈锡芹,程祖顺,等. 二阶导数光谱法定量分析凝灰岩石粉对不同侧链长度聚羧酸减水剂吸附性[J]. 光谱学与光谱分析,2019,39(9):2788-2793.
[14]李鑫,汤卫荣,张永辉,等. 基于高光谱成像技术的烟叶田间成熟度判别模型[J]. 烟草科技,2022,55(7):17-24.
[15]郑煜,常庆瑞,王婷婷,等. 基于连续统去除和偏最小二乘回归的油菜SPAD高光谱估算[J]. 西北农林科技大学学报(自然科学版),2019,47(8):37-45.
[16]YE S F, WANG D, MIN S G. Successive projections algorithm combined with uninformative variable elimination for spectral variable selection[J]. Chemometrics and Intelligent Laboratory Systems,2008,91(2):194-199.
[17]成忠,张立庆,刘赫扬,等. 连续投影算法及其在小麦近红外光谱波长选择中的应用[J]. 光谱学与光谱分析,2010,30(4):949-952.
[18]吴迪,金春华,何勇. 基于连续投影算法的光谱主成分组合优化方法研究[J]. 光谱学与光谱分析,2009,29(10):2734-2737.
[19]张超,余哲修,黄田,等. 基于不同光谱变换的剑湖茭草鲜生物量估测研究[J]. 西南林业大学学报(自然科学),2019,39(6):105-115.
[20]张宇,简季. 基于SPA-BPNN的成都市天府新区东部土壤As含量高光谱估测建模[J]. 桂林理工大学学报,2024,44(1):58-66.
[21]秦佳双,顾大形,倪隆康,等. 桂北岩溶区与非岩溶区植物叶片含水率高光谱反演[J]. 广西植物,2021,41(5):726-737.
[22]孙爱华,顾晓霞,李虎,等. 基于高光谱参数的柑桔园土壤水分动态监测[J]. 中国南方果树,2023,52(4):11-18.
[23]易翔,张立福,吕新,等. 基于无人机高光谱融合连续投影算法估算棉花地上部生物量[J]. 棉花学报,2021,33(3):224-234.
[24]王勇,侯晨悦,杨锡震,等. 基于多种高光谱指标反演冻结土壤含水率的研究[J]. 节水灌溉,2023(7):10-19.
[25]李颀,白泽亮. 基于机器视觉的猕猴桃膨果期营养液预测[J]. 中国科技论文,2020,15(11):1234-1240.
[26]余蛟洋,常庆瑞,班松涛,等. 猕猴桃叶片SPAD值高光谱估算模型构建[J]. 干旱地区农业研究,2018,36(6):168-174.
[27]丁子予,岳学军,曾凡国,等. 基于机器学习和深度学习的玉米种子活力光谱检测[J]. 华中农业大学学报,2023,42(3):230-240.

相似文献/References:

[1]张安世,司清亮,齐秀娟,等.猕猴桃种质资源的SRAP遗传多样性分析及指纹图谱构建[J].江苏农业学报,2018,(01):138.[doi:doi:10.3969/j.issn.1000-4440.2018.01.020]
　ZHANG An-shi,SI Qing-liang,QI Xiu-juan,et al.Genetic diversity and fingerprints of Actinidia germplasm resource based on SRAP markers[J].,2018,(07):138.[doi:doi:10.3969/j.issn.1000-4440.2018.01.020]
[2]范亚磊,赵敏,邓晟,等.侵染江苏猕猴桃的北方根结线虫（Meloidogyne hapla）形态学描述和分子特征分析[J].江苏农业学报,2021,(01):75.[doi:doi:10.3969/j.issn.1000-4440.2021.01.010]
　FAN Ya-lei,ZHAO Min,DENG Sheng,et al.Morphological description and molecular characteristic analysis on Meloidogyne hapla which infect kiwifruit in Jiangsu province[J].,2021,(07):75.[doi:doi:10.3969/j.issn.1000-4440.2021.01.010]
[3]王前菊,王宇,仲伟敏,等.基于UPLC-MS/MS的不同植物生长调节剂处理的猕猴桃果实中代谢物差异分析[J].江苏农业学报,2024,(08):1542.[doi:doi:10.3969/j.issn.1000-4440.2024.08.018]
　WANG Qianju,WANG Yu,ZHONG Weimin,et al.Difference analysis of metabolites in kiwifruit treated with different plant growth regulators based on UPLC-MS/MS[J].,2024,(07):1542.[doi:doi:10.3969/j.issn.1000-4440.2024.08.018]

备注/Memo

备注/Memo:
收稿日期:2023-08-31基金项目:国家高技术研究发展计划资助项目(2013AA102401)作者简介:宋子怡(2000-),女,陕西榆林人,硕士,主要从事土地资源与空间信息技术研究。(E-mail)2364708195@qq.com通讯作者:常庆瑞,(E-mail)changqr@nwsuaf.edu.cn
更新日期/Last Update: 2024-09-14