Estimating of SPAD value for jujube leaves at different growth stages using the Sentinel-2A image
-
摘要: 准确估算枣树叶片叶绿素含量不仅能反映其长势及营养状况,而且还能为田间管理提供科学依据。该研究以枣树展叶期、坐果期及成熟期叶片为研究对象,旨在评估Sentinel-2A数据估算枣树叶片相对叶绿素含量(SPAD值)的潜力。基于5种典型植被指数框架,利用Sentinel-2A数据的10个波段两两组合构建光谱指数,将构建的光谱指数与实测SPAD值进行相关性分析,通过相关系数筛选最优光谱指数。基于最优光谱指数,分别采用多元线性逐步回归模型(MLSR)、支持向量机回归模型(SVR)和随机森林回归模型(RFR)建立SPAD值估算模型,以决定系数(R2)和均方根误差(RMSE)作为模型评价指标,通过模型评估筛选出估算枣树叶片SPAD值的最优模型。结果表明:(1)3个生育期优选的5种最适光谱指数主要由红波段、红边波段和近红外波段组成,且成熟期优选的5种光谱指数与SPAD值相关性最高,均通过0.01的显著性水平检验,相关系数的绝对值均大于0.37;(2)3个生育期建立的估算模型精度有所差异,其中坐果期估算精度最差,展叶期和成熟期估算精度因模型而异,基于MLSR和SVR模型,成熟期的估算精度最高,基于RFR模型,展叶期精度最高,且展叶期的RFR模型为所有估算模型中的最佳模型,R2和RMSE分别为0.90和1.04;(3)采用的MLSR、SVR和RFR三种回归模型中,MLSR和SVR估算结果较为相似,RFR为最优估算模型,且最优估算模型在不同的植被覆盖场景下具有较强的普适性。以上研究结果表明,Sentinel-2A数据适用于估算枣树叶片SAPD值,且展叶期的RFR模型可作为枣树叶片SPAD值估算的最优模型,研究结果可为基于Sentinel-2A数据估算枣树SPAD值的研究提供重要参考。
-
关键词:
- Sentinel-2A /
- 枣树叶片 /
- 不同生育期 /
- SPAD值
Abstract: Objectives: The accurate estimation of leaf chlorophyll content of jujube can not only reflect its growth and nutritional status, but also provide scientific basis for field management. The aim of this study was to evaluate the potential of Sentinel-2A data for estimating soil plant analysis development (SPAD) values of jujube leaves during leaf spreading, fruit setting stage and fruit ripening stage. Methods: In this paper, five traditional vegetation indices related to chlorophyll content were selected, and based on the framework of five traditional vegetation indices, ten bands of Sentinel-2A data were used to improve the traditional vegetation indices, and five spectral indices were constructed for three growth periods respectively. The correlation between the constructed spectral index and the measured SPAD value was analyzed, and the optimal spectral index was screened by the correlation coefficient. Based on the optimal spectral index, multiple linear stepped-regression model (MLSR), support vector machine regression model (SVR) and random forest regression model (RFR) were used to establish SPAD estimation models. The coefficient of determination (R2) and Root mean square error (RMSE) were used as model evaluation indexes, and the optimal model for estimating the SPAD value of jujube leaves was screened out through model evaluation. Results: The results showed that:the five optimal spectral indices optimized at three growth stages were mainly composed of red band, red-edge band and near-infrared band, and the five optimal spectral indices at fruit ripening stage had the highest correlation with SPAD value, all of which passed the significance level test of 0.01, and the absolute values of correlation coefficients were all greater than 0.37. The accuracy of estimation models established at different growth stages was different, and the accuracy of estimation at fruit setting stage was the worst. The estimation accuracy of leaf spreading stage and fruit ripening stage varied according to the models. The accuracy of fruit ripening stage was the highest based on MLSR and SVR, while the accuracy of leaf spreading stage was the highest based on RFR. The RFR model of leaf spreading stage was the best model among all the estimation models, R2 and RMSE were 0.90 and 1.04, respectively. Among the three regression models used, MLSR, SVR and RFR, the estimation results of MLSR and SVR are similar, and RFR is the best estimation model, and the best estimation model has strong universality under different vegetation cover scenarios. Conclusions: The above results show that Sentinel-2A data is suitable for SAPD estimation of jujube leaves, and the RFR model at leaf spreading stage can be used as the optimal model for SPAD estimation of jujube leaves. The results can provide an important reference for the study of estimating SPAD value of jujube based on Sentinel-2A data.-
Keywords:
- Sentinel-2A /
- Jujube tree leaves /
- Different growth stages /
- SPAD value
-
-
[1] Xu M, Chen Q, Kong X, et al. Heavy metal contamination and risk assessment in winter jujube (Ziziphus jujuba Mill. cv. Dongzao)[J]. Food and Chemical Toxicology, 2023, 174:113645.
[2] Zhuo P, Li Y, Wang B, et al. Analysis and experimental study on vibration response characteristics of mechanical harvesting of jujube[J]. Computers and Electronics in Agriculture, 2022, 203:107446.
[3] Bai T, Zhang N, Mercatoris B, et al. Jujube yield prediction method combining Landsat 8 Vegetation Index and the phenological length[J]. Computers and Electronics in Agriculture, 2019, 162:1011-1027.
[4] Liu Y, Hatou K, Aihara T, et al. A robust vegetation index based on different UAV RGB images to estimate SPAD values of naked barley leaves[J]. Remote Sensing, 2021, 13(4):686.
[5] Fang Shenghui, Le Yuan, Liang Qi. Retrieval of Chlorophyll Content Using Continuous Wavelet Analysis Across a Range of Vegetation Species[J]. Geomatics and Information Science of Wuhan University, 2015, 40(3):296-302.(方圣辉,乐源,梁琦.基于连续小波分析的混合植被叶绿素反演[J].武汉大学学报(信息科学版), 2015, 40(3):296-302.) [6] Qin Zhanfei, Chang Qingrui, Shen Jian, et al. Red Edge Characteristics and SPAD Estimation Model Using Hyperspectral Data for Rice in Ningxia Irrigation Zone[J]. Geomatics and Information Science of Wuhan University, 2016, 41(9):1168-1175.(秦占飞,常庆瑞,申健,等.引黄灌区水稻红边特征及SPAD高光谱预测模型[J].武汉大学学报(信息科学版), 2016, 41(9):1168-1175.) [7] Clevers J G P W, Kooistra L, Van den Brand e M M M. Using Sentinel-2A data for retrieving LAI and leaf and canopy chlorophyll content of a potato crop[J]. Remote Sensing, 2017, 9(5):405.
[8] Dong Zhe, Yang Wude, Zhang Meijun, et al. Estimation Models of Maize Leaf SPAD Value Based on Hyperspectral Remote Sensing[J]. Crops,2019,(03):126-131.(董哲,杨武德,张美俊,等.基于高光谱遥感的玉米叶片SPAD值估算模型研究[J].作物杂志,2019,(03):126-131.) [9] Tang Xuguang, Song Kaishan, Liu Dianwei, et al. Comparison of methods for Estimating Soybean Chlorophyll Content Based on Visual/Near Infrared Reflection Spectra[J]. Spectroscopy and Spectral Analysis,2011,31(02):371-374.(汤旭光,宋开山,刘殿伟,等.基于可见/近红外反射光谱的大豆叶绿素含量估算方法比较[J].光谱学与光谱分析,2011,31(02):371-374.) [10] Zhou Mingu, Shao Guomin, Zhang Liyuan, et al. Inversion of SPAD value of winter wheat by multispectral remote sensing of unmanned aerial vehicles[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020,36(20):125-133.(周敏姑,邵国敏,张立元,等.无人机多光谱遥感反演冬小麦SPAD值[J].农业工程学报,2020,36(20):125-133.) [11] Liu Zhong, Wan Wei, Huang Jinyu, et al. Progress on key parameters inversion of crop growth based on unmanned aerial vehicle remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering,2018,34(24):60-71.(刘忠,万炜,黄晋宇,等.基于无人机遥感的农作物长势关键参数反演研究进展[J].农业工程学报,2018,34(24):60-71.) [12] Sun Hong, Li Minzan, Zhao Yong, et al. The Spectral Characteristics and Chlorophyll Content at Winter Wheat Growth Stages[J]. Spectroscopy and Spectral Analysis,2010,30(01):192-196.(孙红,李民赞,赵勇,等.冬小麦生长期光谱变化特征与叶绿素含量监测研究[J].光谱学与光谱分析,2010,30(01):192-196.) [13] Soudani K, François C, Maire L G, et al. Comparative analysis of IKONOS, SPOT, and ETM+data for leaf area index estimation in temperate coniferous and deciduous forest stands[J]. Remote Sensing of Environment,2006,102(1).
[14] Jia Yuqiu, Li Bing, Cheng Yongzheng, et al. Comparison between GF-1 images and Landsat-8 images in monitoring maize LAI. Trans actions of the Chinese Society of Agricultural Engineering,2015,31(09):173-179.(贾玉秋,李冰,程永政,等.基于GF-1与Landsat-8多光谱遥感影像的玉米LAI反演比较.农业工程学报,2015,31(09):173-179.) [15] Cheng Qian. Estimation models of rice LAI and Chlorophyll content based on MOD09[J]. Chinese Journal of Applied Ecology,2006,(08):1453-1458.(程乾.基于MOD09产品的水稻叶面积指数和叶绿素含量的遥感估算模型[J].应用生态学报,2006,(08):1453-1458.) [16] JIN Hua'an, LI Ainong, BIAN Jinhu, et al. Comparative Analysis of HJ-1B CCD2 and SPOT4 HRVIR Data for Aboveground Biomass Estimation in Forest Stands[J]. Geomatics and Information Science of Wuhan University, 2016, 41(11):1483-1490. doi:10.13203/j.whugis20140594.(靳华安,李爱农,边金虎,等. HJ-1B CCD2与SPOT4 HRVIR数据在森林地上生物量反演中的比较分析[J].武汉大学学报(信息科学版), 2016, 41(11):1483-1490. doi:10.13203/j.whugis20140594) [17] Wang Liai, Zhou Xudong, Zhu Xinkai, et al. Inverting wheat leaf area index based on HJ-CCD remote sensing data and random forest algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering,2016,32(03):149-154.(王丽爱,周旭东,朱新开,等.基于HJ-CCD数据和随机森林算法的小麦叶面积指数反演[J].农业工程学报,2016,32(03):149-154.) [18] Yi Qiuxiang. Remote estimation of cotton LAI using Sentinel-2A multispectral data[J]. Transactions of the Chinese Society of Agricultural Engineering,2019,35(16):189-197.(易秋香.基于Sentinel-2A多光谱数据的棉花叶面积指数估算[J].农业工程学报,2019,35(16):189-197.) [19] Cui B, Zhao Q J, Huang W J, et al. Leaf chlorophyll content retrieval of wheat by simulated RapidEye, Sentinel-2A and EnMAP data[J]. Journal of Integrative Agriculture,2019, 18(06):1230-1245.
[20] Qian B X, Ye H C, Huang W J, et al. A Sentinel-2A-based triangular vegetation index for chlorophyll content estimation[J]. Agricultural and Forest Meteorology,2022,322.
[21] Dong L, Chen J M, Zhang X, et al. Improved estimation of leaf chlorophyll content of row crops from canopy reflectance spectra through minimizing canopy structural effects and optimizing off-noon observation time[J]. Remote Sensing of Environment,2020,248.
[22] Xu Yunfei, Cheng Qi, Wei Xiangping, et al. Monitoring of winter wheat growth under UAV using variation method and optimized neural network[J]. Transactions of the Chinese Society of Agricultural Engineering,2021,37(20):71-80.(徐云飞,程琦,魏祥平,等.基于变异系数法和优化神经网络的无人机冬小麦长势监测[J].农业工程学报,2021,37(20):71-80.) [23] Issa S, Dahy B, Saleous N, et al. Carbon stock assessment of date palm using remote sensing coupled with field-based measurements in Abu Dhabi (United Arab Emirates)[J]. International Journal of Remote Sensing,2019,40(19).
[24] Zhang Dongyan, Yang Yuying, Huang Lisheng, et al. Extraction of soybean planting area s combining Sentinel-2A images and optimize d feature model[J]. Transactions of the Chinese Society of Agricultural Engineering,2021, 37(09):110-119.(张东彦,杨玉莹,黄林生,等.结合Sentinel-2A影像和特征优选模型提取大豆种植区[J].农业工程学报,2021,37(09):110-119.) [25] Li Miaomiao, Wu Bingfang, Yan Changzhen, et al. Estimation of Vegetation Fraction in the Upper Basin of Miyun Reservoir by Remote Sensing[J]. Resources science, 2004,(04):153-159.(李苗苗,吴炳方,颜长珍,等.密云水库上游植被覆盖度的遥感估算[J].资源科学,2004,(04):153-159.) [26] Ru Jingna, Yu Yang, Dong Fanfan, et al. Analysis of QTL for Heading Date and Interaction Effects with Environments in Wheat[J]. Journal of Triticeae Crops,2014,34(09):1185-1190.(茹京娜,于洋,董凡凡,等.小麦抽穗期QTL及其与环境的互作[J].麦类作物学报,2014,34(09):1185-1190.) [27] Tuerxun Nigela, Naibi Sulei, Gao Jian, et al. Chlorophyll Content Estimation of Jujube Leaves Based on GWLS-SVR Mosel[J]. Spectroscopy and Spectral Analysis, 2021,41(06):1730-1736.(尼格拉·吐尔逊,苏磊·乃比,高健,等. GWLS-SVR模型的红枣树叶片叶绿素含量估算[J].光谱学与光谱分析,2021,41(06):1730-1736.) [28] Jiang Fugen, Sun Hua, Li Chengjie, et al. Retrieving the forest above ground biomass by combining the red edge bands of Sentinel-2A and GF-6[J]. ACTA ECOLOGICA SINICA,2021,41(20):8222-8236.(蒋馥根,孙华,李成杰,等.联合GF-6和Sentinel-2A红边波段的森林地上生物量反演[J].生态学报,2021,41(20):8222-8236.) [29] Gu Feng, Ding Jianli, Ge Xiangyu, et al. Estimation of Chlorophyll Content of Typical Oasis Vegetation in Arid Area Based on Sentinel-2 Data. ARID ZONE RESEARCH,2019,36(04):924-934.(顾峰,丁建丽,葛翔宇,等.基于Sentinel-2A数据的干旱区典型绿洲植被叶绿素含量估算.干旱区研究,2019,36(04):924-934.) [30] Zhen Jianing, Jiang Xiapeng, Zhao Demei, et al. Retrieving canopy nitrogen content of mangrove forests from Sentinel-2A super-resolution reconstruction data[J]. National Remote Sensing Bulletin, 2022, 26(6):1206-1219.(甄佳宁,蒋侠朋,赵德梅,王俊杰,苗菁,邬国锋.利用Sentinel-2A影像超分辨率重建的红树林冠层氮含量反演[J].遥感学报,2022,26(06):1206-1219.) [31] Zhang Y M, Ta N, Guo S, et al. Combining Spectral and Textural Information from UAV RGB Images for Leaf Area Index Monitoring in Kiwifruit Orchard[J]. Remote Sensing,2022,14(5).
[32] Han Zhaoying, Zhu Xicun, Fang Xianyi, et al. Hyperspectral Estimation of Apple Tree Canopy LAI Based on SVM and RF Regression. Spectroscopy and Spectral Analysis,2016,36(03):800-805.(韩兆迎,朱西存,房贤一,等.基于SVM与RF的苹果树冠LAI高光谱估测.光谱学与光谱分析,2016,36(03):800-805.) [33] Li Fengling, Wang Li, Liu Jing, et al. Remote Sensing Estimation of SPAD Value for Wheat Leaf Based on GF-1 Data. Transactions of the Chinese Society for Agricultural Machinery,2015,46(09):273-281.(李粉玲,王力,刘京,等.基于高分一号卫星数据的冬小麦叶片SPAD值遥感估算.农业机械学报,2015,46(09):273-281.) [34] Breiman L. Random Forests[J]. Machine Learning,2001,45(1).
[35] Jiang Hailing, Yang Hang, Chen Xiaoping, et al. Research on Accuracy and Stability of Inversing Vegetation Chlorophyll Content by Spectral Index Method. Spectroscopy and Spectral Analysis,2015,35(04):975-981.(姜海玲,杨杭,陈小平,等.利用光谱指数反演植被叶绿素含量的精度及稳定性研究.光谱学与光谱分析,2015,35(04):975-981.) [36] Yu K, Lenz-Wiedemann V, Chen X, et al. Estimating leaf chlorophyll of barley at different growth stages using spectral indices to reduce soil background and canopy structure effects[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2014,97.
[37] Zhang M, Su W, Fu Y, et al. Super-resolution enhancement of Sentinel-2A image for retrieving LAI and chlorophyll content of summer corn[J]. European Journal of Agronomy,2019,111(C)
计量
- 文章访问数: 282
- HTML全文浏览量: 15
- PDF下载量: 15