不同生育期小麦冠层SPAD值无人机多光谱遥感估算

doi:10.3964/j.issn.1000-0593(2023)06-1912-09

摘要
参考文献
相关文章 (15)

全文: PDF (15963 KB)
输出: BibTeX | EndNote (RIS)

摘要：随着长江中下游稻麦轮作区水稻成熟期的推迟，冬小麦播期的推迟已经成为影响产量的主要障碍，因此在迟播小麦中筛选抗性较好的品种很有必要。该研究旨在监测冬小麦生长早期冠层叶片的相对叶绿素含量，用于迟播冬小麦品种筛选。为探讨利用无人机多光谱影像监测冬小麦叶绿素含量的可行性，基于多光谱无人机获取的5个单波段光谱反射率和15个植被指数作为自变量，经过递归特征消除法（RFE）特征变量筛选，去除冗余变量，利用后向神经网络（BP）回归算法构建冬小麦相对叶绿素含量（SPAD）值遥感反演模型。根据2020年—2021年江苏省扬州市广陵区实验点冬小麦越冬期、拔节期两个生育期的实测叶片SPAD值，结合同步获取的多光谱无人机影像，分析了这两个生育期遥感变量和SPAD值之间的相关性。并结合遥感变量之间的特征重要性排序进行特征变量筛选，筛选出的变量作为模型的输入，构建并筛选出各生育期最佳的反演模型。比较岭回归（Ridge）和梯度提升树（GBD）算法，以R²和RMSE作为模型评价指标，在验证集上分析了各生育期3种模型的自学习能力和泛化能力。结果表明，经过了最优光谱信息筛选而建立的BP神经网络模型在此两个生育期的数据集上均表现出了最强的回归预测能力。R²和RMSE在越冬期分别为0.806和1.861，拔节期分别为0.827和0.507。通过对无人机多光谱数据进行变量筛选，构建的优选模型BP神经网络具有较高估算精度，且表明在冬小麦的早期监测中，拔节期比越冬期效果好。利用无人机多光谱在估算迟播冬小麦SPAD值进行品种抗性筛选的方法是有价值的。

关键词：品种筛选；无人机；小麦SPAD值； BP神经网络；特征选择

Abstract：With the delay of rice maturity in rice-wheat rotation areas in the middle and lower reaches of the Yangtze River, the delay of the sowing date of winter wheat has become the main obstacle affecting the yield, so it is necessary to screen better resistant varieties in late sowing wheat. This study was designed to monitor the relative chlorophyll content of canopy leaves during the early winter wheat growth for late-sowing winter wheat variety screening. In order to explore the feasibility of monitoring chlorophyll content in winter wheat, this study used five single-band spectral reflectance and 15 vegetation indices obtained by UAV as the independent variables. Through recursive feature elimination (RFE) feature variables screening, redundant variables were removed. A remote sensing inversion model of winter wheat’s relative chlorophyll content (SPAD) was established using the BP neural network regression algorithm. Based on the measured leaf SPAD values of winter wheat in the experimental site of Guangling District, Yangzhou city, Jiangsu Province, during 2020—2021, the correlation between remote sensing variables and SPAD values in the two growth stages was analyzed combined with multi-spectral UAV images obtained simultaneously. In addition, feature variables were screened based on the ranking of feature importance among remote sensing variables, and the selected variables were used as the input of the model to construct and screen out the best inversion model for each growth period. Using Ridge regression (Ridge) and Gradient Boosting Decision Tree (GBD) algorithms as a comparison, and R² and RMSE as model evaluation indexes, the three models’ self-learning ability and generalization ability were analyzed on the validation set. The results showed that the BP neural network model based on optimal spectral information screening showed the strongest regression prediction ability in the two growth periods. R² and RMSE were 0.806 and 1.861 in the overwintering stage and 0.827 and 0.507 in the jointing stage, respectively. In this paper, the variable selection of UAV multi-spectral data was carried out, and the BP neural network of optimization model constructed had high estimation accuracy. It showed that the effect of early monitoring of winter wheat was better in the elongation stage than in the overwintering stage. It is valuable to use UAV multi-spectrum to estimate the SPAD value of late-sowing winter wheat for variety resistance screening.

Key words：Variety screening; UAV; Wheat SPAD values; BP neural network; Feature selection

收稿日期: 2022-02-23 修订日期: 2022-06-27

中图分类号:

S127

基金资助: 江苏省研究生培养创新工程研究生科研与实践创新计划项目（SJCX21_1610），国家重点研发计划项目（2018YFD 0300802），江苏省重点研发计划项目（BE2020319），扬州大学高端人才支持计划项目(2018年度)资助

通讯作者: 王建军，霍中洋 E-mail: wangjianjun@yzu.edu.cn；zyhuo@yzu.edu.cn

作者简介: 周琦，女，1997年生，扬州大学农学院硕士研究生 e-mail: mz120201238@yzu.edu.cn

引用本文:

周琦，王建军，霍中洋，刘畅，王维领，丁琳. 不同生育期小麦冠层SPAD值无人机多光谱遥感估算[J]. 光谱学与光谱分析, 2023, 43(06): 1912-1920.
ZHOU Qi, WANG Jian-jun, HUO Zhong-yang, LIU Chang, WANG Wei-ling, DING Lin. UAV Multi-Spectral Remote Sensing Estimation of Wheat Canopy SPAD Value in Different Growth Periods. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1912-1920.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2023)06-1912-09 或 https://www.gpxygpfx.com/CN/Y2023/V43/I06/1912

[1] GAO De-rong, WANG Hui, LIU Qiao, et al（高德荣, 王慧, 刘巧，等）. Scientia Agricultura Sinica（中国农业科学）, 2019, 52(14): 2379.
[2] GAO De-rong, ZHANG Xiao, KANG Jian-peng, et al（高德荣, 张晓, 康建鹏，等）. Journal of Triticeae Crops（麦类作物学报）, 2014, 34(2): 279.
[3] Bekele F，Korecha D，Negatu L. Journal of Agrometeorology，2017，19(2): 125.
[4] WANG Li-ai, MA Chang, ZHOU Xu-dong, et al（王丽爱, 马昌, 周旭东，等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2015, 46(1): 259.
[5] GAO Xiao-mei, LI Yan-li, LU Bi-lin, et al（高小梅, 李燕丽, 卢碧林，等）. Chinese Journal of Applied Ecology（应用生态学报）, 2021, 32(3): 959.
[6] ZHOU Min-gu, SHAO Guo-min, ZHANG Li-yuan, et al（周敏姑, 邵国敏, 张立元，等）. Transactions of the Chinese Society of Agricultureal Engineering（农业工程学报）, 2020, 36(20): 125.
[7] WEI Qing, ZHANG Bao-zhong, WEI Zheng，et al（魏青, 张宝忠, 魏征，等）. Journal of Triticeae Crops（麦类作物学报）, 2020, 40(3): 365.
[8] LIU Shuang, YU Hai-ye, ZHANG Jun-he, et al（刘爽, 于海业, 张郡赫，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析）, 2021, 41(6): 1912.
[9] Shi Peihua, Wang Yuan, Xu Jianmin, et al. Computers and Electronics in Agriculture, 2021, 180: 105860.
[10] ZHANG Zhi-tao, ZHOU Yong-cai, YANG Shuai，et al（张智韬, 周永财, 杨帅，等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2021, 52(4): 197.
[11] Rondeaux G, Steven M, Baret F. Remote Sensing of Environment, 1996, 55(2): 95.
[12] Verrelst J, Schaepman M, Koetz B, et al. Remote Sensing of Environment, 2008, 112(5): 2341.
[13] Gitelson A A, Vina A, Ciganda V, et al. Geophysical Research Letters, 2005, 32(8): L08403.
[14] Gitelson A A, Gritz Y, Merzlyak M N. Journal of Plant Physiology, 2003, 160(3): 271.
[15] Chen J M. Canadian Journal of Remote Sensing, 2014, 22(3): 229.
[16] WANG Zheng-xing, LIU Chuang, HUETE Alfredo, et al（王正兴, 刘闯，HUETE Alfredo, 等）. Acta Ecologica Sinica（生态学报）, 2003，23(5): 979.
[17] Dash J, Curran P J. Advances in Space Research, 2007, 39(1): 100.
[18] Huete A, Didan K, Miura T, et al. Remote Sensing of Environment, 2002, 83(1): 195.
[19] SHI Duan-yang, LIN Qiang, HU Bing，et al（施端阳, 林强, 胡冰，等）. Journal of Ordnance Equipment Engineering（兵器装备工程学报）, 2021, 42(10): 79.
[20] DU Ya-juan, ZHAO En-fa, ZHANG Yu-shun，et al（杜亚娟, 赵恩法, 张玉顺，等）. Chinese Heart Jorunal（心脏杂志）, 2020, 32(5): 471.
[21] Liu N, Liu G, Sun H. Sensors, 2020, 20(12): 3430.
[22] Liu Y, Hatou K, Aihara T, et al. Remote Sensing, 2021, 13(4): 686.
[23] TIAN Ming-lu, BAN Song-tao, CHANG Qing-rui，et al（田明璐, 班松涛, 常庆瑞，等）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2016, 32(21): 102.
[24] LI Yan-li, XIONG Qin-xue, LU Bi-lin，et al（李燕丽, 熊勤学, 卢碧林，等). Journal of Irrigation and Drainage（灌溉排水学报）, 2020, 39(12): 41.
[25] CHEN Xiao-na, ZHAO Geng-xing, ZHOU Xue，et al（陈晓娜, 赵庚星, 周雪，等）. Tianjin Agriculture Science（天津农业科学）, 2018, 24(2): 60.
[26] ZHOU Xue, WANG Fang, ZHAO Geng-xing（周雪, 王芳, 赵庚星）. Shangdong Agriculture Science（山东农业科学）, 2016, 48(6): 138.
[27] MA Wen-jun, CHANG Qing-rui, TIAN Ming-lu，et al（马文君, 常庆瑞, 田明璐，等）. Agricultural Research in the Arid Areas（干旱地区农业研究）, 2017, 35(5): 42.