北方寒地水稻叶片磷素含量高光谱反演方法研究

doi:10.3964/j.issn.1000-0593(2023)05-1442-08

摘要
参考文献
相关文章 (15)

全文: PDF (9426 KB)
输出: BibTeX | EndNote (RIS)

摘要：为了快速、准确的检测北方寒地水稻叶片的磷素含量，分析水稻的长势情况，为精准施肥以及稻田的科学管理提供依据，以北方寒地水稻为研究对象，以小区实验为基础，使用海洋光学HR 2000+光谱仪获取水稻叶片高光谱反射率数据，采用钒钼黄比色法对水稻叶片磷素含量进行测定。采用SG平滑与多元散射校正（MSC）两种方法对水稻叶片高光谱数据进行预处理，并将预处理后的光谱数据使用连续投影法（SPA）与无信息变量消除法（UVE）两种算法进行特征选择。采用SPA算法筛选得到的特征共有11个，其中位于可见光波段处的有6个，分别为411、420、428、442、467和689 nm；近红外波段处有5个，分别为797、850、866、965和976 nm；UVE算法筛选得到的特征共47个，均位于可见光波段范围内，分布在405~603 nm之间。分别将这两种方法筛选出的特征波段的反射率作为输入，构建极限学习机（ELM），BP神经网络以及狼群算法优化的BP神经网络（WPA-BP）三种水稻叶片磷素含量反演模型并加以分析。结果表明：以UVE算法筛选的特征反射率为输入量构建的三种模型的验证集R²在0.705 2~0.724 5之间，RMSE在0.017 4~0.020 4之间；在相同的反演模型的条件下，使用SPA算法筛选的特征反射率为输入量构建的模型预测效果更好，三种模型的验证集R²在0.726 4~0.829 3之间，RMSE在0.018 0~0.021 1之间；另外，在利用这两种算法筛选到的特征进行建模时，对比三种模型的预测结果发现，经过狼群算法优化后的BP神经网络模型的精度明显高于极限学习机和BP神经网络，其验证集的决定系数R²为0.803 4，RMSE为0.018 0。鉴于此，结合连续投影算法和狼群算法优化后的BP神经网络模型在北方寒地水稻叶片磷素含量高光谱反演中具有一定的优势，可作为水稻叶片磷素含量的检测以及精准定量施肥的参考和借鉴。

关键词：水稻；高光谱数据；磷素含量；狼群算法；反演模型

Abstract：In order to quickly and accurately detect the phosphorus content information of rice leaves in the cold northern region, analyze the growth of rice, and provide the basis for precision fertilization and scientific management of rice fields, this study takes rice in the cold northern region as the research object, based on the plot experiment, and uses the marine optical HR 2000+ spectrometer to obtain the hyperspectral reflectance data of rice leaves, the content of phosphorus in rice leaves was determined by vanadium molybdenum yellow colorimetry.SG smoothing and multiple scattering corrections (MSC) were used to preprocess rice leaf hyperspectral data. The spectral data were selected by using SPA and UVE. Eleven features were screened by the SPA algorithm, including 6 in the visible band (411, 420, 428, 442, 467 and 689 nm) and 5 in near-infrared band (797, 850, 866, 965 and 976 nm). A total of 47 features were obtained by the UVE algorithm, which was all located in the visible band range and distributed between 405 and 603 nm. Taking the characteristic reflectance selected by the two methods as input, three inversion models of phosphorus content in rice leaves were constructed and analyzed, including extreme learning machine (ELM), BP neural network and wolf pack algorithm (WPA-BP).The results show that the verification set R² of the three models constructed with the characteristic reflectivity filtered by the UVE algorithm as the input is between 0.705 2~0.724 5 and RMSE is between 0.017 4~0.020 4; Under the condition of the same inversion model, the prediction effect of the model constructed by using the characteristic reflectivity filtered by SPA algorithm as the input is good. The verification set R² of the three models is between 0.726 4~0.829 3, and RMSE is between 0.018 0~0.021 1; In addition, when using the features screened by the two algorithms for modeling, comparing the prediction results of the three models, it is found that the accuracy of the BP neural network model optimized by the wolf swarm algorithm is significantly higher than that of the ELM and BP neural network, and the determination coefficient R² of the verification set is 0.803 4 and RMSE is 0.018 0. Because of this, the combination of SPA and WPA-BP has certain advantages in a hyperspectral inversion of phosphorus content in rice leaves in the cold northern region, which can be used as a reference for the detection of phosphorus content in rice leaves and accurate quantitative fertilization.

Key words：Rice; Hyperspectral data; Phosphorus content; Wolf pack algorithm; Inversion model

收稿日期: 2022-03-07 修订日期: 2022-05-31

中图分类号:

O657.3

基金资助: 辽宁省重点攻关项目（LSNZD202005），国家重点研发计划项目（2018YFD0300309）资助

通讯作者: 许童羽 E-mail: xutongyu@syau.edu.cn

作者简介: 杨柳，女，1998年生，沈阳农业大学信息与电气工程学院硕士研究生 e-mail: 475474313@qq.com

引用本文:

杨柳，郭忠辉，金忠煜，白驹驰，于丰华，许童羽. 北方寒地水稻叶片磷素含量高光谱反演方法研究[J]. 光谱学与光谱分析, 2023, 43(05): 1442-1449.
YANG Liu, GUO Zhong-hui, JIN Zhong-yu, BAI Ju-chi, YU Feng-hua, XU Tong-yu. Inversion Method Research of Phosphorus Content in Rice Leaves Produced in Northern Cold Region Based on WPA-BP. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1442-1449.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2023)05-1442-08 或 https://www.gpxygpfx.com/CN/Y2023/V43/I05/1442

[1] LIU Yan-ling, LI Yu, BAI Yi-jing, et al(刘彦伶, 李渝, 白怡婧，等). Journal of Plant Nutrition and Fertilizers(植物营养与肥料学报), 2019, 25(7): 1146.
[2] CHENG Ming-fang, HE Ping, JIN Ji-yun(程明芳, 何萍, 金继运). Crops(作物杂志)，2010，(1): 12.
[3] Osborne S L, Schepers J S, Francis D D, et al. Agronomy Journal, 2002, 94(6): 1214.
[4] YE Lin-wei, TANG Rong-nian, LI Chuang(叶林蔚, 唐荣年, 李创). Journal of Agricultural Science and Technology(中国农业科技导报), 2021, 23(7): 117.
[5] LIN Fen-fang, DING Xiao-dong, FU Zhi-peng, et al(林芬芳, 丁晓东, 付志鹏，等). Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2009, 29(9): 2467.
[6] Mahajan G R, Pandey R N, Sahoo R N, et al. Precision Agriculture, 2017, 18(5): 736.
[7] BAN Song-tao, TIAN Ming-lu, CHANG Qing-rui, et al(班松涛, 田明璐, 常庆瑞，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2021, 52(8): 163.
[8] LI Ying, XUE Li-hong, PAN Fu-yan, et al(李颖, 薛利红, 潘复燕，等). Scientia Agricultura Sinica(中国农业科学), 2014, 47(14): 2742.
[9] XU Tong-yu, GUO Zhong-hui, YU Feng-hua, et al(许童羽, 郭忠辉, 于丰华，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(2): 209.
[10] DUAN Bin-wu, XU Xia, HE Xiao-yan, et al(段彬伍, 徐霞, 何小嫣，等). China Rice(中国稻米), 2012, 18(4): 48.
[11] WANG Zhan, WANG Ke, WANG Wei-chao(王展, 王可, 王伟超). Laser & Optoelectronics Progress(激光与光电子学进展), 2019, 56(2): 217.
[12] Li J, Zhang H, Zhan B, et al. Infrared Physics & Technology, 2019, 104: 103154.
[13] Wang Z, Chen J, Fan Y, et al. Computers and Electronics in Agriculture, 2020, 169: 105160.
[14] Wang Z, Zhang Y, Fan S, et al. IEEE Access, 2020, 8: 195229.
[15] WU Hu-sheng, ZHANG Feng-ming, WU Lu-shan(吴虎胜, 张凤鸣, 吴庐山). Systems Engineering and Electronics(系统工程与电子技术), 2013, 35(11): 2430.
[16] LIU Cong, FEI Wei, HU Sheng(刘聪, 费炜, 胡胜). Science Technology and Engineering(科学技术与工程), 2020, 20(9): 3378.