玉米叶片重金属铅含量的SVD-ANFIS高光谱预测模型

doi:10.3964/j.issn.1000-0593(2021)06-1930-06

Abstract
References
Related Citation (15)

Download: PDF (2221 KB)
Export: BibTeX | EndNote (RIS)

Abstract Heavy metals can enter the human body through the food chain after the crops had been polluted by them and can seriously harm the body health. Therefore, how to quickly and accurately monitor the content of heavy metals in crops has become important research in the fields of ecology and food security. The conventional biochemical monitoring methods have the disadvantages of cumbersome operation, long implementation process and destructiveness, while the hyperspectral remote sensing has the advantages of high spectral resolution, a large amount of information, strong biochemical inversion ability, convenience and fast, and no damage to the monitored object, so using hyperspectral remote sensing to monitor of heavy metal content in crops has become one of the hotspots in the field of remote sensing research. The potted corn plants stressed by different concentrations of Pb(NO₃)₂ solution were used as the research object in the paper, based on the data of the reflectance spectra of corn leaves under different lead ion (Pb²⁺) stress gradients and the measured Pb²⁺ contents in the leaves and combined with the Singular Value Decomposition (SVD) theory and Adaptive Network-based Fuzzy Inference System (ANFIS) structure, an SVD-ANFIS model was established for predicting the Pb²⁺ content in corn leaf. Firstly, SVD was used to process the reflectance spectra of Old leaves (O), Middle leaves (M), New leaves (N) under different stress gradients so that the singular values of the original spectral information were obtained. Then, the singular values corresponding to O, M, N leaves were selected to seek the optimal input combination of the ANFIS structure. Finally, the singular values of the spectra of the O-M (double-input) combination were selected as the input quantity of the ANFIS structure. After obtaining the optimal fuzzy rule base through training and learning, the output quantity of ANFIS structure was the content of Pb²⁺ in the leaves. Thus the SVD-ANFIS model achieved its predictive performance. The results showed that the model’s output error value was small and the prediction accuracy was high, and the prediction effect was best when the membership function was chosen as bell function in the fuzzy training process. When the multi-parameter Back Propagation (BP) neural network prediction model was used to verify the superiority of the prediction of the SVD-ANFIS model, the determination coefficient (R²) of the BP model and SVD-ANFIS model were 0.977 6 and 0.988 7, and the root means square error (RMSE) were 2.455 9 and 0.601 3 respectively, so the SVD-ANFIS model was shown to has a higher fit degree and better prediction effect. At the same time, spectral data of the corn leaves polluted by Pb²⁺ in different years were selected to test the feasibility of the SVD-ANFIS model, and its R² and RMSE were 0.986 4 and 0.887 4, respectively, it indicated that the SVD-ANFIS model could be better used to predict the content of Pb²⁺ in corn leaves with high robustness and could be used as a method to predict the content of heavy metals in corn leaves.

Key words：Spectral analysis; Corn leaves; Singular value decomposition; Adaptive network-based fuzzy inference system; Heavy metal pollution; Prediction model

Received: 2020-06-08 Accepted: 2020-09-30

ZTFLH:

TP7

Corresponding Authors: YANG Ke-ming E-mail: ykm69@163.com

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2021)06-1930-06 OR https://www.gpxygpfx.com/EN/Y2021/V41/I06/1930

[1] FAN Zhi-ying, LI Jiang-rong, GAO Tan, et al(樊志颖, 李江荣, 高郯, 等). Journal of Northwest A&F University·Natural Science Edition(西北农林科技大学学报·自然科学版), 2020, 2002(8): 1.
[2] YI Xing-song, LAN An-jun, WEN Xi-mei, et al(易兴松, 兰安军, 文锡梅, 等). Journal of Ecology(生态学杂志), 2018, 37(6): 1781.
[3] CHEN Nan, LIU Chang-huan, XU Ke, et al(陈楠, 刘长焕, 许可, 等). China Environmental Monitoring(中国环境监测), 2020, 36(2): 88.
[4] HU Yong-quan, HUANG Jian-bo, TIAN Zhi-hua(胡永泉, 黄建波, 田志华, 等). Oil Geophysical Prospecting (石油物探), 2019, 58(1): 43.
[5] Reynolds-Barredo J M, Peraza-Rodríguez H, Sanchez R, et al. Journal of Computational Physics, 2020, 406: 109214.
[6] Adedeji Paul A, Akinlabi Stephen, Madushele Nkosinathi, et al. Journal of Cleaner Production, 2020, 254: 120135.
[7] ZHU Shi-min, CHEN Chang-fu, GAO Jie(朱世民, 陈昌富, 高傑). Journal of Hunan University·Natural Science Edition(湖南大学学报·自然科学版), 2019, 46(11): 137.
[8] JIE Ming, NIU Hong-ya, QI Dan-yuan, et al(解铭, 牛红亚, 齐丹媛, 等). Fuzzy System and Mathematics (模糊系统与数学), 2019, 33(1): 143.
[9] XIA Qin, XING Shuai, MA Dong-yang, et al(夏琴, 邢帅, 马东洋, 等). Journal of Remote Sensing(遥感学报), 2016, 20(3): 441.
[10] Bui Quang-Thanh, Pham Manh Van, Nguyen Quoc-Huy, et al. International Journal of Remote Sensing, 2019, 40(13): 5078.
[11] LI Xu-qing, LI Long, ZHUANG Lian-ying, et al(李旭青, 李龙, 庄连英, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2019, 50(6): 226.
[12] LIU Fei, YANG Ke-ming, SUN Yang-yang, et al(刘飞, 杨可明, 孙阳阳, 等). Science Technology and Engineering(科学技术与工程), 2015, 15(20): 152.
[13] TAO Chao, WANG Ya-jin, ZOU Bin, et al(陶超, 王亚晋, 邹滨, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(6): 1850.
[14] GUO Feng-yi, GAO Hong-xin, WANG Zhi-yong, et al(郭凤仪, 高洪鑫, 王智勇, 等). Journal of Power System and Automation(电力系统及其自动化学报), 2019, 31(11): 39.
[15] FU Hong-po, WEN Yun-tong, MIAO Feng-hai, et al(付红坡, 温云同, 苗风海, 等). Journal of Sensing Technology(传感技术学报), 2019, 32(12): 1795.