水稻产量遥感监测机器学习算法对比

doi:10.3964/j.issn.1000-0593(2022)05-1620-08

Abstract
References
Related Citation (15)

Download: PDF (4150 KB)
Export: BibTeX | EndNote (RIS)

Abstract Rice is China’s major grain food crop, grown mainly in the Yangtze River valley and southern China and on the Yunnan-Guizhou Plateau. The use of hyperspectral remote sensing technology to monitor rice yield before it matures is important. It can promptly adjust cultivation management methods and guide reasonable fertilization, and accurately grasp rice yield information to help the government make decisions in advance. In this study, the nitrogen fertilizer gradient experiment was carried on 2019—2020 at Zhongluotan experimental base in Baiyun District, Guangzhou City. The rice canopy hyperspectral data, crop population growth parameters (plant above-ground biomass (AGB) and leaf area index (LAI)) and crop nitrogen nutrient intakes at the rice differentiation and heading stage were obtained. Three machine learning algorithms, Bayesian Ridge Regression (BRR), Support Vector Regression (SVR), and Partial Least Square Regression (PLSR), were used to establish yield estimate models based on the different data sources, including rice canopy spectrum data, spectrum data combined with crop growth parameters, and spectral data, crop growth parameters, and crop nutrient intake data. The estimation accuracy of BRR, SVR and PLSR models, were evaluated and compared, then the best estimation model and optimal estimation growth period for rice yield were determined. The results showed that among the three methods, the BRR and SVR methods were more suitable for yield monitoring, with better performance in different periods and different parameter combinations (R²>0.82, NRMSE<8.22%). Based on the 2019 and 2020 data, the best monitoring model for yield monitoring using full-band spectral information was the BRR model at the differentiation stage with R² of 0.90 and the SVR model at the tasseling stage with R² of 0.87. When full-band spectral information was used for yield monitoring, the best monitoring model for both periods was the BRR model with R² of 0.90 and 0.92, respectively, compared with the BRR and SVR models, the highest R² of the PLSR model was only 0.75 for different periods and different combinations of parameters; based on the 2020 data, when three different parameter combinations were used as inputs, the BRR model was the best in both periods, and the modeling accuracy was higher in the differentiation period than in the tasseling period (R² increased by at least 0.02 and NRMSE decreased by at least 0.61%), and when the input parameter combinations were full-band spectra with crop population growth parameters and crop nutrient uptake, the accuracy of the BRR model for yield estimation reached Through the experimental study, it was concluded that the optimal monitoring period for yield is the differentiation period. The optimal monitoring model is the BRR model. The study results can provide a reference for early remote sensing monitoring of rice yield.

Key words：Hyperspectral remote sensing; Rice yield estimation; Bayesian ridge regression; Support vector regression

Received: 2021-09-30 Accepted: 2022-02-25

ZTFLH:

TP79

Corresponding Authors: SONG Xiao-yu E-mail: songxy@nercita.org.cn

Cite this article:

JING Xia,ZHANG Jie,WANG Jiao-jiao, et al. Comparison of Machine Learning Algorithms for Remote Sensing Monitoring of Rice Yields[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1620-1627.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2022)05-1620-08 OR https://www.gpxygpfx.com/EN/Y2022/V42/I05/1620

[1] ZHANG Han, ZHAO Xiao-min, GUO Xi, et al(张晗, 赵小敏, 郭熙, 等). Jiangsu Agricultural Science(江苏农业科学), 2018, 46(12): 1.
[2] JIANG Huan-yu, YING Yi-bin, XIE Li-juan(蒋焕煜, 应义斌, 谢丽娟). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2008，28(6): 1300.
[3] Liu X D, Sun Q H. International Journal of Pest Management, 2016, 62(3): 205.
[4] XUE Li-hong, CAO Wei-xing, LUO Wei-hong(薛利红, 曹卫星, 罗卫红). Journal of Remote Sensing(遥感学报), 2005，(1): 100.
[5] SONG Hong-yan, HU Ke-lin, PENG Xi(宋红燕, 胡克林, 彭希). Journal of China Agricultural University(中国农业大学学报), 2016, 21(8): 27.
[6] Kawamura K, Ikeura H, Phongchanmaixay S, et al. Remote Sensing, 2018, 10(8): 1249.
[7] FENG Wei，ZHU Yan，TIAN Yong-chao，et al（冯伟, 朱艳, 田永超，等）. Journal of Wheat Crops(麦类作物学报), 2007，(6): 1076.
[8] Bennett K P, Parrado-Hernández E. Journal of Machine Learning Research, 2006, 7: 1265.
[9] Liakos K G, Busato P, Moshou D. Sensors，2018，18(8): 2674.
[10] Bao Y, Mi C, Wu N, et al. Applied Sciences, 2019, 9(19): 4119.
[11] ZHANG Fu-suo, CUI Zhen-ling, WANG Ji-qing, et al（张福锁, 崔振岭, 王激清, 等）. Botanical Bulletin（植物学通报）, 2007，(6): 687.
[12] Curran P J, Dungan J L, Macler B A, et al. Remote Sensing of Environment, 1992, 39(2): 153.
[13] ZHAO Xiao-min, SUN Xiao-xiang, WANG Fang-dong, et al（赵小敏, 孙小香, 王芳东, 等）. Journal of Jiangxi Agricultural University（江西农业大学学报）, 2019, 41(1): 1.
[14] Davari M, Karimi S A, Bahrami H A, et al. CATENA, 2021, 197: 104987.
[15] dos Santos F R, de Oliveira J F, Bona E, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2021, 175: 106016.
[16] Assaf A G, Tsionas M, Tasiopoulos A. Tourism Management, 2019, 71: 1.
[17] DING Shi-fei, QI Bing-juan, TAN Hong-yan（丁世飞, 齐丙娟, 谭红艳）. Journal of the University of Electronic Science and Technology（电子科技大学学报）, 2011, 40(1): 2.