Preliminary Study on the Intertemporal Predictability of the Physiological Index of Early Rice Based on Hyperspectral
ZHU Hai-jun1, FU Hong-yu1, 2, WANG Xue-hua1*, CUI Guo-xian1, 2*，SHI Ai-long1, XUE Wei-chun3
1. Agronomy College, Hunan Agricultural University, Changsha 410128, China
2. Ramie Research Institute, Hunan Agricultural University, Changsha 410128, China
3. Agriculture and Rural Bureau of Heshan District, Yiyang 413000, China
Abstract：Chlorophyll and leaf nitrogen content (LNC) are important indicators of crop growth. Real-time and accurate monitoring of Chlorophyll and LNC is helpful for field management and improvement of crop quality and yield. Currently, hyperspectral technology and empirical regression methods are widely used to construct crop biochemical parameter prediction models. However, there are still gaps in the research on predicting leaf biochemical parameters across periods. In this study, 120 leaf hyperspectral data, chlorophyll and LNC were obtained at five stages of early rice. Three different algorithms, namely, Partial Least Squares Regression (PLSR), Random Forest (RF), and Support Vector Regression (SVR) were used to establish inter-temporal prediction models for Chlorophyll and LNC in different growth stages. In addition, the intertemporal prediction model and the traditional non-intertemporal prediction model were evaluated. The results showed that the early rice chlorophyll inter-temporal prediction SVR model had the best prediction effect, with the inter-tillering prediction model having R2 of 0.54, the inter-booting prediction model has R2 of 0.36, the inter-heading prediction model has R2 of 0.30, inter-grouting prediction model has R2 of 0.55, and inter-mature prediction model has R2 of 0.74. The intertemporal prediction model of early rice leaf LNC was poor, and the LNC cannot be intertemporally predicted. Compared with the non-intertemporal prediction model, although the accuracy of the intertemporal prediction model has decreased, it can effectively overcome the shortcomings of poor universality of the empirical model, which is beneficial to realize the physiological characteristics of different growth stages of crops in the same life cycle. At the same time, we found that crop physiological indicators have inter-temporal predictability. This concept provides new ideas for the prediction of crop phenotype, internal crop quality and yield.
Key words：Hyperspectral; Early rice; Leaf nitrogen content; Chlorophyll; Intertemporal prediction
祝海竣，付虹雨，王学华，崔国贤，石爱龙，薛卫纯. 高光谱早稻生理指标可跨期预测性的初步研究[J]. 光谱学与光谱分析, 2022, 42(01): 170-175.
ZHU Hai-jun, FU Hong-yu, WANG Xue-hua, CUI Guo-xian，SHI Ai-long, XUE Wei-chun. Preliminary Study on the Intertemporal Predictability of the Physiological Index of Early Rice Based on Hyperspectral. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 170-175.
[1] Yao X, Huang Y, Shang G, et al. Remote Sensing，2015, 7：14939.
[2] LIN Yi, LIU Si-yuan, YAN Lei, et al(林 沂, 刘思远, 晏 磊, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(6): 1956.
[3] Hu H, Bai Y L, Yang L P, et al. Plant Nutrition and Fertilizer Science, 2009, 15(6): 1317.
[4] Zhang Manyin, Li Mengjie, Liu Weiwei, et al. Spectroscopy Letters, 2019, 52(9): 483.
[5] Qiu Shanshan, Wang Jun, Gao Liping. Journal of Agricultural and Food Chemistry, 2014, 62(27): 6426.
[6] ZHANG Yin-jie, WANG Lei, BAI You-lu, et al(张银杰, 王 磊, 白由路, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(9): 2829.
[7] Li Zhenhai, Jin Xiuliang, Yang guijun, et al. Remote Sensing, 2018, 10(9): 1.
[8] YANG Fu-qin, FENG Hai-kuan, LI Zhen-hai, et al(杨福芹, 冯海宽, 李振海, 等). Journal of Shanxi Agricultural University·Nature Science Edition(山西农业大学学报·自然科学版), 2020, 40(5): 99.
[9] Katherine Meacham-Hensold, Christopher M Montes, Jin Wu, et al. Remote Sensing of Environment, 2019, 231: 111176.
[10] LIANG Xue-ying, FAN Feng-lei(梁雪映, 樊风雷). Journal of Agricultural Science and Technology(中国农业科技导报), 2019, 21(1): 51.
[11] Ghasemi J B, Tavakoli H. Analytical Methods, 2013, 5: 1863.
[12] Shao Y, Zhao C, Bao Y, et al. Food & Bioprocess Technology, 2012, 5(1): 100.
[13] Yang J, Du L, Gong W, et al. PLOS ONE, 2018, 13(1), 1.
