Science, Technology, Engineering and Mathematics.
Open Access


Download as PDF

Volume 1, Issue 2, Pp 19-27, 2023

DOI: 10.61784/ajes231208


Francesco Dumitru


Division of Catania, Italian National Institute for Nuclear Physics, Catania, Italy.

Corresponding Author

Francesco Dumitru


In recent years, UAV remote sensing technology has been widely used in the inversion of physical and chemical parameters of rice, and has gradually developed into the main way to obtain remote sensing information at the plot scale of rice fields. one of the paths. In-depth analysis of the current status and existence of inversion research on rice agronomic physical and chemical parameters (referring to parameters that can determine certain physical and chemical properties in the agricultural field) based on UAV remote sensing In the problem, it is helpful to better grasp the future development trend of rice drone remote sensing. Review of UAV remote sensing technology in retrieving biochemical component content, structural parameters, productivity, etc. The current research status of the research, in which the inversion research on the content of biochemical components mainly focuses on the direction of nitrogen and chlorophyll and is still dominated by data-driven methods, such as for inversion of nitrogen Narrow band vegetation index NDRE, inversion of rice chlorophyll content by coupling extreme learning machine and partial least squares regression, etc. , and the inversion method based on physical model Fewer; the inversion research of structural parameters mainly includes leaf area index, biomass, etc. , and the method includes the radiation transfer mechanism model used to invert the leaf area index. PROSAIL, used to reverse Optimized Gaussian process regression method based on canopy spectral characteristics for evolving biomass; remote sensing of productivity focuses on rice yield estimation, disease and lodging detection, and the method is useful for water Rice estimation utilization RGB Image usage K- Means Fusion with kernel correlation filtering algorithm. A summary of UAV remote sensing platforms, equipment, and methods was conducted, and nearly 10 year rice farmer Research progress and results of UAV remote sensing inversion of physical and chemical parameters. 


Rice; UAV; Remote sensing; Inversion; Spectrum


Francesco Dumitru. Current status and prospects of research on UAV remote sensing inversion of rice agronomic physical and chemical parameters. Academic Journal of Earth Sciences. 2023, 1(2): 19-27. DOI: 10.61784/ajes231208.


[1] Zhang Hongcheng, Hu Yajie, Yang Jianchang, etc. Development and Prospects of Rice Cultivation with Chinese Characteristics. Chinese Agricultural Sciences, 2021, 54(7) : 1301- 1321.

[2] FENG S, CAO Y L, XU T Y, et al. Rice leaf blast classification method based on fused features and one-dimensional deep convolutional neural network. Remote Sensing, 2021, 13(16):3207.

[3] Liu Tan, Xu Tongyu, Yu Fenghua, et al. based on PROSAIL Remote sensing estimation of rice chlorophyll content with model bias compensation. Journal of Agricultural Machinery, 2020, 51(5): 156- 164.

[4] SUN J, YANG J, SHI S, et al. Estimating rice leaf nitrogen concentration :Influence of regression algorithms based on passive and active leaf reflectance. Remote Sensing, 2017, 9(9):951.

[5] Liu Cong, Peng Yi, Fang Shenghui. Inversion of net photosynthetic rate of rice leaves based on hyperspectral data. Journal of China Agricultural University, 2020, 25(1):56-65.

[6] FRANCH B, BAUTISTA A S, FITA D, et al. Within-field rice yield estimation based on sentinel-2 satellite data. Remote Sensing, 2021, 13(20):4095.

[7] Zhang Yueqi, Li Rongping, Mu Xihan, et al. Based on multi-temporal GF -6 Extraction of rice planting area from remote sensing images. Journal of Agricultural Engineering, 2021, 37(17): 189- 196.

[8] NI R G, TIAN J Y, LI X J, et al. An enhanced pixel-based phenological feature for accurate paddy rice mapping with Senti ? nel-2 imagery in Google Earth Engine. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 178:282-296.

[9] XIA T, JI W W, LI W D, et al. Phenology-based decision tree classification of rice-crayfish fields from Sentinel-2 imagery in Qianjiang, China. International Journal of Remote Sensing, 2021, 42(21):8124-8144.

[10] ZHANG H D, WANG L Q, TIAN T, et al. A review of unmanned aerial vehicle low-altitude remote sensing (UAV-LARS) use in agricultural monitoring in China. Remote Sensing, 2021, 13(6): 1221.

[11] DELAVARPOUR N, KOPARAN C, NOWATZKI J, et al. A technical study on UAV characteristics for precision agriculture applications and associated practical challenges. Remote Sensing, 2021, 13(6): 1204.

[12] JANG G, KIM J, YU J K, et al. Review:Cost-effective unmanned aerial vehicle (UAV) platform for field plant breeding appli? cation. Remote Sensing, 2020, 12(6):998.

[13] Cao Yingli, Liu Yadi, Ma Dianrong, etc. Rice ear drone image segmentation method based on optimal subset selection. Journal of Agricultural Machinery, 2020, 51(8): 171- 177, 188.

[14] Tian Ting, Zhang Qing, Zhang Haidong, etc. Rice yield estimation based on UAV remote sensing. China Rice, 20 22, 28 (1):67-71, 77.

[15] WANG Y Y, ZHANG K, TANG C L, et al. Estimation of rice growth parameters based on linear mixed-effect model using multispectral images from fixed-wing unmanned aerial vehicles. Remote Sensing, 2019, 11(11): 1371.

[16] YANG Q, SHI L S, HAN J Y, et al. Deep convolutional neural networks for rice grain yield estimation at the ripening stage using UAV-based remotely sensed images. Field Crops Research, 2019, 235: 142- 153.

[17] ALVAREZ J, CARVAJAL A, SIERRA J, et al. In-flight and wireless damage detection in a UAV composite wing using fiber optic sensors and strain field pattern recognition. Mechanical Systems and Signal Processing, 2020, 136: 106526.

[18] Yang Pu, Zhao Yuanyang, Li Yiming, et al. A review of research on agricultural air-land integration based on multi-source information fusion. Journal of Agricultural Machinery, 2021, 52(Supplement 1): 185- 196.

[19] BARRERO O, PERDOMO S A. RGB and multispectral UAV image fusion for Gramineae weed detection in rice fields. Precision Agriculture, 2018, 19(5):809-822.

[20] Mu Taoyang, Zhao Wei, Hu Xiaoyu, et al. based on improved Rice lodging identification method using DeepLabV 3+ model combined with UAV remote sensing. Journal of China Agricultural University, 2022, 27 (2): 143- 154.

[21] YAMAGUCHI T, TANAKA Y, IMACHI Y, et al. Feasibility of combining deep learning and RGB images obtained by un ? manned aerial vehicle for leaf area index estimation in rice. Remote Sensing, 2020, 13(1):84.

[22] COLORADO J D, CERA N, CALDAS J S, et al. Estimation of nitrogen in rice crops from UAV-captured images. Remote Sensing, 2020, 12(20).

[23] Zhao Xiaoyang, Zhang Jian, Zhang Dongyan, et al. Comparative study on the effectiveness of visible light and multispectral sensors in the assessment of rice sheath blight disease under low-altitude remote sensing platform. Spectroscopy and Spectral Analysis, 2019, 39(4): 1192- 11 98.

[24] YANG Q, SHI L S, HAN J Y, et al. A VI-based phenology adaptation approach for rice crop monitoring using UAV multi ? spectral images. Field Crops Research, 2022, 277: 108419.

[25] GOSWAMI S, CHOUDHARY S S, CHATTERJEE C, et al. Estimation of nitrogen status and yield of rice crop using un ? manned aerial vehicle equipped with multispectral camera. Journal of Applied Remote Sensing, 2021, 15(4):042407.

[26] YU F H, FENG S, DU W, et al. A study of nitrogen deficiency inversion in rice leaves based on the hyperspectral reflec ? tance differential. Frontiers in Plant Science, 2020, 11:573272.

[27] Liu Youfu, Xiao Deqin, Liu Yalan, etc. Method for evaluating temperature characteristic variation of rice canopy thermal images induced by brown planthopper. Journal of Agricultural Machinery, 2020, 51(5): 165- 172.

[28] JIN H X, K?PPL C, FISCHER B, et al. Drone-based hyperspectral and thermal imagery for quantifying upland rice pro ? ductivity and water use efficiency after biochar application. Remote Sens, 2021, 13: 1866.

[29] Jiang Yun, Wang Jun, Chen Fangyuan. At the field scale in black soil area Extraction of crop planting areas from LiDAR point cloud data. Surveying and Mapping Engineering, 2020, 29(4):32-37, 43.

[30] LIU H L, ZHANG J S, PAN Y Z, et al. An efficient approach based on UAV orthographic imagery to map paddy with support of field-level canopy height from point cloud data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11:2034-2046.

[31] Gong Haiyan. Expanding the application of DJI industry - Interview with Wei Kunling, head of the surveying and mapping industry of Shenzhen DJI Innovation Technology Co. , Ltd. China Surveying and Mapping, 2021(1):60-63.

[32] Zhao Jing, Yan Chunyu, Yang Dongjian, et al. Extraction of corn lodging information after typhoon disaster based on UAV multispectral remote sensing. Journal of Agricultural Engineering, 2021, 37(24):56-64.

[33] Yu Fenghua, Zhao Dan, Guo Zhonghui, et al. Analysis and decomposition of mixed pixel characteristics of UAV hyperspectral images at the tillering stage of rice. Spectroscopy and Spectral Analysis, 2022, 42(3):94 7- 953.

[34] Zhang Hongming, Wang Jiajia, Han Wenting, et al. Extraction of crop canopy temperature based on thermal infrared remote sensing images. Journal of Agricultural Machinery, 2019, 50(4):203-210.

[35] Xu Zhiyang, Chen Qiao, Chen Yongfu. LiDAR UAV images assisted by single tree segmentation CNN + EL Tree species identification. Journal of Agricultural Machinery, 2022, 53(3): 197-205.

[36] Wang Xiaoke, Liu Tingting, Xu Guiling, etc. Hybrid rice vegetation index nitrogen nutrition diagnostic model based on canopy hyperspectral remote sensing. Chinese Rice, 2021, 27(3):21-29.

[37] ZHENG H B, MA J F, ZHOU M, et al. Enhancing the nitrogen signals of rice canopies across critical growth stages through the integration of textural and spectral information from unmanned aerial vehicle (UAV) multispectral imagery. Remote Sensing, 2020, 12(6):957.

[38] INOUE Y, SAKAIYA E, ZHU Y, et al. Diagnostic mapping of canopy nitrogen content in rice based on hyperspectral mea ? surements. Remote Sensing of Environment, 2012, 126:210-221.

[39] Yang Hongyun, Zhou Qiong, Yang Jun, et al. Research on nitrogen nutrition diagnosis of rice leaves based on hyperspectral. Journal of Zhejiang Agriculture, 2019, 31(10): 1575- 1582.

[40] DU W, XU T Y, YU F H, et al. Measurement of nitrogen content in rice by inversion of hyperspectral reflectance data from an unmanned aerial vehicle. Ciência Rural, 2018, 48(6).

[41] QIU Z C, MA F, LI Z W, et al. Estimation of nitrogen nutrition index in rice from UAV RGB images coupled with machine learning algorithms. Computers and Electronics in Agriculture, 2021, 189: 106421.

[42] GE H X, XIANG H T, MA F, et al. Estimating plant nitrogen concentration of rice through fusing vegetation indices and col ? or moments derived from UAV-RGB images. Remote Sensing, 2021, 13(9): 1620.

[43] Feng Shuai, Xu Tongyu, Yu Fenghua, et al. Research on the inversion method of nitrogen content of japonica rice canopy leaves in Northeast China based on UAV hyperspectral remote sensing. Spectroscopy and Spectral Analysis, 2019, 39(10):3281-3287.

[44] Zhang Yabiao, Luo Ju, Tang Jian, etc. Hyperspectral characteristics of different rice varieties and analysis of pigments and moisture content. Anhui Agricultural Sciences, 2015, 43(7):40-44. [45] Cao Yingli, Jiang Kailun, Liu Yadi, et al. Research on rice chlorophyll inversion based on hyperspectral red edge position extraction. Journal of Shenyang Agricultural University, 2021, 52(6):718-728.

[46] XU X, LU J, ZHANG N, et al. Inversion of rice canopy chlorophyll content and leaf area index based on coupling of radiative transfer and Bayesian network models. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150: 185- 196.

[47] LIU T, XU T Y, YU F H, et al. A method combining ELM and PLSR (ELM-P) for estimating chlorophyll content in rice with feature bands extracted by an improved ant colony optimization algorithm. Computers and Electronics in Agriculture, 2021, 186: 106177.

[48] Ban Songtao, Tian Minglu, Chang Qingrui, et al. Estimation of phosphorus content in rice leaves based on UAV hyperspectral images. Journal of Agricultural Machinery, 2021, 52(8): 163- 171.

[49] LU J S, EITEL J U H, ENGELS M, et al. Improving Unmanned Aerial Vehicle (UAV) remote sensing of rice plant potassium accumulation by fusing spectral and textural information. International Journal of Applied Earth Observation and Geoinformation, 2021, 104: 102592.

[50] GONG Y, YANG K L, LIN Z H, et al. Remote estimation of leaf area index (LAI) with unmanned aerial vehicle (UAV) imaging for different rice cultivars throughout the entire growing season. Plant Methods, 2021, 17(1):88.

[51] Hang Yanhong, Su Huan, Yu Ziyang, et al. Estimation of rice leaf area index based on UAV spectrum, texture characteristics and coverage. Journal of Agricultural Engineering, 2021, 37(9):64-71.

[52] LI W, CHEN S S, PENG Z P, et al. Phenology effects on physically based estimation of paddy rice canopy traits from UAV hyperspectral imagery. Remote Sensing, 2021, 13(9): 1792.

[53] ZHENG H B, CHENG T, ZHOU M, et al. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery. Precision Agriculture, 2019, 20(3):611-629.

[54] XU L, ZHOU L F, MENG R, et al. An improved approach to estimate ratoon rice aboveground biomass by integrating UAV- based spectral, textural and structural features. Precision Agriculture, 2022, 23(4): 1276- 1301.

[55] DAISUKE, OGAWA, TOSHIHIRO, et al. Surveillance of panicle positions by unmanned aerial vehicle to reveal morphological features of rice. . PloS One, 2019, 14(10):e0224386.

[56] LU W Y, OKAYAMA T, KOMATSUZAKI M. Rice height monitoring between different estimation models using UAV photo ? grammetry and multispectral technology. Remote Sensing, 2021, 14(1):78.

[57] Xu Tongyu, Hong Xue, Chen Chunling, et al. canopy based NDVI Research on northern japonica rice yield model based on data. Journal of Zhejiang Agriculture, 2016, 28(10): 17 90- 1795.

[58] Sui Lina, Fang Jian, Guo Lifeng. Application of UAV spectral analysis in rice yield prediction. Agricultural Mechanization Research, 2020, 42(8):35-40.

[59] PIPATSITEE P, EIUMNOH A, TISARUM R, et al al _ Above - ground vegetation indices and yield attributes self rice crop using un ? manned aerial vehicle combined with ground truth measurements. Notulae Botanicae Horticulture Agrobotany Cluj - Napoca, 2020, 48(4):2385–2398.

[60] Wang Feilong, Wang Fumin, Hu Jinghui, et al. UAV remote sensing rice yield estimation and yield mapping based on relative spectral variables. Remote Sensing Technology and Application, 2020, 35(2):458-468.

[61] DUAN B, FANG S H, GONG Y, et al. Remote estimation of grain yield based on UAV data in different rice cultivars under contrasting climatic zone. Field Crops Research, 2021, 267: 108148.

[62] REZA M N, NA I S, BAEK S W, et al. Rice yield estimation based on K-means clustering with graph-cut segmentation us ? ing lowaltitude UAV images. Biosystems Engineering, 2019, 177: 109- 121.

[63] WANG F M, YI Q X, HU J H, et al. Combining spectral and textural information in UAV hyperspectral images to estimate rice grain yield. International Journal of Applied Earth Observation and Geoinformation, 2021, 102.

[64] WANG J, WU B Z, KOHNEN M V, et al. Classification of rice yield using UAV-based hyperspectral imagery and lodging feature. Plant Phenomics (Washington, D C), 2021, 2021:9765952.

[65] HAYAT M A, WU J X, CAO Y L. Unsupervised Bayesian learning for rice panicle segmentation with UAV images. Plant Methods, 2020, 16: 18.

[66] OGAWA D, SAKAMOTO T, TSUNEMATSU H, et al. Haplotype analysis from unmanned aerial vehicle imagery of rice MAG ? IC population for the trait dissection of biomass and plant architecture. Journal of Experimental Botany, 2021, 72(7):2371- 2382.

[67] AN G Q, XING M F, HE B B, et al. Extraction of areas of rice false smut infection using UAV hyperspectral data. Remote Sensing, 2021, 13(16):3185.

[68] Xiao Wen, Cao Yingli, Feng Shuai, etc. Based on windowing Gram - Schmidt Transformation and PSO - SVR Algorithm-based detection of rice sheath blight disease index. Spectroscopy and Spectral Analysis, 2021, 41(7):2181-2187.

[69] Kong Fanchang, Liu Huanjun, Yu Ziyang, et al. UAV hyperspectral remote sensing identification of japonica rice panicle blast in alpine and cold areas. Journal of Agricultural Engineering, 2020, 36(22):68-75.

[70] YANG M D, BOUBIN J G, TSAI H P, et al. Adaptive autonomous UAV scouting for rice lodging assessment using edge computing with deep learning EDANet. Computers and Electronics in Agriculture, 2020, 179: 105817.

[71] TIAN M L, BAN S T, YUAN T, et al. Assessing rice lodging using UAV visible and multispectral image. International Journal of Remote Sensing, 2021, 42(23):8840-8857.

[72] LI S Y, DING X Z, KUANG Q L, et al. Potential of UAV-based active sensing for monitoring rice leaf nitrogen status. Frontiers in Plant Science, 2018, 9: 1834.

[73] FéRET J B, GITELSON A A, NOBLE S D, et al. PROSPECT-D:Towards modeling leaf optical properties through a complete lifecycle. Remote Sensing of Environment, 2017, 193:204-215.

[74] WAN L, ZHANG J F, XU Y, et al. PROSDM:Applicability of PROSPECT model coupled with spectral derivatives and similarity metrics to retrieve leaf biochemical traits from bidirectional reflectance. Remote Sensing of Environment, 2021, 267: 112761.

[75] FéRET J B, BERGER K, DE BOISSIEU F, et al. PROSPECT-PRO for estimating content of nitrogen-containing leaf proteins and other carbon-based constituents. Remote Sensing of Environment, 2021, 252: 112173.

[76] YU F H, XU T Y, DU W, et al. Radiative transfer models (RTMs) for field phenotyping inversion of rice based on UAV hyperspectral remote sensing. International Journal of Agricultural and Biological Engineering, 2017, 10(4): 150- 157.

[77] Zang Ying, Hou Xiaobo, Wang Pei, et al. Research on Huanghuazhan rice fertilization decision-making model based on UAV remote sensing technology. Journal of Shenyang Agricultural University, 2019, 5 0(3):324-330.

[78] Yu Fenghua, Cao Yingli, Xu Tongyu, et al. Precise fertilization by drone during the tillering stage of rice in cold areas based on hyperspectral remote sensing prescription maps. Journal of Agricultural Engineering, 2020, 36(15): 103- 110.

[79] Zhu Yan, Tang Liang, Liu Leilei, et al. Research progress of crop growth model (CropGrow). Chinese Agricultural Sciences, 2020, 53 (16):3235-3256.

[80] Cao Qiang, Tian Xingshuai, Ma Jifeng, et al. Research progress on critical nitrogen concentration dilution curves of China's three major grain crops. Journal of Nanjing Agricultural University, 2020, 43(3):392-402. 

All published work is licensed under a Creative Commons Attribution 4.0 International License. sitemap
Copyright © 2017 - 2024 Science, Technology, Engineering and Mathematics.   All Rights Reserved.