数字农科院2.0

Time Series Field Estimation of Rice Canopy Height Using an Unmanned Aerial Vehicle-Based RGB/Multispectral Platform

文献类型： 外文期刊

作者： Ziqiu Li;Xiangqian Feng;Juan Li;Danying Wang;Weiyuan Hong;Jinhua Qin;Aidong Wang;Hengyu Ma;Qin Yao;Song Chen

作者机构：

关键词： digital surface model;rice canopy height estimation;two-stage linear regression;unmanned aerial vehicle;vegetation index

期刊名称： Agronomy

ISSN： 2073-4395

年卷期： 2024 年 14 卷 5 期

页码：

收录情况： SCIE（2024版）

摘要： Crop plant height is a critical parameter for assessing crop physiological properties, such as above-ground biomass and grain yield and crop health. Current dominant plant height estimation methods are based on digital surface model (DSM) and vegetation indexes (VIs). However, DSM-based methods usually estimate plant height by growth stages, which would result in some discontinuity between growth stages due to different fitting curves. Additionally, there has been limited research on the application of VI-based plant height estimation for multiple crop species. Thus, this study investigated the validity and challenges associated with these methods for estimating canopy heights of multi-variety rice throughout the entire growing season. A total of 474 rice varieties were cultivated in a single season, and RGB images including red, green, and blue bands, DSMs, multispectral images including near infrared and red edge bands, and manually measured plant heights were collected in 2022. DSMs and 26 commonly used VIs were employed to estimate rice canopy heights during the growing season. The plant height estimation using DSMs was performed using different quantiles (50th, 75th, and 95th), while two-stage linear regression (TLR) models based on each VI were developed. The DSM-based method at the 95th quantile showed high accuracy, with an R2 value of 0.94 and an RMSE value of 0.06 m. However, the plant height estimation at the early growth stage showed lower effectiveness, with an R2 < 0. For the VIs, height estimation with MTCI yielded the best results, with an R2 of 0.704. The first stage of the TLR model (maximum R2 = 0.664) was significantly better than the second stage (maximum R2 = 0.133), which indicated that the VIs were more suitable for estimating canopy height at the early growth stage. By grouping the 474 varieties into 15 clusters, the R2 values of the VI-based TLR models exhibited inconsistencies across clusters (maximum R2 = 0.984; minimum R2 = 0.042), which meant that the VIs were suitable for estimating canopy height in the cultivation of similar or specific rice varieties. However, the DSM-based method showed little difference in performance among the varieties, which meant that the DSM-based method was suitable for multi-variety rice breeding. But for specific clusters, the VI-based methods were better than the DSM-based methods for plant height estimation. In conclusion, the DSM-based method at the 95th quantile was suitable for plant height estimation in the multi-variety rice breeding process, and we recommend using DSMs for plant height estimation after 26 DAT. Furthermore, the MTCI-based TLR model was suitable for plant height estimation in monoculture planting or as a correction for DSM-based plant height estimation in the pre-growth period of rice.

分类号：

  • 相关文献

[1]Inversion of Crop Water Content Using Multispectral Data and Machine Learning Algorithms in the North China Plain. Zhenghao Zhang,Gensheng Dou,Xin Zhao,Yang Gao,Saisai Liu,Anzhen Qin. 2024

[2]Effects of vegetation indices to the spatial changes of desert environment using EOS/MODIS data: A case study to Sangong inland arid ecosystem. Lu, Liping,Qin, Zhihao,Qin, Zhihao,Gao, Maofang,Zhao, Chengyi,Li, Wenjuan. 2006

[3]Comparison of two methods for monitoring leaf total chlorophyll content (LTCC) of wheat using field spectrometer data. Jin, X.,Wang, K.,Li, S.,Jin, X.,Diao, W.,Xiao, C.,Wang, K.,Li, S.,Wang, F.,Chen, B..

[4]Estimation of crop LAI using hyperspectral vegetation indices and a hybrid inversion method. Liang, Liang,Zhang, Lianpeng,Lin, Hui,Liang, Liang,Zhao, Shuhe,Liang, Liang,Di, Liping,Deng, Meixia,Qin, Zhihao.

[5]Remote sensing of crop production in China by production efficiency models: models comparisons, estimates and uncertainties. Tao, FL,Yokozawa, M,Zhang, Z,Xu, YL,Hayashi, Y.

[6]New fast detection method of forest fire monitoring and application based on FY-1D/MVISR data. Feng, Jianzhong,Tang, Huajun,Zhou, Qingbo,Chen, Zhongxin,Bai, Linyan,Feng, Jianzhong. 2008

[7]Spectral Reflectance and Vegetation Index Changes in Deciduous Forest Foliage Following Tree Removal: Potential for Deforestation Monitoring. Peng, D.,Hu, Y.,Li, Z..

[8]Comparison of vegetation indices and red-edge parameters for estimating grassland cover from canopy reflectance data. Liu, Zhan-Yu,Huang, Jing-Feng,Wu, Xin-Hong,Dong, Yong-Ping. 2007

[9]Remote sensing monitoring of wheat leaf rust based on UAV multispectral imagery and the BPNN method. Ju, Chengxin,Chen, Chen,Li, Rui,Zhao, Yuanyuan,Zhong, Xiaochun,Sun, Ruilin,Liu, Tao,Sun, Chengming. 2023

[10]Replacing The Red Band With T.he Red-Swir Band (0.74(Red)+0.26(Swir)) C an Reduce The Sensitivity Of Vegetation Indices To Soil Background. Chen, XH, Guo, ZF, Chen, J, Yang, W, Yao, YM, Zhang, CS, Cui, XH, Cao, X. 2019

[11]Monitoring the Rice Panicle Blast Control Period Based on UAV Multispectral Remote Sensing and Machine Learning. Bin Ma,Guangqiao Cao,Chaozhong Hu,Cong Chen. 2023

[12]Estimating wheat fractional vegetation cover using a density peak k-means algorithm based on hyperspectral image data. Da zhong LIU,Fei fei YANG,Sheng ping LIU. 2021

[13]The superiority of the normalized difference phenology index (NDPI) for estimating grassland aboveground fresh biomass. Dawei Xu,Cong Wang,Jin Chen,Miaogen Shen,Beibei Shen,Ruirui Yan,Zhenwang Li,Arnon Karnieli,Jiquan Chen,Yuchun Yan,Xu Wang,Baorui Chen,Dameng Yin,Xiaoping Xin. 2021

[14]The superiority of the normalized difference phenology index (NDPI) for estimating grassland aboveground fresh biomass. Dawei Xu,Cong Wang,Jin Chen,Miaogen Shen,Beibei Shen,Ruirui Yan,Zhenwang Li,Arnon Karnieli,Jiquan Chen,Yuchun Yan,Xu Wang,Baorui Chen,Dameng Yin,Xiaoping Xin. 2021

[15]Quantifying effect of tassels on near-ground maize canopy RGB images using deep learning segmentation algorithm. Shao, Mingchao,Nie, Chenwei,Cheng, Minghan,Yu, Xun,Bai, Yi,Ming, Bo,Song, Hongli,Jin, Xiuliang. 2021

[16]The spatiotemporal change of cropland and its impact on vegetation dynamics in the farming-pastoral ecotone of northern China. Deji Wuyun,Liang Sun,Zhongxin Chen,Anhong Hou,Luís Guilherme Teixeira Crusiol,Lifeng Yu,Ruiqing Chen,Zheng Sun. 2022

[17]Combining novel feature selection strategy and hyperspectral vegetation indices to predict crop yield. Fei S.,Li L.,Han Z.,Chen Z.,Xiao Y.. 2022

[18]Applications of a Hyperspectral Imaging System Used to Estimate Wheat Grain Protein: A Review. Junjie Ma,Bangyou Zheng,Yong He. 2022

[19]A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles. Yuefeng Lu,Zhenqi Song,Yuqing Li,Zhichao An,Lan Zhao,Guosheng Zan,Miao Lu. 2023

[20]Water Chlorophyll a Estimation Using UAV-Based Multispectral Data and Machine Learning. Zhao X.,Li Y.,Chen Y.,Qiao X.,Qian W.. 2023

作者其他论文 更多>>