基于无人机多源影像融合的水稻籽粒蛋白质含量估测

doi:10.3864/j.issn.0578-1752.2026.01.004

中国农业科学 ›› 2026, Vol. 59 ›› Issue (1): 41-56.doi: 10.3864/j.issn.0578-1752.2026.01.004

• 耕作栽培·生理生化·农业信息技术 • 上一篇下一篇

基于无人机多源影像融合的水稻籽粒蛋白质含量估测

费耀莹¹(), 王迪², 唐伟杰³^,⁴, 郭彩丽¹, 张小虎¹, 邱小雷¹, 程涛¹, 姚霞¹^,⁴, 江冲亚¹, 朱艳¹, 曹卫星¹, 郑恒彪¹^,⁴^,^*()

¹ 南京农业大学农学院/国家信息农业工程技术中心/智慧农业教育部工程研究中心/农业农村部农作物系统分析与决策重点实验室/江苏省信息农业重点实验室，南京 210095
² 江苏徐淮地区淮阴农业科学研究所，江苏淮安 223001
³ 江苏省农业科学院种质资源与生物技术研究所，南京 210014
⁴ 生物育种钟山实验室，南京 210014

收稿日期:2025-06-12 接受日期:2025-10-22 出版日期:2026-01-07 发布日期:2026-01-07
通信作者:
郑恒彪，E-mail：zhenghb@njau.edu.cn
联系方式: 费耀莹，E-mail：faye09010618@163.com。
基金资助:
国家重点研发计划(2022YFD2001100); 钟山育种实验室项目(ZSBBL-KY2023-05); 江苏省青年科技人才托举工程(JSTJ-2024-429)

Estimation of Rice Grain Protein Content Using Fusion Imagery from UAV-based Multi-Sensors

FEI YaoYing¹(), WANG Di², TANG WeiJie³^,⁴, GUO CaiLi¹, ZHANG XiaoHu¹, QIU XiaoLei¹, CHENG Tao¹, YAO Xia¹^,⁴, JIANG ChongYa¹, ZHU Yan¹, CAO WeiXing¹, ZHENG HengBiao¹^,⁴^,^*()

¹ College of Agriculture, Nanjing Agricultural University/National Engineering and Technology Center for Information Agriculture/ Engineering Research Center of Smart Agriculture, Ministry of Education/Key Laboratory for Crop System Analysis and Decision Making, Ministry of Agriculture and Rural Affairs/Jiangsu Key Laboratory for Information Agriculture, Nanjing 210095
² Huaiyin Institute of Agricultural Sciences in Xuhuai Region of Jiangsu, Huaian 223001, Jiangsu
³ Institute of Germplasm Resources and Biotechnology, Jiangsu Academy of Agricultural Sciences, Nanjing 210014
⁴ Zhongshan Biological Breeding Laboratory, Nanjing 210014

Received:2025-06-12 Accepted:2025-10-22 Published:2026-01-07 Online:2026-01-07

摘要/Abstract

摘要：

【目的】水稻籽粒蛋白质含量（grain protein content，GPC）是衡量稻米品质和商品价值的重要指标。建立快速、无损的水稻GPC估测方法，旨在为作物智慧育种提供理论依据和技术支持。【方法】采用无人机搭载RGB相机和多光谱相机，于2022—2023年获取522份水稻育种材料抽穗-成熟期的RGB和多光谱影像及实测GPC数据。利用Gram-Schmidt图像融合方法对RGB和多光谱影像进行处理得到融合影像，并结合基于原始多光谱图像提取的光谱特征和纹理特征，采用随机森林（random forest，RF）、极限梯度提升机（extreme gradient boosting，XGBoost）、梯度提升回归（gradient boosting regression，GBR）3种机器学习回归算法构建GPC估测模型。【结果】RGB影像的红波段包含更丰富的图像信息，经过该波段融合后的植被指数与GPC的相关性均高于由原始多光谱影像计算的植被指数。均值纹理（Mean）在纹理指数构建中出现频率最高（占比63.16%），其中MEA₅₆₀-MEA₈₄₀指数与不同类型水稻的GPC具有一定的相关性（淮安常规粳稻：|r²|=0.28；如皋杂交粳稻：|r²|=0.20）。以多光谱图像特征、纹理特征和融合图像特征作为输入参数组合构建的水稻GPC估测模型，在抽穗期（R2 cal=0.64）和成熟期（R2 cal=0.70）的精度高于灌浆期模型（R2 cal=0.53）。相较于使用原始影像特征，结合融合影像特征提高了GPC的估测精度（ΔR2 cal=0.08-0.26）。RF构建的年际模型精度高于XGBoost和GBR模型（RF：R2 val=0.74，RMSE=0.21%；XGBoost：R2 val=0.58，RMSE=0.23%；GBR：R2 val=0.42，RMSE=0.23%）。【结论】结合无人机影像融合技术和机器学习方法能有效提高水稻育种材料GPC的估测精度，研究结果可为大规模水稻品质参数精准估算提供理论参考和有效途径。

关键词: 无人机, 多源影像, 特征融合, 机器学习, 水稻, 籽粒蛋白质含量, 无损估测

Abstract:

【Objective】Grain protein content (GPC) is a crucial indicator for evaluating rice quality and its commercial value. Establishing a rapid and non-destructive method for estimating rice GPC was established, so as to provide theoretical foundations and technical support for smart breeding and precision crop management. 【Method】This study employed a drone equipped with both an RGB camera and a multispectral camera to collect RGB and multispectral imagery, along with ground-measured grain protein content (GPC) data, from the heading to maturity stages of 522 rice breeding material accessions from 2022 to 2023. The Gram-Schmidt image fusion method was applied to process the RGB and multispectral images for generating fused images. Spectral and texture features extracted from the original multispectral images were combined with fused image features, and three machine learning regression algorithms—Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Regression (GBR)—were employed to construct GPC estimation models. 【Result】The R-band of the RGB images contained richer image information. Vegetation indices derived from the fused R-band exhibited higher correlations with GPC than those calculated from the original multispectral data. The mean texture (Mean) appeared most frequently in texture index construction (accounting for 63.16%), with the MEA₅₆₀-MEA₈₄₀ index showing certain correlations with GPC across different rice types (Huaian conventional japonica: |r²|=0.28; Rugao hybrid japonica: |r²|=0.20). Using a combination of multispectral image features, texture features, and fused image features as input parameters, the GPC estimation models for rice breeding materials achieved higher accuracy at the heading stage (R2 cal=0.64) and maturity stage (R2 cal=0.70) than at the filling stage model (R2 cal=0.53). Incorporating fused image features improved GPC estimation accuracy (ΔR2 cal=0.08-0.26) over using original image features. The interannual model of RF outperformed those of XGBoost and GBR in accuracy(RF: R2 val=0.74, RMSE=0.21%; XGBoost: R2 val=0.58, RMSE=0.23%; GBR: R2 val=0.42, RMSE=0.23%). 【Conclusion】The integration of UAV image fusion technique and machine learning methods could effectively enhance the estimation accuracy of the grain protein content (GPC) in rice breeding materials. These findings provided a theoretical reference and practical approaches for the precise estimation of rice quality parameters on a large scale.

Key words: unmanned aerial vehicle (UAV), multi-source imagery, feature fusion, machine learning, rice, grain protein content (GPC), non-destructive estimation

费耀莹, 王迪, 唐伟杰, 郭彩丽, 张小虎, 邱小雷, 程涛, 姚霞, 江冲亚, 朱艳, 曹卫星, 郑恒彪. 基于无人机多源影像融合的水稻籽粒蛋白质含量估测[J]. 中国农业科学, 2026, 59(1): 41-56.

FEI YaoYing, WANG Di, TANG WeiJie, GUO CaiLi, ZHANG XiaoHu, QIU XiaoLei, CHENG Tao, YAO Xia, JIANG ChongYa, ZHU Yan, CAO WeiXing, ZHENG HengBiao. Estimation of Rice Grain Protein Content Using Fusion Imagery from UAV-based Multi-Sensors[J]. Scientia Agricultura Sinica, 2026, 59(1): 41-56.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2026.01.004

https://www.chinaagrisci.com/CN/Y2026/V59/I1/41

图/表 17

图1

表1

表2

表3

本研究中所用的光谱参数"

光谱参数 Spectral parameter	名称 Name	公式 Formula	参考文献 Reference
NDRE	归一化差值红边指数 Normalized difference red-edge index	$\mathrm{NDRE}=\frac{\mathrm{R}_{840}-\mathrm{R}_{717}}{\mathrm{R}_{840}+\mathrm{R}_{717}}$	[22]
CI_rededge	红边叶绿素指数 Red-edge chlorophyll index	$\mathrm{CI}_{\text {rededge }}=\frac{\mathrm{R}_{840}}{\mathrm{R}_{717}}-1$	[23]
CI_green	绿度叶绿素指数 Green chlorophyll index	$\mathrm{CI}_{\text {green }}=\frac{\mathrm{R}_{717}}{\mathrm{R}_{560}}-1$	[23]
NDYI	归一化差值黄度指数 Normalized difference yellowness index	$\mathrm{NDYI}=\frac{\mathrm{R}_{560}-\mathrm{R}_{475}}{\mathrm{R}_{560}+\mathrm{R}_{475}}$	[24]
EVI2	增强型植被指数2 Enhanced vegetation index 2	$\mathrm{EVI} 2=\frac{2.5 \times\left(\mathrm{R}_{840}-\mathrm{R}_{717}\right)}{\mathrm{R}_{840}+6 \times \mathrm{R}_{668}-7.5 \times \mathrm{R}_{475}+1}$	[25]
MCARI	修正型叶绿素吸收反射指数 Modified chlorophyll absorption reflectance index	$M C A R I=\left[\left(R_{717}-R_{668}\right)-0.2 \times\left(R_{717}-R_{560}\right)\right] \times\left(\frac{R_{717}}{R_{668}}\right)$	[26]
SAVI	土壤调节植被指数 Soil adjusted vegetation index	$\mathrm{SAVI}=\frac{1.5 \times\left(\mathrm{R}_{840}-\mathrm{R}_{668}\right)}{\mathrm{R}_{840}+\mathrm{R}_{668}+0.5}$	[27]
DATT	达特指数 Datt vegetation index	$\mathrm{DATT}=\frac{\mathrm{R}_{840}-\mathrm{R}_{717}}{\mathrm{R}_{840}-\mathrm{R}_{668}}$	[28]
DVI	差值植被指数 Difference vegetation index	$\mathrm{DVI}=\mathrm{R}_{840}-\mathrm{R}_{668}$	[29]
GNDVI	绿度归一化差值植被指数 Green normalized difference vegetation index	$\text { GNDVI }=\frac{R_{840}-R_{560}}{R_{840}+R_{560}}$	[30]
OSAVI	优化型土壤调节植被指数 Optimized soil adjusted vegetation index	$\text { OSAVI }=\frac{R_{840}-R_{668}}{R_{840}+R_{668}+0.16}$	[31]
SIPI	结构不敏感色素指数 Structure-intensive pigment index	$\text { SIPI }=\frac{R_{840}-R_{475}}{R_{840}+R_{668}}$	[32]
SRPI	简单比值色素指数 Simple ratio pigment index	$\mathrm{SRPI}=\frac{\mathrm{R}_{475}}{\mathrm{R}_{668}}$	[32]

表3

表4

表5

图2

表6

图3

图4

图5

图6

表7

表8

图7

图8

图9

参考文献 45

[1]	FU Z P, YU S S, ZHANG J Y, XI H, GAO Y, LU R H, ZHENG H B, ZHU Y, CAO W X, LIU X J. Combining UAV multispectral imagery and ecological factors to estimate leaf nitrogen and grain protein content of wheat. European Journal of Agronomy, 2022, 132: 126405. doi: 10.1016/j.eja.2021.126405
[2]	FAN Y G, FENG H K, YUE J B, JIN X L, LIU Y, CHEN R Q, BIAN M B, MA Y P, SONG X Y, YANG G J. Using an optimized texture index to monitor the nitrogen content of potato plants over multiple growth stages. Computers and Electronics in Agriculture, 2023, 212: 108147. doi: 10.1016/j.compag.2023.108147
[3]	LI R, WANG D L, ZHU B, LIU T, SUN C M, ZHANG Z J. Estimation of nitrogen content in wheat using indices derived from RGB and thermal infrared imaging. Field Crops Research, 2022, 289: 108735. doi: 10.1016/j.fcr.2022.108735
[4]	王宇唯, 马旭, 谭穗妍, 贾兴娜, 陈嘉盈, 秦亦娟, 胡希红, 郑惠文. 无人机遥感与地面观测的多模态数据融合反演水稻氮含量. 农业工程学报, 2024, 40(18): 100-109.
	WANG Y W, MA X, TAN S Y, JIA X N, CHEN J Y, QIN Y J, HU X H, ZHENG H W. Inverting rice nitrogen content with multimodal data fusion of unmanned aerial vehicle remote sensing and ground observations. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(18): 100-109. (in Chinese)
[5]	LI W Y, WU W X, YU M L, TAO H Y, YAO X, CHENG T, ZHU Y, CAO W X, TIAN Y C. Monitoring rice grain protein accumulation dynamics based on UAV multispectral data. Field Crops Research, 2023, 294: 108858. doi: 10.1016/j.fcr.2023.108858
[6]	ZHANG M Z, CHEN T E, GU X H, KUAI Y, WANG C, CHEN D, ZHAO C J. UAV-borne hyperspectral estimation of nitrogen content in tobacco leaves based on ensemble learning methods. Computers and Electronics in Agriculture, 2023, 211: 108008. doi: 10.1016/j.compag.2023.108008
[7]	LONGMIRE A R, POBLETE T, HUNT J R, CHEN D, ZARCO-TEJADA P J. Assessment of crop traits retrieved from airborne hyperspectral and thermal remote sensing imagery to predict wheat grain protein content. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 193: 284-298. doi: 10.1016/j.isprsjprs.2022.09.015
[8]	LONGMIRE A, POBLETE T, HORNERO A, CHEN D, ZARCO- TEJADA P J. Estimation of grain protein content in commercial bread and durum wheat fields via traits inverted by radiative transfer modelling from Sentinel-2 timeseries. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 206: 49-62. doi: 10.1016/j.isprsjprs.2023.10.018
[9]	JAY S, GORRETTA N, MOREL J, MAUPAS F, BENDOULA R, RABATEL G, DUTARTRE D, COMAR A, BARET F. Estimating leaf chlorophyll content in sugar beet canopies using millimeter- to centimeter-scale reflectance imagery. Remote Sensing of Environment, 2017, 198: 173-186. doi: 10.1016/j.rse.2017.06.008
[10]	QIU Z C, MA F, LI Z W, XU X B, GE H X, DU C W. Estimation of nitrogen nutrition index in rice from UAV RGB images coupled with machine learning algorithms. Computers and Electronics in Agriculture, 2021, 189: 106421. doi: 10.1016/j.compag.2021.106421
[11]	TANAKA T S T, GISLUM R. Prediction of winter wheat nitrogen status using UAV imagery, weather data, and machine learning. European Journal of Agronomy, 2025, 164: 127534. doi: 10.1016/j.eja.2025.127534
[12]	ZHANG S H, DUAN J Z, QI X H, GAO Y Z, HE L, LIU L R, GUO T C, FENG W. Combining spectrum, thermal, and texture features using machine learning algorithms for wheat nitrogen nutrient index estimation and model transferability analysis. Computers and Electronics in Agriculture, 2024, 222: 109022. doi: 10.1016/j.compag.2024.109022
[13]	张良培, 沈焕锋. 遥感数据融合的进展与前瞻. 遥感学报, 2016, 20(5): 1050-1061.
	ZHANG L P, SHEN H F. Progress and future of remote sensing data fusion. National Remote Sensing Bulletin, 2016, 20(5): 1050-1061. (in Chinese) doi: 10.11834/jrs.20166243
[14]	XU S Z, XU X G, BLACKER C, GAULTON R, ZHU Q Z, YANG M, YANG G J, ZHANG J M, YANG Y A, YANG M, XUE H Y, YANG X D, CHEN L P. Estimation of leaf nitrogen content in rice using vegetation indices and feature variable optimization with information fusion of multiple-sensor images from UAV. Remote Sensing, 2023, 15(3): 854. doi: 10.3390/rs15030854
[15]	LI X W, SU X X, LI J, ANWAR S, ZHU X Q, MA Q, WANG W H, LIU J K. Coupling image-fusion techniques with machine learning to enhance dynamic monitoring of nitrogen content in winter wheat from UAV multi-source. Agriculture, 2024, 14(10): 1797. doi: 10.3390/agriculture14101797
[16]	YANG Q, SHI L S, HAN J Y, CHEN Z W, YU J. A VI-based phenology adaptation approach for rice crop monitoring using UAV multispectral images. Field Crops Research, 2022, 277: 108419. doi: 10.1016/j.fcr.2021.108419
[17]	刘吉凯, 王伟强, 苏祥祥, 李军, 年颖, 祝雪晴, 马强, 李新伟. 基于无人机多光谱影像和机器学习的水稻产量与氮素利用率预测. 农业工程学报, 2025, 41(20): 127-138.
	LIU J K, WANG W Q, SU X X, LI J, NIAN Y, ZHU X Q, MA Q, LI X W. Prediction of rice yield and nitrogen use efficiency based on UAV multispectral imaging and machine learning. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(20): 127-138. (in Chinese)
[18]	ZHENG H B, CHENG T, LI D, YAO X, TIAN Y C, CAO W X, ZHU Y. Combining unmanned aerial vehicle (UAV)-based multispectral imagery and ground-based hyperspectral data for plant nitrogen concentration estimation in rice. Frontiers in Plant Science, 2018, 9: 936. doi: 10.3389/fpls.2018.00936 pmid: 30034405
[19]	EUGENIO F C, GROHS M, SCHUH M, VENANCIO L P, SCHONS C, BADIN T L, MALLMANN C L, FERNANDES P, PEREIRA DA SILVA S D, FANTINEL R A. Estimated flooded rice grain yield and nitrogen content in leaves based on RPAS images and machine learning. Field Crops Research, 2023, 292: 108823. doi: 10.1016/j.fcr.2023.108823
[20]	KANG S Y, ZHANG Q L, WEI H R, SHI Y. An efficient multiscale integrated attention method combined with hyperspectral system to identify the quality of rice with different storage periods and humidity. Computers and Electronics in Agriculture, 2023, 213: 108259. doi: 10.1016/j.compag.2023.108259
[21]	WANG D L, LI R, LIU T, LIU S P, SUN C M, GUO W S. Combining vegetation, color, and texture indices with hyperspectral parameters using machine-learning methods to estimate nitrogen concentration in rice stems and leaves. Field Crops Research, 2023, 304: 109175. doi: 10.1016/j.fcr.2023.109175
[22]	FITZGERALD G, RODRIGUEZ D, O’LEARY G. Measuring and predicting canopy nitrogen nutrition in wheat using a spectral index: The canopy chlorophyll content index (CCCI). Field Crops Research, 2010, 116(3): 318-324. doi: 10.1016/j.fcr.2010.01.010
[23]	GITELSON A A, GRITZ Y, MERZLYAK M N. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. Journal of Plant Physiology, 2003, 160(3): 271-282. doi: 10.1078/0176-1617-00887 pmid: 12749084
[24]	SULIK J J, LONG D S. Spectral considerations for modeling yield of canola. Remote Sensing of Environment, 2016, 184: 161-174. doi: 10.1016/j.rse.2016.06.016
[25]	JIANG Z Y, HUETE A R, DIDAN K, MIURA T. Development of a two-band enhanced vegetation index without a blue band. Remote Sensing of Environment, 2008, 112(10): 3833-3845. doi: 10.1016/j.rse.2008.06.006
[26]	DAUGHTRY C S T, WALTHALL C L, KIM M S, DE COLSTOUN E B, MCMURTREY J E. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 2000, 74(2): 229-239. doi: 10.1016/S0034-4257(00)00113-9
[27]	HUETE A R. A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 1988, 25(3): 295-309. doi: 10.1016/0034-4257(88)90106-X
[28]	DATT B. A new reflectance index for remote sensing of chlorophyll content in higher plants: tests using Eucalyptus leaves. Journal of Plant Physiology, 1999, 154(1): 30-36. doi: 10.1016/S0176-1617(99)80314-9
[29]	RICHARDSONS A J, WIEGAND A. Distinguishing vegetation from soil background information. Photogrammetric Engineering and Remote Sensing, 1977, 43: 1541-1552.
[30]	GITELSON A, MERZLYAK M N. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. spectral features and relation to chlorophyll estimation. Journal of Plant Physiology, 1994, 143(3): 286-292. doi: 10.1016/S0176-1617(11)81633-0
[31]	STEVEN M D. The sensitivity of the OSAVI vegetation index to observational parameters. Remote Sensing of Environment, 1998, 63(1): 49-60. doi: 10.1016/S0034-4257(97)00114-4
[32]	PENUELAS J, FREDERIC B, FILELLA I. Semi-empirical indices to assess carotenoids/chlorophyll-a ratio from leaf spectral reflectance. Photosynthetica, 1995, 31: 221-230.
[33]	ZHENG H B, MA J F, ZHOU M, LI D, YAO X, CAO W X, ZHU Y, CHENG T. 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. doi: 10.3390/rs12060957
[34]	WAINER J, CAWLEY G. Nested cross-validation when selecting classifiers is over Zealous for most practical applications. Expert Systems with Applications, 2021, 182: 115222. doi: 10.1016/j.eswa.2021.115222
[35]	李树涛, 李聪妤, 康旭东. 多源遥感图像融合发展现状与未来展望. 遥感学报, 2021, 25(1): 148-166.
	LI S T, LI C Y, KANG X D. Development status and future prospects of multi-source remote sensing image fusion. National Remote Sensing Bulletin, 2021, 25(1): 148-166. (in Chinese) doi: 10.11834/jrs.20210259
[36]	HE J Y, ZHANG N, SU X, LU J S, YAO X, CHENG T, ZHU Y, CAO W X, TIAN Y C. Estimating leaf area index with a new vegetation index considering the influence of rice panicles. Remote Sensing, 2019, 11(15): 1809. doi: 10.3390/rs11151809
[37]	REN D Y, DING C Q, QIAN Q. Molecular bases of rice grain size and quality for optimized productivity. Science Bulletin, 2023, 68(3): 314-350. doi: 10.1016/j.scib.2023.01.026
[38]	SHENDRYK Y, SOFONIA J, GARRARD R, RIST Y, SKOCAJ D, THORBURN P. Fine-scale prediction of biomass and leaf nitrogen content in sugarcane using UAV LiDAR and multispectral imaging. International Journal of Applied Earth Observation and Geoinformation, 2020, 92: 102177. doi: 10.1016/j.jag.2020.102177
[39]	LI D L, SONG Z Y, QUAN C Q, XU X B, LIU C. Recent advances in image fusion technology in agriculture. Computers and Electronics in Agriculture, 2021, 191: 106491. doi: 10.1016/j.compag.2021.106491
[40]	刘骁驰, 黄向阳, 金明, 李思齐, 唐子竣, 向友珍, 李志军, 张富仓. 融合无人机多光谱与纹理特征解析开花期大豆叶片氮浓度的垂直分布. 农业工程学报, 2025, 41(14): 174-183.
	LIU X C, HUANG X Y, JIN M, LI S Q, TANG Z J, XIANG Y Z, LI Z J, ZHANG F C. Integrating UAV-derived multispectral and texture features for vertical distribution of nitrogen concentration in soybean leaves during flowering. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(14): 174-183. (in Chinese)
[41]	PULLANAGARI R R, DEHGHAN-SHOAR M, YULE I J, BHATIA N. Field spectroscopy of canopy nitrogen concentration in temperate grasslands using a convolutional neural network. Remote Sensing of Environment, 2021, 257: 112353. doi: 10.1016/j.rse.2021.112353
[42]	LI D, CHEN J M, YU W G, ZHENG H B, YAO X, CAO W X, WEI D D, XIAO C C, ZHU Y, CHENG T. Assessing a soil-removed semi-empirical model for estimating leaf chlorophyll content. Remote Sensing of Environment, 2022, 282: 113284. doi: 10.1016/j.rse.2022.113284
[43]	FAN Y G, FENG H K, LIU Y, FENG H, YUE J B, JIN X L, CHEN R Q, BIAN M B, MA Y P, YANG G J. Transferability of models for predicting potato plant nitrogen content from remote sensing data and environmental variables across years and regions. European Journal of Agronomy, 2024, 161: 127388. doi: 10.1016/j.eja.2024.127388
[44]	LI D, TIAN L, WAN Z F, JIA M, YAO X, TIAN Y C, ZHU Y, CAO W X, CHENG T. Assessment of unified models for estimating leaf chlorophyll content across directional-hemispherical reflectance and bidirectional reflectance spectra. Remote Sensing of Environment, 2019, 231: 111240. doi: 10.1016/j.rse.2019.111240
[45]	FÉRET J B, BERGER K, DE BOISSIEU F, MALENOVSKÝ Z. PROSPECT-PRO for estimating content of nitrogen-containing leaf proteins and other carbon-based constituents. Remote Sensing of Environment, 2021, 252: 112173. doi: 10.1016/j.rse.2020.112173

地点 Site	播种时间 Sowing time	品种 Variety	株行距 plant and row spacing	面积 Area (m²)	小区个数 Number of plots
如皋 Rugao	2022-05-15	常规粳稻 Conventional Japonica rice 杂交粳稻 Hybrid Japonica rice	20 cm×20 cm	3.60	240
如皋 Rugao	2023-05-10	常规粳稻 Conventional Japonica rice 杂交粳稻 Hybrid Japonica rice	20 cm×30 cm	5.20	240
淮安 Huaian	2023-05-10	常规粳稻 Conventional Japonica rice	20 cm×20 cm	10.75	297

相机 Camera	影像大小 Image size (pixel)	波段 Band	视场角 Field of view	飞行高度 Flight height (m)	像素大小 Pixel size (cm)	实物图 Product photo
禅思P1 DJI Zenmuse P1	8192×5460	R（620-750 nm）、G（500-570 nm）、B（450-495 nm）	38°×31°	30	0.38
RedEdge-MX	1280×960	475±20、560±20、668±10、717±40、840±10 nm	47.2°×20.9°	30	2.17

模型 Model	年份 Year	类型 Type	数据集描述 Dataset description	样本数量 Number
机器学习 Machine learning	2023	常规粳稻 Conventional Japonica Rice	训练集 Training set	105
		常规粳稻 Conventional Japonica Rice	验证集 Validation set	45
		杂交粳稻 Hybrid Japonica Rice	训练集 Training set	80
		杂交粳稻 Hybrid Japonica Rice	验证集 Validation set	34
交叉验证 Cross validation	2023	常规粳稻 Conventional Japonica Rice	训练集 Training set	103
		常规粳稻 Conventional Japonica Rice	验证集 Validation set	44
		杂交粳稻 Hybrid Japonica Rice	训练集 Training set	60
		杂交粳稻 Hybrid Japonica Rice	验证集 Validation set	26
年际验证 Inter-annual validation	2022	杂交粳稻 Hybrid Japonica Rice	训练集 Training set	200
年际验证 Inter-annual validation	2023	杂交粳稻 Hybrid Japonica Rice	验证集 Validation set	200

类型 Type	地点 Site	年份 Year	均值 Mean	最大值 Max	最小值 Min	中位数 Median	标准差 Standard deviation	变异系数 Coefficient of variation (%)
常规粳稻 Conventional Japonica rice	如皋 Rugao	2022	6.64	7.80	5.67	6.62	0.58	0.09
	淮安 Huaian	2023	7.11	8.02	6.07	7.14	0.47	0.07
	如皋 Rugao	2023	8.61	10.41	6.97	8.49	0.98	0.11
杂交粳稻 Hybrid Japonica rice	如皋 Rugao	2022	7.04	10.38	5.40	6.83	0.97	0.14
杂交粳稻 Hybrid Japonica rice	如皋 Rugao	2023	9.08	11.97	6.70	9.12	1.21	0.13

时期 Period	波段 Band	峰值信噪比 PSNR	结构相似性指数 SSIM	归一化均方根误差NRMSE	空间频率 SF	标准差 SD	平均梯度 AG
抽穗期 Heading	红 Red	12.09	0.70	0.26	32.06	31.39	18.36
抽穗期 Heading	绿 Green	8.44	0.59	0.39	15.04	14.43	8.42
灌浆初期 Early filling	红 Red	9.86	0.62	0.36	16.12	15.75	8.85
灌浆初期 Early filling	绿 Green	8.92	0.41	0.32	16.34	15.82	8.80
灌浆中期 Middle filling	红 Red	12.09	0.61	0.26	32.06	31.39	18.36
灌浆中期 Middle filling	绿 Green	9.73	0.49	0.33	13.01	12.84	7.29
成熟期 Maturity	红 Red	10.05	0.67	0.34	18.61	17.44	10.64
成熟期 Maturity	绿 Green	9.55	0.58	0.32	18.31	15.25	9.31

基于无人机多源影像融合的水稻籽粒蛋白质含量估测

Estimation of Rice Grain Protein Content Using Fusion Imagery from UAV-based Multi-Sensors

RichHTML

PDF

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 45

相关文章 15

Metrics

本文评价

推荐阅读 0

生育时期 Period	参数 Parameter	R²	RF		XGBoost		GBR
生育时期 Period	参数 Parameter	R²	淮安 Huaian	如皋 Rugao	淮安 Huaian	如皋 Rugao	淮安 Huaian	如皋 Rugao
抽穗开花期 Heading	植被指数、纹理指数 Vegetation index、Texture index	建模R2 cal Calibration R2 cal	0.54	0.49	0.55	0.68	0.48	0.34
	植被指数、纹理指数 Vegetation index、Texture index	验证R2 val Validation R2 val	0.29	0.39	0.54	0.67	0.38	0.08
	融合指数、纹理指数 Fusion index、Texture index	建模R2 cal Calibration R2 cal	0.56	0.78	0.64	0.64	0.63	0.60
	融合指数、纹理指数 Fusion index、Texture index	验证R2 val Validation R2 val	0.41	0.73	0.33	0.55	0.42	0.46
灌浆初期 Early filling	植被指数、纹理指数 Vegetation index、Texture index	建模R2 cal Calibration R2 cal	-	0.44	-	0.79	-	0.26
	植被指数、纹理指数 Vegetation index、Texture index	验证R2 val Validation R2 val	-	0.42	-	0.74	-	0.21
	融合指数、纹理指数 Fusion index、Texture index	建模R2 cal Calibration R2 cal	-	0.76	-	0.62	-	0.41
	融合指数、纹理指数 Fusion index、Texture index	验证R2 val Validation R2 val	-	0.74	-	0.58	-	0.40
灌浆中期 Middle filling	植被指数、纹理指数 Vegetation index、Texture index	建模R2 cal Calibration R2 cal	0.42	0.42	0.46	0.80	0.30	0.13
	植被指数、纹理指数 Vegetation index、Texture index	验证R2 val Validation R2 val	0.28	0.32	0.20	0.65	0.18	0.08
	融合指数、纹理指数 Fusion index、Texture index	建模R2 cal Calibration R2 cal	0.44	0.78	0.53	0.73	0.45	0.62
	融合指数、纹理指数 Fusion index、Texture index	验证R2 val Validation R2 val	0.33	0.74	0.37	0.66	0.31	0.49
成熟期 Maturity	植被指数、纹理指数 Vegetation index、Texture index	建模R2 cal Calibration R2 cal	0.31	0.47	0.32	0.75	0.30	0.42
	植被指数、纹理指数 Vegetation index、Texture index	验证R2 val Validation R2 val	0.26	0.44	0.28	0.72	0.23	0.14
	融合指数、纹理指数 Fusion index、Texture index	建模R2 cal Calibration R2 cal	0.46	0.76	0.70	0.62	0.48	0.53
	融合指数、纹理指数 Fusion index、Texture index	验证R2 val Validation R2 val	0.29	0.75	0.51	0.51	0.33	0.37

[1]	王忠妮, 雷月, 李佳丽, 宫彦龙, 朱速松. ABC转运蛋白OsARG1调控水稻抽穗期的功能[J]. 中国农业科学, 2026, 59(1): 1-16.
[2]	董桂春, 王子涵, 王树深, 李杰, 霍晓晴, 杨瑞, 周娟, 舒小伟, 李妍, 曹靓婧, 王子瑞, 姚友礼, 黄建晔. 硫包衣缓释肥提升水稻产量及氮肥利用率的技术途径[J]. 中国农业科学, 2026, 59(1): 57-77.
[3]	王爱冬, 李瑞杰, 冯向前, 洪卫源, 李子秋, 张晓果, 王丹英, 陈松. 基于多角度成像与机器学习的水稻叶面积精确估算[J]. 中国农业科学, 2025, 58(9): 1719-1734.
[4]	韦萍, 潘炬忠, 朱德平, 邵胜雪, 陈珊珊, 韦雅倩, 高维维. OsDREB1J调控水稻籽粒大小的功能研究[J]. 中国农业科学, 2025, 58(8): 1463-1478.
[5]	刘劲松, 伍龙梅, 包晓哲, 刘志霞, 张彬, 杨陶陶. 短期减施氮肥对华南地区早晚兼用型水稻产量和稻米品质的影响[J]. 中国农业科学, 2025, 58(8): 1508-1520.
[6]	王彬, 吴朋浩, 鲁剑巍, 任涛, 丛日环, 陆志峰, 李小坤. 长江中游地区水稻-油菜轮作体系需水特征[J]. 中国农业科学, 2025, 58(7): 1355-1365.
[7]	熊嘉妮, 李宗玥, 胡衡亮, 顾天宇, 高艳, 彭佳师. OsLCT1启动子驱动OsNRAMP5表达对镉向水稻种子迁移的影响[J]. 中国农业科学, 2025, 58(7): 1259-1268.
[8]	晋艺丹, 何旎清, 程朝平, 林少俊, 黄凤凰, 白康呈, 张涛, 汪文潇, 余敏祥, 杨德卫. 稻瘟病抗病蛋白Pigm-1互作蛋白的筛选与鉴定[J]. 中国农业科学, 2025, 58(6): 1043-1051.
[9]	靳亚茹, 陈斌, 王歆凯, 周田田, 李笑, 邓晶晶, 杨郁文, 郭冬姝, 张保龙. 利用基因编辑产生长片段缺失创制低谷蛋白水稻种质[J]. 中国农业科学, 2025, 58(6): 1052-1064.
[10]	徐元元, 贾东升, 宾羽, 魏太云. 黑尾叶蝉PGRP6负调控共生菌抑制水稻矮缩病毒的经卵传播[J]. 中国农业科学, 2025, 58(5): 907-917.
[11]	陈鸽, 谷雨, 文炯, 傅岳峰, 何兮, 李薇, 周峻宇, 刘琼峰, 吴海勇. 冬闲杂草还田对水稻光合物质生产和产量的影响[J]. 中国农业科学, 2025, 58(4): 647-659.
[12]	王少骅, 沈年桥, 储天然, 吴永汉, 李康宁, 石延霞, 谢学文, 李磊, 范腾飞, 李宝聚, 柴阿丽. 浙江苍南番茄-水稻轮作对连作土壤理化性质和微生物群落的影响[J]. 中国农业科学, 2025, 58(4): 692-703.
[13]	李璐, 谢庄, 谢可盈, 张瀚, 赵卓文, 向奥妮, 李巧龙, 凌英华, 何光华, 赵芳明. 水稻CSSL-Z492单、双片段代换系构建及粒型QTL的遗传解析[J]. 中国农业科学, 2025, 58(3): 401-415.
[14]	庄丽华, 罗磊, 赵春芳, 王纪忠, 张亚东, 赫磊. 水稻粒型突变体sgd13的鉴定及其基因定位[J]. 中国农业科学, 2025, 58(24): 5097-5109.
[15]	郭松, 韩磊, 汪源, 王子君, 钱紫慧, 路佳明, 赵灿, 王维领, 许轲, 张洪程, 杨凤萍, 霍中洋. 控释与速效氮肥不同配比一次性侧深施对水稻产量、氮肥利用率和碳减排的影响[J]. 中国农业科学, 2025, 58(24): 5216-5233.