Estimation of alfalfa yields on the basis of unmanned aerial vehicle multi-spectral and red-green-blue images

doi:10.11686/cyxb2024045

Abstract

Abstract:

Yield is a key component of the economic output of alfalfa （Medicago sativa） pasture. Timely and accurate quantification of alfalfa yield is useful to improve nutrient management and optimize planting patterns. The traditional method to estimate yield in pasture relies on destructive sampling， and there is a certain time lag in obtaining the results. In contrast， unmanned aerial vehicle （UAV）-based monitoring technologies can quickly obtain information to model yield in a non-destructive manner. However， the spectral and spatial resolutions cannot be balanced based on image information from a single sensor， so a comprehensive analysis of crop growth is impossible. It is difficult to effectively improve the accuracy of estimates based on a single UAV image. Therefore， the aim of this study was to explore the potential to combine multi-source image information from UAVs to estimate alfalfa yield during harvesting. In this study， red-green-blue （RGB） and multispectral （MS） images were collected during the alfalfa harvesting period. Based on spectral， texture， and wavelet features extracted from the RGB and MS images， two machine learning algorithms involving partial least squares （PLSR） and Gaussian process regression （GPR） algorithms were used to evaluate the robustness of the alfalfa yield estimation model. The results show that the wavelet features of RGB images were more effective for the comparison of color index and texture features. The combination of the two types of features improved the accuracy of alfalfa yield estimates to some degree. The GPR alfalfa yield estimation model combining three types of features （color index， texture， and wavelet） had high accuracy （training set coefficient of determination R²=0.76， validation set coefficient of determination R²=0.63， and RPD=1.61）. For MS images， the model built based on texture features was the most accurate （training set coefficient of determination R²=0.76， validation set coefficient of determination R²=0.63， and the ratio of prediction to deviation RPD=1.61）. The alfalfa yield estimation model based on texture features was slightly better than that based on spectral index features， and the GPR alfalfa yield estimation model constructed by combining the two types of features was very accurate （training set coefficient of determination R²=0.83， validation set coefficient of determination R²=0.58， and RPD=1.55）. The accuracy of the alfalfa yield estimation model was significantly improved when the RGB image and MS image features were fused. Particularly， the GPR model with three kinds of feature parameters （multi-spectral index， multi-spectral texture， RGB wavelet feature） was the most accurate in estimating alfalfa yield （coefficient of determination R²=0.83 in the training set， coefficient of determination R²=0.75 in the validation set， and RPD=1.98）. In conclusion， the GPR algorithm provided the best estimation results， and the estimation accuracy was improved by 13.6% compared with that of the PLSR model. These results provide a reference for remotely monitoring artificial grassland and estimating yield in the future.

Key words: alfalfa, drone image, yield, vegetation index, textural features, wavelet characteristic, feature fusion

Yu-fei BAI, Hang YIN, Hai-bo YANG, Zhen-hua FENG, Fei LI. Estimation of alfalfa yields on the basis of unmanned aerial vehicle multi-spectral and red-green-blue images[J]. Acta Prataculturae Sinica, 2024, 33(12): 45-58.

Figures/Tables 9

Fig.1 Summary of the test area

Table 1 RGB index selection and multi-spectral band optimization formula

项目Item	指数 Index	公式 Formula	文献 Reference
CI	r	R/（R+G+B）	［25］
	g	G/（R+G+B）
	b	B/（R+G+B）
	蓝/绿色素指数Blue/green pigment index （BGI）	b/g
	蓝/红色素指数Blue/red pigment index （BRI）	b/r
	绿/红色素指数green/red pigment index （GRI）	g/r
	超绿指数Excess green index （ExG）	2g-r-b
	绿红植被指数Green red vegetation index （GRVI）	（g-r）/（g+r）	［26］
	可见大气阻力指数Visible atmospherically resistant index （VARI）	（g-r）/（g+r-b）	［27］
	修正绿红植被指数Modified green red vegetation index （MGRVI）	（g²-r²）/（g²+r²）	［12］
	红绿蓝植被指数Red-green-blue vegetation index （RGBVI）	（g²-rb）/（g²+rb）
	三角形绿色指数Triangular greenness index （TGI）	-0.5［190（r-g）-120（r-b）］	［28］
SI	差值植被指数Different vegetation index （DVI）	$N I R - R E$	［26］
	比率植被指数Ratio vegetation index （RVI）	$N I R / R$	［29］
	归一化植被指数Normalized difference vegetation index （NDVI）	$(N I R - R) / (N I R + R)$
	红边叶绿素指数Red edge chlorophyll index （CIred-edge）	$(N I R - R) / N I R$	［30］
	三波段比率光谱指数Three-band ratio spectral index （TRSI）	$N I R / (R × R E)$	［31］
	蓝氮指数1 Blue nitrogen index 1 （BNI1）	$N I R / (R + R E)$	［32］
	蓝氮指数2 Blue nitrogen index 2 （BNI2）	$(N I R + R) / R E$
	植被衰减指数Plant senescence reflectance index （PSRI）	$(N I R - R E) / R$	［30］
	陆地叶绿素指数The MERIS terrestrial chlorophyll index （MTCI）	$(N I R - R E) / (R E - G)$	［33］
	修正红边比率Modified red-edge ratio （mSR705）	$(N I R - G) / (R E - G)$	［34］
	修正红边归一化差异植被指数Modified red-edge normalized difference vegetatio index （mND705）	$(R E - N I R) / [(R E + N I R) - 2 G]$
	双峰氮指数Double-peak nitrogen index （NDDA）	$(G + R E - 2 N I R) / (G - R E)$	［35］
	修正叶绿素吸收反射指数Modified chlorophyll absorption reflectance index （MCARI）	$(R - R E)$ -0.2（ $R - G) × R / R E$	［36］
	优化土壤调节植被指数Optimized soil-adjusted vegetation index （OSAVI）	$1.16 (N I R - R) / (N I R + R) + 0.16$	［37］
	修正的归一化差分植被指数Modified normalized difference vegetation index （nNDVIblue）	$(R - N I R + 2 G) / (R + N I R - 2 G)$	［38］
	转换叶绿素吸收反射指数Transformed chlorophyll absorption reflectance index （TCARI）	$3 (N I R - R) - 0.2 (N I R - R E) × (N I R / R)$	［39］
	冠层叶绿素反演指数Canopy chlorophyll inversion index （TCARI/OSAVI）
	氮平面域指数Nitrogen planar domain index （CIred-edge/NDVI）		［40］
	MCARI/OSAVI		［41］

Table 1 RGB index selection and multi-spectral band optimization formula

项目Item	指数 Index	公式 Formula	文献 Reference
CI	r	R/（R+G+B）	［25］
	g	G/（R+G+B）
	b	B/（R+G+B）
	蓝/绿色素指数Blue/green pigment index （BGI）	b/g
	蓝/红色素指数Blue/red pigment index （BRI）	b/r
	绿/红色素指数green/red pigment index （GRI）	g/r
	超绿指数Excess green index （ExG）	2g-r-b
	绿红植被指数Green red vegetation index （GRVI）	（g-r）/（g+r）	［26］
	可见大气阻力指数Visible atmospherically resistant index （VARI）	（g-r）/（g+r-b）	［27］
	修正绿红植被指数Modified green red vegetation index （MGRVI）	（g²-r²）/（g²+r²）	［12］
	红绿蓝植被指数Red-green-blue vegetation index （RGBVI）	（g²-rb）/（g²+rb）
	三角形绿色指数Triangular greenness index （TGI）	-0.5［190（r-g）-120（r-b）］	［28］
SI	差值植被指数Different vegetation index （DVI）	$N I R - R E$	［26］
	比率植被指数Ratio vegetation index （RVI）	$N I R / R$	［29］
	归一化植被指数Normalized difference vegetation index （NDVI）	$(N I R - R) / (N I R + R)$
	红边叶绿素指数Red edge chlorophyll index （CIred-edge）	$(N I R - R) / N I R$	［30］
	三波段比率光谱指数Three-band ratio spectral index （TRSI）	$N I R / (R × R E)$	［31］
	蓝氮指数1 Blue nitrogen index 1 （BNI1）	$N I R / (R + R E)$	［32］
	蓝氮指数2 Blue nitrogen index 2 （BNI2）	$(N I R + R) / R E$
	植被衰减指数Plant senescence reflectance index （PSRI）	$(N I R - R E) / R$	［30］
	陆地叶绿素指数The MERIS terrestrial chlorophyll index （MTCI）	$(N I R - R E) / (R E - G)$	［33］
	修正红边比率Modified red-edge ratio （mSR705）	$(N I R - G) / (R E - G)$	［34］
	修正红边归一化差异植被指数Modified red-edge normalized difference vegetatio index （mND705）	$(R E - N I R) / [(R E + N I R) - 2 G]$
	双峰氮指数Double-peak nitrogen index （NDDA）	$(G + R E - 2 N I R) / (G - R E)$	［35］
	修正叶绿素吸收反射指数Modified chlorophyll absorption reflectance index （MCARI）	$(R - R E)$ -0.2（ $R - G) × R / R E$	［36］
	优化土壤调节植被指数Optimized soil-adjusted vegetation index （OSAVI）	$1.16 (N I R - R) / (N I R + R) + 0.16$	［37］
	修正的归一化差分植被指数Modified normalized difference vegetation index （nNDVIblue）	$(R - N I R + 2 G) / (R + N I R - 2 G)$	［38］
	转换叶绿素吸收反射指数Transformed chlorophyll absorption reflectance index （TCARI）	$3 (N I R - R) - 0.2 (N I R - R E) × (N I R / R)$	［39］
	冠层叶绿素反演指数Canopy chlorophyll inversion index （TCARI/OSAVI）
	氮平面域指数Nitrogen planar domain index （CIred-edge/NDVI）		［40］
	MCARI/OSAVI		［41］

Table 2 Eight texture indices were extracted from the image

纹理特征Textural features	公式Formula
均值Mean	$μ = 1 N ∑ i = 1 N x i $$
方差Variance （var）	$σ 2 = 1 N ∑ i = 1 N (x i - μ) 2 $$
同质性Homogenetity （hom）	$h o m = ∑ i = 1 N ∑ j = 1 N 1 1 + (i - j) 2 M i, j $$
对比度Contrast （con）	$c o n = ∑ i = 1 N ∑ j = 1 N (i - j) 2 M i, j $$
差异性Dissimilarity （dis）	$d i s = ∑ i ∑ j N (i, j) \| i - j \|$
熵Entropy （ent）	$e n t = - ∑ i = 1 N ∑ j = 1 N M i, j l o g 2 M i, j $$
二阶距Second moment （sm）	$s m = ∑ i = 1 N ∑ j = 1 N i - μ 2 M i, j $$
相关性 Correlation （cor）	$c o r = ∑ i = 1 N ∑ j = 1 N i - μ j - μ M i, j ∑ i = 1 N ∑ j = 1 N i - μ 2 M i, j ∑ i = 1 N ∑ j = 1 N j - μ 2 M i, j$

Table 2 Eight texture indices were extracted from the image

纹理特征Textural features	公式Formula
均值Mean	$μ = 1 N ∑ i = 1 N x i $$
方差Variance （var）	$σ 2 = 1 N ∑ i = 1 N (x i - μ) 2 $$
同质性Homogenetity （hom）	$h o m = ∑ i = 1 N ∑ j = 1 N 1 1 + (i - j) 2 M i, j $$
对比度Contrast （con）	$c o n = ∑ i = 1 N ∑ j = 1 N (i - j) 2 M i, j $$
差异性Dissimilarity （dis）	$d i s = ∑ i ∑ j N (i, j) \| i - j \|$
熵Entropy （ent）	$e n t = - ∑ i = 1 N ∑ j = 1 N M i, j l o g 2 M i, j $$
二阶距Second moment （sm）	$s m = ∑ i = 1 N ∑ j = 1 N i - μ 2 M i, j $$
相关性 Correlation （cor）	$c o r = ∑ i = 1 N ∑ j = 1 N i - μ j - μ M i, j ∑ i = 1 N ∑ j = 1 N i - μ 2 M i, j ∑ i = 1 N ∑ j = 1 N j - μ 2 M i, j$

Fig.2 Low frequency information extraction by wavelet transform under two scales

Table 3 RGB sensor feature combination modeling estimation

变量 Variable	特征数量 Feature quantity	偏最小二乘回归PLSR			高斯回归GPR
变量 Variable	特征数量 Feature quantity	Cali-R²	Vali-R²	Vali-RPD	Cali-R²	Vali-R²	Vali-RPD
CI	10	0.39	0.45	1.36	0.31	0.15	1.08
TF_RGB	22	0.53	0.52	1.45	0.75	0.19	1.13
WF_RGB	17	0.63	0.60	1.57	0.64	0.66	1.72
CI+TF_RGB	29	0.61	0.55	1.46	0.86	0.36	1.26
CI+WF_RGB	25	0.66	0.55	1.41	0.72	0.63	1.65
TF_RGB+WF_RGB	37	0.67	0.57	1.22	0.88	0.52	1.41
CI+TF_RGB+WF_RGB	52	0.69	0.65	1.54	0.76	0.63	1.61

Fig.3 Two algorithms estimate for different feature combinations

Table 4 Multi-spectral sensor feature combination modeling and estimation

变量 Variable	特征数量 Feature quantity	偏最小二乘回归Partial least squares regression			高斯回归Gaussian process regression
变量 Variable	特征数量 Feature quantity	Cali-R²	Vali-R²	Vali-RPD	Cali-R²	Vali-R²	Vali-RPD
SI	20	0.43	0.49	1.42	0.58	0.46	1.37
TF_MS	25	0.49	0.55	1.52	0.57	0.56	1.50
SI+TF_MS	29	0.48	0.44	1.35	0.83	0.58	1.55

Table 5 RGB+MS sensor feature combination modeling estimation

变量 Variable	特征数量 Feature quantity	偏最小二乘回归PLSR			高斯回归GPR
变量 Variable	特征数量 Feature quantity	Cali-R²	Vali-R²	Vali-RPD	Cali-R²	Vali-R²	Vali-RPD
SI+WF_RGB	16	0.59	0.55	1.49	0.89	0.61	1.62
SI+TF_RGB	24	0.52	0.46	1.37	0.77	0.42	1.32
TF_MS+CI	23	0.56	0.56	1.52	0.69	0.60	1.57
TF_MS+WF_RGB	28	0.53	0.53	1.47	0.85	0.71	1.85
CI+TF_MS+WF_RGB	43	0.64	0.63	1.64	0.82	0.73	1.80
SI+TF_RGB+WF_RGB	57	0.67	0.66	1.51	0.80	0.66	1.67
SI+TF_MS+WF_RGB	61	0.66	0.62	1.50	0.83	0.75	1.98

Fig.4 CI+TFRGB+WFRGB， SI+TFMS， SI+TFMS+WFRGB features were selected for relief importance ranking

References 51

1	Yang Q C， Kang J M， Zhang T J， et al. Distribution， breeding and utilization of alfalfa germplasm resources. Chinese Science Bulletin， 2016， 61（2）： 261-270.
	杨青川，康俊梅，张铁军，等. 苜蓿种质资源的分布、育种与利用. 科学通报， 2016， 61（2）： 261-270.
2	Wang M L. Focusing on the expansion of pasture industry to ensure the high-quality development of livestock industry. Modern Agriculture， 2023， 48（6）： 3-6， 24.
	王明利. 着力草业扩面增量保障畜牧业高质量发展. 现代农业， 2023， 48（6）： 3-6， 24.
3	Sun Q Z， Yu Z， Ma C H， et al. Achievements of the alfalfa industry in last decade and priorities in next decade in China. Pratacultural Science， 2013， 30（3）： 471-477.
	孙启忠，玉柱，马春晖，等. 我国苜蓿产业过去10年发展成就与未来10年发展重点. 草业科学， 2013， 30（3）： 471-477.
4	Wang R G， Xu W P. Development characteristics and trend of alfalfa industry in China. Journal of Agricultural Science and Technology， 2021， 23（12）： 7-12.
	王瑞港，徐伟平. 我国苜蓿产业发展特征与趋势分析. 中国农业科技导报， 2021， 23（12）： 7-12.
5	Zhang L， Chen X P， Jia L L. Parameter research of using UAV-based visible spectral analysis technology in dynamical diagnosis of nitrogen status of summer maize. Journal of Plant Nutrition and Fertilizers， 2018， 24（1）： 261-269.
	张玲，陈新平，贾良良. 基于无人机可见光遥感的夏玉米氮素营养动态诊断参数研究. 植物营养与肥料学报， 2018， 24（1）： 261-269.
6	Chen J S， Zhu R F， Gao C， et al. Nitrogen status diagnosis of fertilized alfalfa during budding stage using digital photography analysis. Acta Agrestia Sinica， 2013， 21（3）： 576-580.
	陈积山，朱瑞芬，高超，等. 基于图像处理技术对现蕾期紫花苜蓿氮素营养的诊断研究. 草地学报， 2013， 21（3）： 576-580.
7	Miao C L， Li Z X， Zhao Z C， et al. Real-time monitoring and analysis algorithm for key biophysical indicators of cultivated alfalfa in a grassland intelligent perception system. Acta Prataculturae Sinica， 2023， 32（12）： 90-103.
	苗春丽，李仲贤，赵志成，等. 栽培苜蓿草地智能感知系统关键生物物理指标实时监测及分析算法研究. 草业学报， 2023， 32（12）： 90-103.
8	Wang Q， Che Y P， Chai H H， et al. Monitoring of sugar beet growth using canopy spectrum and structural characteristics with UAV images. Transactions of the Chinese Society of Agricultural Engineering， 2021， 37（20）： 90-98.
	王庆，车荧璞，柴宏红，等. 基于无人机影像的冠层光谱和结构特征监测甜菜长势. 农业工程学报， 2021， 37（20）： 90-98.
9	Yue J B， Yang G J， Tian Q J， et al. Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices. ISPRS Journal of Photogrammetry and Remote Sensing， 2019， 150： 226-244.
10	Xing L X， Meng Z G， Edward M O. Information extraction of remote sensing texture based on wavelet transform. Journal of Jilin University （Earth Science Edition）， 2004， 34（3）： 481-483.
	邢立新，孟治国， Edward M O. 基于小波变换的遥感纹理信息提取. 吉林大学学报（地球科学版）， 2004， 34（3）： 481-483.
11	Liu Y， Sun Q， Feng H K， et al. Estimation of above-ground biomass of potato based on wavelet analysis. Spectroscopy and Spectral Analysis， 2021， 41（4）： 1205-1212.
	刘杨，孙乾，冯海宽，等. 基于小波分析的马铃薯地上生物量估算. 光谱学与光谱分析， 2021， 41（4）： 1205-1212.
12	Juliane B， Kang Y， Helge A， et al. Combining UAV-based plant height from crop surface models， visible， and near infrared vegetation indices for biomass monitoring in barley. International Journal of Applied Earth Observations and Geoinformation， 2015， 39（2）： 79-87.
13	Mutanga O， Skidmore K A. Narrow band vegetation indices overcome the saturation problem in biomass estimation. International Journal of Remote Sensing， 2004， 25（19）： 3999-4014.
14	Wang D， Li D， Xu L J， et al. Research progress and application of intelligent management of alfalfa. China Agricultural Informatics， 2022， 34（2）： 16-26.
	王笛，李达，徐丽君，等. 苜蓿智慧管理研究进展与应用. 中国农业信息， 2022， 34（2）： 16-26.
15	Yan H J， Zhuo Y， Li M N， et al. Alfalfa yield prediction using machine learning and UAV multispectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering， 2022， 38（11）： 64-71.
	严海军，卓越，李茂娜，等. 基于机器学习和无人机多光谱遥感的苜蓿产量预测. 农业工程学报， 2022， 38（11）： 64-71.
16	Ni H R， Wang R， Hu H， et al. Seed identification of alfalfa varieties based on multispectral imaging. Acta Agrestia Sinica， 2023， 31（10）： 2985-2991.
	倪浩然，王润，胡昊，等. 基于多光谱成像技术鉴别不同紫花苜蓿品种的种子. 草地学报， 2023， 31（10）： 2985-2991.
17	Jia Y Z， Xiao L Q， Yue T W， et al. Combining texture， color， and vegetation indices from fixed-wing UAS imagery to estimate wheat growth parameters using multivariate regression methods. Computers and Electronics in Agriculture， 2021， 185（6）： 106-138.
18	Shao Y J， Tang Q X， Cui J P， et al. Cotton leaf area index estimation combining UAV spectral and textural features. Transactions of the Chinese Society for Agricultural Machinery， 2023， 54（6）： 186-196.
	邵亚杰，汤秋香，崔建平，等. 融合无人机光谱信息与纹理特征的棉花叶面积指数估测. 农业机械学报， 2023， 54（6）： 186-196.
19	Meng L， Yin D， Cheng M， et al. Improved crop biomass algorithm with piecewise function （iCBA-PF） for maize using multi-source UAV data. Drones， 2023， 7（4）： 254.
20	Chandel A K， Khot L R， Yu L X. Alfalfa crop vigor and yield characterization using high-resolution aerial multispectral and thermal infrared imaging technique. Computers and Electronics in Agriculture， 2021， 182（3）： 105999.
21	Noland L R， Wells S M， Coulter A J， et al. Estimating alfalfa yield and nutritive value using remote sensing and air temperature. Field Crops Research， 2018， 222（6）： 189-196.
22	Yang J， Ding F， Chen C， et al. Correlation of wheat biomass and yield with UAV image characteristic parameters. Transactions of the Chinese Society of Agricultural Engineering， 2019， 35（23）： 104-110.
	杨俊，丁峰，陈晨，等. 小麦生物量及产量与无人机图像特征参数的相关性. 农业工程学报， 2019， 35（23）： 104-110.
23	Han W T， Peng X S， Zhang L Y， et al. Summer maize yield estimation based on vegetation index derived from multi-temporal UAV remote sensing. Transactions of the Chinese Society for Agricultural Machinery， 2020， 51（1）： 148-155.
	韩文霆，彭星硕，张立元，等. 基于多时相无人机遥感植被指数的夏玉米产量估算. 农业机械学报， 2020， 51（1）： 148-155.
24	Wang K， Zhu D Z， Zhang D Y， et al. Advance of the imaging spectral technique in diagnosis of the information of crop. Spectroscopy and Spectral Analysis， 2011， 31（3）： 589-594.
	王坤，朱大洲，张东彦，等. 成像光谱技术在农作物信息诊断中的研究进展. 光谱学与光谱分析， 2011， 31（3）： 589-594.
25	Woebbecke D M， Meyer G E， Von Bargen K， et al. Color indices for weed identification under various soil， residue， and lighting conditions. Transactions of the ASAE， 1995， 38（1）： 259-269.
26	Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment， 1979， 8（2）： 127-150.
27	Gitelson A A， Kaufman Y J， Stark R， et al. Novel algorithms for remote estimation of vegetation fraction. Remote Sensing of Environment， 2002， 80（1）： 76-87.
28	Hunt Jr E R， Doraiswamy P C， McMurtrey J E， et al. A visible band index for remote sensing leaf chlorophyll content at the canopy scale. International Journal of Applied Earth Observation and Geoinformation， 2013， 21（4）： 103-112.
29	Bannari A， Morin D， Bonn F， et al. A review of vegetation indices. Remote Sensing Reviews， 1995， 13（10）： 95-120.
30	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. Plant Physiology， 2003， 160（3）： 271-282.
31	Chappelle E W， Kim M S， McMurtrey Ⅲ J E. Ratio analysis of reflectance spectra （RARS）： an algorithm for the remote estimation of the concentrations of chlorophyll a， chlorophyll b， and carotenoids in soybean leaves. Remote Sensing of Environment， 1992， 39（3）： 239-247.
32	Tian Y， Yao X， Yang J， et al. Assessing newly developed and published vegetation indices for estimating rice leaf nitrogen concentration with ground space-based hyperspectral reflectance. Field Crop Research， 2011， 120（2）： 299-310.
33	Dash J， Curran P J. The MERIS terrestrial chlorophyll index. Remote Sensing of Environment， 2004， 25（23）： 5403-5413.
34	Sims D A， Gamon J A. Relationships between leaf pigment content and spectral reflectance across a wide range of species， leaf structures and developmental stages. Remote Sensing of Environment， 2002， 81（2/3）： 337-354.
35	Feng W， Guo B B， Wang Z J， et al. Measuring leaf nitrogen concentration in winter wheat using double-peak spectral reflection remote sensing data. Field Crop Research， 2014， 159（3）： 43-52.
36	Daughtry C S T， Walthall C L， Kim M S， et al. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment， 2000， 74（2）： 229-239.
37	Rondeaux G， Steven M， Baret F. Optimization of soil-adjusted vegetation indices. Remote Sensing of Environment， 1996， 55（2）： 95-107.
38	Wang W， Yao X， Yao X F， et al. Estimating leaf nitrogen concentration with three-band vegetation indices in rice and wheat. Field Crop Research， 2012， 129（4）： 90-98.
39	Haboudane D， Miller J R， Tremblay N， et al. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sensing of Environment， 2002， 81（2/3）： 416-426.
40	Li F， Mistele B， Hu Y C， et al. Remotely estimating aerial N status of phenologically differing winter wheat cultivars grown in contrasting climatic and geographic zones in China and Germany. Field Crop Research， 2012， 138（10）： 21-32.
41	Zarco-Tejada P J， Miller J R， Morales A， et al. Hyperspectral indices and model simulation for chlorophyll estimation in open-canopy tree crops. Remote Sensing of Environment， 2004， 90（4）： 463-476.
42	Fan J L， Wang H， Liao Z Q， et al. Winter wheat leaf area index estimation based on texture-color features and vegetation indices. Transactions of the Chinese Society for Agricultural Machinery， 2023， 54（7）： 347-359.
	范军亮，王涵，廖振棋，等. 基于纹理-颜色特征与植被指数融合的冬小麦LAI估测. 农业机械学报， 2023， 54（7）： 347-359.
43	Chen X， Xing L X， Gao Z Y， et al. Information extraction of remote sensing image texture based on wavelet transform. Journal of Anhui Agricultural Sciences， 2015， 43（4）： 363-366.
	陈潇，邢立新，高志勇，等. 基于小波变换的遥感影像纹理信息提取. 安徽农业科学， 2015， 43（4）： 363-366.
44	Liang J L， Liu Y H， Xu J， et al. Classification feature optimization of remote sensing images based on ReliefF algorithm. Surveying and Mapping of Geology and Mineral Resources， 2020， 36（3）： 1-5.
	梁加玲，刘彦花，徐军，等. 基于ReliefF算法的遥感影像分类特征优化. 地矿测绘， 2020， 36（3）： 1-5.
45	Dessislava G， Eugenia R， Petar D， et al. Phenotypic traits estimation and preliminary yield assessment in different phenophases of wheat breeding experiment based on UAV multispectral images. Remote Sensing， 2022， 14（4）： 1019.
46	Mohsen A， Davoud A， Hossein A， et al. Alfalfa yield estimation based on time series of Landsat 8 and PROBA-V images： An investigation of machine learning techniques and spectral-temporal features. Remote Sensing Applications： Society and Environment， 2022， 25（1）： 100657.
47	Zhang N N， Zhang X， Wang C K， et al. Cotton LAI estimation based on hyperspectral and successive projection algorithm. Transactions of the Chinese Society for Agricultural Machinery， 2022， 53（S1）： 257-262.
	张楠楠，张晓，王城坤，等. 基于高光谱和连续投影算法的棉花叶面积指数估测. 农业机械学报， 2022， 53（S1）： 257-262.
48	Feng L， Zhang Z， Ma Y， et al. Alfalfa yield prediction using UAV-based hyperspectral imagery and ensemble learning. Remote Sensing， 2020， 12（12）： 2028.
49	Cui Y， Ji Y， Liu R， et al. Faba bean （Vicia faba L.） yield estimation based on dual-sensor data. Drones， 2023， 7（6）： 378.
50	Huang J X， Zhang J， Liu J M， et al. Correlation analysis between drought and winter wheat yields based on remotely sensed drought severity index. Transactions of the Chinese Society for Agricultural Machinery， 2015， 46（3）： 166-173.
	黄健熙，张洁，刘峻明，等. 基于遥感DSI指数的干旱与冬小麦产量相关性分析. 农业机械学报， 2015， 46（3）： 166-173.
51	Zhang X J， Chen Y L， Xiao G， et al. A review of crop yield prediction based on machine learning. Anhui Agricultural Science Bulletin， 2021， 27（3）： 117-119， 134.
	张向君，陈优良，肖钢，等. 基于机器学习的农作物产量预测研究综述. 安徽农学通报， 2021， 27（3）： 117-119， 134.

[1]	Zheng-yan LI, Zhi-ming XU, Yan LI, Yang LI. Effects of short-term continuous cropping of alfalfa on the growth and soil microenvironment of subsequent sorghum-sudan grass hybrid crops in the Jianghuai area [J]. Acta Prataculturae Sinica, 2024, 33(9): 155-168.
[2]	Xiao-tong WANG, Xiao-hong LI, Xu-xia MA, Wen-qi CAI, Xue-li FENG, Shu-xia LI. Identification and analysis of members of the FBA gene family in alfalfa [J]. Acta Prataculturae Sinica, 2024, 33(9): 81-93.
[3]	Ying-ying ZHANG, Dan-dan HU, Chun-hui MA, Qian-bing ZHANG. Leaf structure and photosynthetic properties of alfalfa in response to bacteria and phosphorus addition [J]. Acta Prataculturae Sinica, 2024, 33(8): 133-144.
[4]	Wei LI, Han WANG, Chang-qing WANG, Yu-xin PAN, Jian-rong HOU, Wen-juan KANG, Su-qin SHANG, Shang-li SHI. Responses to temperature of population parameters of the pest mite Sancassania alfalfa fed on alfalfa [J]. Acta Prataculturae Sinica, 2024, 33(8): 181-189.
[5]	Zheng WANG, Wei CHANG, Jun-cheng LI, Lian-tai SU, Li GAO, Peng ZHOU, Yuan AN. Effects of alfalfa green manure on the yield， nitrogen absorption， and nitrogen translocation of feed maize [J]. Acta Prataculturae Sinica, 2024, 33(8): 63-73.
[6]	Shou-xia XU. Meta-analysis of the effects of arbuscular mycorrhizae on the yield and quality of wheat [J]. Acta Prataculturae Sinica, 2024, 33(7): 192-204.
[7]	Jin-zhu GAO, Dong-hao ZHAO, Le GAO, Xi-hao SU, Xue-qing HE. Effects of cerium nitrate and abscisic acid treatment on alfalfa seed germination and seedling physiological characteristics [J]. Acta Prataculturae Sinica, 2024, 33(6): 175-186.
[8]	Min WANG, Li LI, Rong JIA, Ai-ke BAO. Evaluation of physiological characteristics and cold resistance of 10 alfalfa varieties under low temperature stress [J]. Acta Prataculturae Sinica, 2024, 33(6): 76-88.
[9]	Hai-ming KONG, Jia-xing SONG, Jing YANG, Qian LI, Pei-zhi YANG, Yu-man CAO. Identification and transcript profiling of the CAMTA gene family under abiotic stress in alfalfa [J]. Acta Prataculturae Sinica, 2024, 33(5): 143-154.
[10]	Sheng-ran HE, Xiao-jing LIU, Ya-jiao ZHAO, Xue WANG, Jing WANG. Effects of alfalfa/sweet sorghum intercropping on rhizosphere soil characteristics and microbial community characteristics [J]. Acta Prataculturae Sinica, 2024, 33(5): 92-105.
[11]	Hao LIU, Xian-yang LI, Fei HE, Xue WANG, Ming-na LI, Rui-cai LONG, Jun-mei KANG, Qing-chuan YANG, Lin CHEN. Identification of the alfalfa SAUR gene family and its expression pattern under abiotic stress [J]. Acta Prataculturae Sinica, 2024, 33(4): 135-153.
[12]	Xian-yang LI, Hao LIU, Fei HE, Xue WANG, Ming-na LI, Rui-cai LONG, Jun-mei KANG, Qing-chuan YANG, Lin CHEN. Identification and expression pattern of the WRKY transcription factor family in Medicago sativa [J]. Acta Prataculturae Sinica, 2024, 33(4): 154-170.
[13]	Hai-wang YUE, Jian-wei WEI, Guang-cai WANG, Peng-cheng LIU, Shu-ping CHEN, Jun-zhou BU. Comprehensive evaluation of silage maize hybrids in the Huanghuaihai plain based on mega-environments delineated using envirotyping techniques [J]. Acta Prataculturae Sinica, 2024, 33(3): 120-138.
[14]	Yan LI, Fu-long MA, Lu HAN, Hai-zhen WANG. Productivity and adaptability of ‘WL’ alfalfa varieties with different fall dormancy in the extremely arid region of Southern Xinjiang [J]. Acta Prataculturae Sinica, 2024, 33(3): 139-149.
[15]	Xue WANG, Xiao-jing LIU, Jing WANG, Yong WU, Chang-chun TONG. Root and carbon-nitrogen metabolism characteristics of alfalfa-oat mixed stands under continuous intercropping [J]. Acta Prataculturae Sinica, 2024, 33(3): 85-96.