基于无人机影像特征的冬小麦植株氮含量预测及模型迁移能力分析

doi:10.3864/j.issn.0578-1752.2023.05.004

Abstract

Abstract:

【Objective】Accurate monitoring and rational application of nitrogen are particularly important for healthy growth, yield and quality improvement of wheat, and reduction of environmental pollution and resource waste. The purpose of this study was to develop UAV-based models for accurately and effectively assessment of the plant nitrogen content in the key growth stages of wheat growth, and to explore the transferability of the models constructed based on machine learning methods. 【Method】Winter wheat experiment were conducted from 2020 to 2022 in Shangshui county, Henan province, China. Based on the K6 multichannel imager mounted on DJM600 UAV, 5-band (Red, Green, Blue, Rededge, and Nir) multispectral images were obtained from a UAV system in the stages of jointing, booting, flowering and filling in winter wheat, to calculate 20 vegetation indices and 40 texture features from different band combinations. Correlation analysis was used to screen the sensitive characteristics of nitrogen content in winter wheat plants from the 65 image features. Combining the sensitive spectral features and texture features of the nitrogen content of winter wheat plants, BP neural network (BP), random forest (RF), Adaboost, and support vector machine (SVR) machine learning regression methods were used to build plant nitrogen content models, and compared for the model performance and transferability. 【Result】(1)The correlation coefficients between plant nitrogen content and image features passed the test of 0.01 extremely significant level, including 22 spectral features and 29 texture features. (2) 51 spectral and texture features were adopted to build four machine learning models. The estimates of plant nitrogen by the RF and Adaboost methods were relatively concentrated, mostly close to the 1﹕1 line; while the estimations from the BP and SVR methods were relatively scattered. The RF method was the best, with R², RMSE, and MAE of 0.81, 0.42%, and 0.29%, respectively; The SVR method was the worst, with R², RMSE, and MAE of 0.66, 0.54% and 0.40%, respectively. (3) The prediction effects of the four methods on the nitrogen content of W0 and W1 treatments trained using W1 and W0 treatments were the same as those trained using both W0 and W1 datasets, both of which were closer to the 1﹕1 line for the RF and Adaboost methods. The R² of transfer prediction results for the models constructed by BP, RF, Adaboost, and SVR methods were 0.75, 0.72, 0.72, and 0.66 for the prediction of nitrogen content in W0 treatment and 0.51, 0.69, 0.61 (trained using data under W1 treatment) and 0.45 for the prediction under W1 treatment (trained using data under W0 treatment), respectively.【Conclusion】All models showed strong transferability, especially the RF and Adaboost methods, in predicting winter wheat nitrogen content under rainfed and irrigation water management.

Key words: UAV, spectral feature, textural feature, machine learning, nitrogen content in winter wheat, transferability

GUO Yan, JING YuHang, WANG LaiGang, HUANG JingYi, HE Jia, FENG Wei, ZHENG GuoQing. UAV Multispectral Image-Based Nitrogen Content Prediction and the Transferability Analysis of the Models in Winter Wheat Plant[J].Scientia Agricultura Sinica, 2023, 56(5): 850-865.

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: https://www.chinaagrisci.com/EN/10.3864/j.issn.0578-1752.2023.05.004

https://www.chinaagrisci.com/EN/Y2023/V56/I5/850

Figures/Tables 11

Fig. 1

Table 1

Vegetation index and the calculating formula"

植被指数 Vegetation index	简写Abbreviation	计算公式 Formulas	文献 References
绿波段归一化植被指数 Green-band normalized vegetation index	GNDVI	(R_nir-R_green)/(R_nir+R_green)	[43]
绿波段优化土壤调节植被指数 Green-band optimized soil adjusted vegetation index	GOSAVI	1.16×(R_nir-R_green)/(R_nir+R_green+0.16)	[44]
归一化差异植被指数 Normalized difference vegetation index	NDVI	(R_nir-R_red)/(R_nir+R_red)	[45]
改进简单比值植被指数 Modified simple ratio index	MSR	((R_nir/R_red)-1)/(((R_nir/R_red)+1)^0.5)	[46]
红边优化土壤调节植被指数 Rededge-band optimized soil adjusted vegetation index	REOSAVI	1.16×(R_nir-R_red)/(R_nir+R_red+0.16)	[47]
红边重归一化植被指数 Rededge-band renormalized difference vegetation index	RERDVI	(R_nir-R_{red edge})/((R_nir+R_rededge)^0.5)	[43]
叶绿素吸收比值指数 Chlorophyll absorption ratio index	CARI	(R_{red edge}-R_red)-0.2×(R_rededge+R_red)	[48]
优化土壤调节植被指数 Optimized soil adjusted vegetation index	OSAVI	(R_nir-R_red)/(R_nir+R_red+0.16)	[48]
归一化蓝绿差异指数 Normalized blue-green difference index	NGBDI	(R_green-R_blue)/(R_green+R_blue)	[49]
增强型植被指数 Enhanced vegetation index	EVI	2.5×(R_nir-R_red)/(R_nir+6×R_red-7.5×R_blue+1)	[50]
三角植被指数 Triangle vegetation index	TVI	0.5×(120×(R_nir-R_green)-200×(R_red-R_green))	[51]
大气阻抗植被指数 Atmospherically resistant vegetation index	VARI	(R_green-R_red)/(R_green+R_red-R_blue)	[52]
过绿指数 Excessive green index	EXG	2×R_green-R_red-R_blue	[53]
比值植被指数 Ratio vegetation index	RVI	R_nir/R_red	[52]
修正三角植被指数 Modified triangle vegetation index	MTVI	(1.5×(1.2×(R_nir-R_green)-2.5×(R_red-R_green)))/(((2×R_nir+1)²-6×R_nir-5×(R_red)^0.5-0.5)^0.5)	[54]
土壤调节植被指数Soil adjusted vegetation index	SAVI	1.5×(R_nir-R_red)/(R_nir+R_red+0.5)	[55]
归一化蓝绿波段差值植被指数 Normalized blue-green band difference vegetation index	GBNDVI	(R_nir-(R_green+R_blue))/(R_nir+R_green+R_blue)	[43]
重归一化植被指数Renormalized difference vegetation index	RDVI	(R_nir-R_red)(R_nir+R_red)^0.5	[54]
差值植被指数Difference vegetation index	DVI	R_nir-R_red	[56]
优化植被指数Optimized vegetation index	VIplot	1.45×(R²_nir+1)(R_red+0.45)	[57]

Table 1

Table 2

Table 3

Table 4

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 5

Fig. 6

References 79

[1]	United States Department of Agriculture USDA, World Agricultural Production. Circular Series WAP. 2022: 27-42. https://apps.fas.usda.gov/psdonline/circulars/production.pdf.
[2]	PERRY E M, FITZGERALD G J, NUTTALL J G, O’LEARY G, SCHULTHESS U, WHITLOCK A. Rapid estimation of canopy nitrogen of cereal crops at paddock scale using a canopy chlorophyll content index. Field Crops Research, 2012, 134: 158-164. doi: 10.1016/j.fcr.2012.06.003
[3]	LU N, WANG W, ZHANG Q, LI D, YAO X, TIAN Y C, ZHU Y, CAO W X, BARET F, LIU S Y, CHENG T. Estimation of nitrogen nutrition status in winter wheat from unmanned aerial vehicle based multi-angular multispectral imagery. Frontiers in Plant Science, 2019, 10: 1601. doi: 10.3389/fpls.2019.01601 pmid: 31921250
[4]	郭燕, 井宇航, 贺佳, 王来刚, 冯伟, 刘海礁. 小麦冠层氮素含量光谱估算研究进展. 麦类作物学报, 2021, 41(11): 1425-1431.
	GUO Y, JING Y H, HE J, WANG L G, FENG W, LIU H J. Research progress of nitrogen content estimation in winter wheat canopy based on optical spectrum. Journal of Triticeae Crops, 2021, 41(11): 1425-1431.(in Chinese)
[5]	ROSIN N A, DALMOLIN R, HORST-HEINEN T Z, MOURA- BUENO J M, SILVA-SANGOI D V, SILVA L. Diffuse reflectance spectroscopy for estimating soil organic carbon and make nitrogen recommendations. Scientia Agricola, 2021, 78(5): e20190246.
[6]	杨宝华, 陈建林, 陈林海, 曹卫星, 姚霞, 朱艳. 基于敏感波段的小麦冠层氮含量估测模型. 农业工程学报, 2015, 31(22): 176-182.
	YANG B H, CHEN J L, CHEN L H, CAO W X, YAO X, ZHU Y. Estimation model of wheat canopy nitrogen content based on sensitive bands. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(22): 176-182.(in Chinese)
[7]	王玉娜, 李粉玲, 王伟东, 陈晓凯, 常庆瑞. 基于无人机高光谱的冬小麦氮素营养监测. 农业工程学报, 2020, 36(22): 31-39.
	WANG Y N, LI F L, WANG W D, CHEN X K, CHANG Q R. Monitoring of winter wheat nitrogen nutrition based on UAV hyperspectral images. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(22): 31-39.(in Chinese)
[8]	JIANG J L, ZHU J, WANG X, CHENG T, TIAN Y C, ZHU Y, YAO X. Estimating the leaf nitrogen content with a new feature extracted from the ultra-high spectral and spatial resolution images in wheat. Remote Sensing, 2021, 13(4): 739. doi: 10.3390/rs13040739
[9]	SABZI S, POURDARBANI R, ROHBAN M H, GARCÍA-MATEOS G, ARRIBAS J I. Estimation of nitrogen content in cucumber plant (Cucumis sativus L.) leaves using hyperspectral imaging data with neural network and partial least squares regressions. Chemometrics and Intelligent Laboratory Systems, 2021, 217: 104404. doi: 10.1016/j.chemolab.2021.104404
[10]	SHI P H, WANG Y, XU J M, ZHAO Y L, YANG B L, YUAN Z M, SUN Q H. Rice nitrogen nutrition estimation with RGB images and machine learning methods. Computers and Electronics in Agriculture, 2021, 180: 105860. doi: 10.1016/j.compag.2020.105860
[11]	井宇航, 郭燕, 张会芳, 戎亚思, 张少华, 冯伟, 王来刚, 贺佳, 刘海礁, 郑国清. 无人机飞行高度对冬小麦植株氮积累量预测模型的影响. 河南农业科学, 2022, 51(2):147-158.
	JING Y H, GUO Y, ZHANG H F, RONG Y S, ZHANG S H, FENG W, WANG L G, HE J, LIU H Q, ZHENG G Q. Effects of UAV flight height on prediction model of plant nitrogen accumulation in winter wheat. Journal of Henan Agricultural Sciences, 2022, 51(2):147-158.(in Chinese)
[12]	张潇元, 张立福, 张霞, 王树东, 田静国, 翟涌光. 不同光谱植被指数反演冬小麦叶氮含量的敏感性研究. 中国农业科学, 2017, 50(3): 474-485. doi: 10.3864/j.issn.0578-1752.2017.03.006
	ZHANG X Y, ZHANG L F, ZHANG X, WANG S D, TIAN J G, ZHAI Y G. Sensitivity of different spectral vegetation index for estimating winter wheat leaf nitrogen. Scientia Agricultura Sinica, 2017, 50(3): 474-485.(in Chinese) doi: 10.3864/j.issn.0578-1752.2017.03.006
[13]	LI Z H, LI Z H, FAIRBAIRN D, LI N, XU B, FENG H K, YANG G J. Multi-LUTs method for canopy nitrogen density estimation in winter wheat by field and UAV hyperspectral. Computers and Electronics in Agriculture, 2019, 162: 174-182. doi: 10.1016/j.compag.2019.04.005
[14]	魏鹏飞, 徐新刚, 李中元, 杨贵军, 李振海, 冯海宽, 陈帼, 范玲玲, 王玉龙, 刘帅兵. 基于无人机多光谱影像的夏玉米叶片氮含量遥感估测. 农业工程学报, 2019, 35(8):126-133.
	WEI P F, XU X G, LI Z Y, YANG G J, LI Z H, FENG H K, CHEN G, FAN L L, WANG Y L, LIU S B. Remote sensing estimation of nitrogen content in summer maize leaves based on multispectral images of UAV. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(8): 126-133.(in Chinese)
[15]	贾丹, 陈鹏飞. 低空无人机影像分辨率对冬小麦氮浓度反演的影响. 农业机械学报, 2020, 51(7): 164-169.
	JIA D, CHEN P F. Effect of low altitude UAV image resolution on inversion of winter wheat nitrogen concentration. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(7): 164-169.(in Chinese)
[16]	GANDHIMATHI ALIAS USHA S, VASUKI S. Significance of texture features in the segmentation of remotely sensed images. International Journal for Light and Electron Optics-Optik, 2022, 249: 168241. doi: 10.1016/j.ijleo.2021.168241
[17]	WALSH O S, SHAFIAN S, MARSHALL J, JACKSON C, MCCLINTICK-CHESS J R, BLANSCET S M, SWOBODA K, THOMPSON C, BELMONT K M, WALSH W L. Assessment of UAV based vegetation indices for nitrogen concentration estimation in spring wheat. Advances in Remote Sensing, 2018, 7: 71-90. doi: 10.4236/ars.2018.72006
[18]	杨福芹, 冯海宽, 肖天豪, 李天驰, 郭向前. 融合无人机影像光谱与纹理特征的冬小麦氮营养指数估算. 农业现代化研究, 2020, 41(4): 718-726.
	YANG F Q, FENG H K, XIAO T H, LI T C, GUO X Q. Nitrogen nutrition index estimation in winter wheat by UAV spectral information and texture feature fusion. Research of Agricultural Modernization, 2020, 41(4): 718-726.(in Chinese)
[19]	JAY S, MAUPAS F, BENDOULA R, GORRETTA N. Retrieving LAI, chlorophyll and nitrogen contents in sugar beet crops from multi-angular optical remote sensing: Comparison of vegetation indices and PROSAIL inversion for field phenotyping. Field Crops Research, 2017, 210: 33-46. doi: 10.1016/j.fcr.2017.05.005
[20]	CHLINGARYAN A, SUKKARIEH S, WHELAN B. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review. Computers and Electronics in Agriculture, 2018, 151: 61-69. doi: 10.1016/j.compag.2018.05.012
[21]	BERGER K, VERRELST J, FÉRET J, HANK T B, WOCHER M, MAUSER W, CAMPS-VALLS G. Retrieval of aboveground crop nitrogen content with a hybrid machine learning method. International Journal of Applied Earth Observation and Geoinformation, 2020, 92: 102174. doi: 10.1016/j.jag.2020.102174
[22]	黄芬, 高帅, 姚霞, 张小虎, 朱艳. 基于机器学习和多颜色空间的冬小麦叶片氮含量估算方法研究. 南京农业大学学报, 2020, 43(2): 364-371.
	HUANG F, GAO S, YAO X, ZHANG X H, ZHU Y. Estimation of winter wheat leaf nitrogen concentration using machine learning algorithm and multi-color space. Journal of Nanjing Agricultural University, 2020, 43(2): 364-371.(in Chinese)
[23]	李金敏, 陈秀青, 杨琦, 史良胜. 基于高光谱的水稻叶片氮含量估计的深度森林模型研究. 作物学报, 2021, 47(7): 1342-1350. doi: 10.3724/SP.J.1006.2021.02060
	LI J M, CHEN X Q, YANG Q, SHI L S. Deep learning models for estimation of paddy rice leaf nitrogen concentration based on canopy hyperspectral data. Acta Agronomica Sinica, 2021, 47(7): 1342-1350.(in Chinese)
[24]	QIU Z C, MA F, LI Z W, XU X B, GE H X, DU C. 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
[25]	李美炫, 朱西存, 白雪源, 彭玉凤, 田中宇, 姜远茂. 基于无人机影像阴影去除的苹果树冠层氮素含量遥感反演. 中国农业科学, 2021, 54(10): 2084-2094. doi: 10.3864/j.issn.0578-1752.2021.10.005
	LI M X, ZHU X C, BAI X Y, PENG Y F, TIAN Z Y, JIANG Y M. Remote sensing inversion of nitrogen content in apple canopy based on shadow removal in UAV multi-spectral remote sensing images. Scientia Agricultura Sinica, 2021, 54(10): 2084-2094.(in Chinese) doi: 10.3864/j.issn.0578-1752.2021.10.005
[26]	MESSINA G, PRATICÒ S, BADAGLIACCA G, DI FAZIO S, MONTI M, MODICA G. Monitoring onion crop “Cipolla Rossa di Tropea Calabria IGP” growth and yield response to varying nitrogen fertilizer application rates using UAV imagery. Drones, 2021, 5: 61. doi: 10.3390/drones5030061
[27]	GAMON J A, PENUElAS J, FIELD C B. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sensing of Environment, 1992, 41(1): 35-44. doi: 10.1016/0034-4257(92)90059-S
[28]	XIAO X M, HE L, SALAS W, LI C S, MOORE B, ZHAO R, FROLKING S, BOLES S. Quantitative relationships between field-measured leaf area index and vegetation index derived from vegetation images for paddy rice fields. International Journal of Remote Sensing, 2002, 23(18): 3595-3604. doi: 10.1080/01431160110115799
[29]	ZHOU Y C, LAO C C, YANG Y L, ZHANG Z T, CHEN H Y, CHEN Y W, CHEN J Y, NING J, YANG N. Diagnosis of winter-wheat water stress based on UAV-borne multispectral image texture and vegetation indices. Agricultural Water Management, 2021, 256: 107076. doi: 10.1016/j.agwat.2021.107076
[30]	于丰华, 邢思敏, 郭忠辉, 白驹驰, 许童羽. 基于特征转移植被指数的水稻叶片氮素含量定量估算. 农业工程学报, 2022, 38(2): 175-182.
	YU F H, XING S M, GUO Z H, BAI J C, XU T Y. Remote sensing inversion of the nitrogen content in rice leaves using character transfer vegetation index. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(2): 175-182.(in Chinese)
[31]	牛亚晓, 张立元, 韩文霆, 邵国敏. 基于无人机遥感与植被指数的冬小麦覆盖度提取方法. 农业机械学报, 2018, 49(4): 212-221.
	NIU Y X, ZHANG L Y, HAN W T, SHAO G M. Fractional vegetation cover extraction method of winter wheat based on UAV remote sensing and vegetation index. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(4): 212-221.(in Chinese)
[32]	奚雪, 赵庚星. 基于无人机多光谱遥感的冬小麦叶绿素含量反演及监测. 中国农学通报, 2020, 36(20): 119-126. doi: 10.11924/j.issn.1000-6850.casb20190400050
	XI X, ZHAO G X. Chlorophyll content in winter wheat: Inversion and monitoring based on UAV multi-spectral remote sensing. Chinese Agricultural Science Bulletin, 2020, 36(20): 119-126.(in Chinese) doi: 10.11924/j.issn.1000-6850.casb20190400050
[33]	WAN L, LI Y J, CEN H Y, ZHU J P, YIN W X, WU W K, ZHU H Y, SUN D W, ZHOU W J, HE Y. Combining UAV-based vegetation indices and image classification to estimate flower number in oilseed rape. Remote Sensing, 2018, 10(9): 1484. doi: 10.3390/rs10091484
[34]	万亮, 岑海燕, 朱姜蓬, 张佳菲, 杜晓月, 何勇. 基于纹理特征与植被指数融合的水稻含水量无人机遥感监测. 智慧农业, 2020, 2(1): 58-67.
	WAN L, CEN H Y, ZHU J P, ZHANG J F, DU X Y, HE Y. Using fusion of texture features and vegetation indices from water concentration in rice crop to UAV remote sensing monitor. Smart Agriculture, 2020, 2(1): 58-67.(in Chinese)
[35]	于利峰, 乌兰吐雅, 乌云德吉, 许洪滔, 包珺玮, 任婷婷. 基于纹理特征与MODIS-NDVI时间序列的耕地面积提取研究. 中国农业资源与区划, 2018, 39(11): 169-177.
	YU L F, WULAN T Y, WUYUN D J, XU H T, BAO J W, REN T T. Study on extraction of arable land area based on texture features and MODIS-NDVI time series. Chinese Journal of Agricultural Resources and Regional Planning, 2018, 39(11): 169-177.(in Chinese)
[36]	王镕. 基于光谱和纹理特征综合的农作物种植结构提取方法研究. 兰州: 兰州交通大学, 2019.
	WANG R. Study on extraction of crop planting structure based on spectral and texture features. Lanzhou: Lanzhou Jiaotong University, 2019.(in Chinese)
[37]	YANG Y, CHEN J. Comprehensive analysis of water carrying capacity based on wireless sensor network and image texture of feature extraction. Alexandria Engineering Journal, 2022, 61: 2877-2886. doi: 10.1016/j.aej.2021.08.018
[38]	AOUAT S, AIT-HAMMI I, HAMOUCHENE I. A new approach for texture segmentation based on the Gray Level Co-occurrence Matrix. Multimedia Tools and Applications, 2021, 80: 24027-24052. doi: 10.1007/s11042-021-10634-4
[39]	高苹, 徐敏, 孔维财, 张志薇. 基于最优化相关分析的油菜开花期预报模型研究. 海洋气象学报, 2021, 41(3): 77-83.
	GAO P, XU M, KONG W C, ZHANG Z W. Establishment of predicting models for oilseed rape florescence using an optimal correlation analysis method. Journal of Marine Meteorology, 2021, 41(3): 77-83.(in Chinese)
[40]	崔承齐, 刘艳阳, 江晓林, 孙知雨, 杜振伟, 武轲, 梅鸿献, 郑永战. 芝麻产量相关性状的多位点全基因组关联分析及候选基因预测. 中国农业科学, 2022, 55(1): 219-232. doi: 10.3864/j.issn.0578-1752.2022.01.018
	CUI C Q, LIU Y Y, JIANG X L, SUN Z Y, DU Z W, WU K, MEI H X, ZHENG Y Z. Multi-locus genome-wide association analysis of yield-related traits and candidate gene prediction in sesame (Sesamum indicum L.). Scientia Agricultura Sinica, 2022, 55(1): 219-232.(in Chinese)
[41]	宋宇斐. 基于数字图像的小麦叶绿素和氮素营养检测研究. 保定: 河北农业大学, 2020.
	SONG Y F. Detection of chlorophyll and nitrogen nutrition of wheat based on digital images. Baoding: Hebei Agricultural University, 2020.(in Chinese)
[42]	刘秀英, 余俊茹, 王世华. 光谱特征变量和BP神经网络构建油用牡丹种子含水率估算模型. 农业工程学报, 2020, 36(22): 308-315.
	LIU X Y, YU J R, WANG S H. Estimation of moisture content in peony seed oil using spectral characteristic variables and BP neural network. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(22): 308-315.(in Chinese)
[43]	GITELSON A A, KAUFMAN Y J, MERZLYAK M N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sensing of Environment, 1996, 58(3): 289-298. doi: 10.1016/S0034-4257(96)00072-7
[44]	GILABERT M A, GONZÁLEZ-PIQUERAS J, GARCÍA-HARO F J, MELIÁ J. A generalized soil-adjusted vegetation index. Remote Sensing of Environment, 2002, 82(2): 303-310. doi: 10.1016/S0034-4257(02)00048-2
[45]	ROUSE J W. Monitoring the vernal advancement of retrogradation (green wave effect) of natural vegetation. NASA/GSFC Type III. Final Report. Greenbelt Md, 1974: 371.
[46]	CHEN J M. Evaluation of vegetation indices and a modified simple ratio for boreal applications. Canadian Journal of Remote Sensing, 1996, 22(3): 229-242. doi: 10.1080/07038992.1996.10855178
[47]	CAO Q, MIAO Y, SHEN J N, YU W F, YUAN F, CHENG S S, HUANG S Y, WANG H Y, YANG W, LIU F. Improving in-season estimation of rice yield potential and responsiveness to topdressing nitrogen application with crop circle active crop canopy sensor. Precision Agriculture, 2015, 17: 136-154. doi: 10.1007/s11119-015-9412-y
[48]	RONDEAUX G, BARET F, STEVEN M. Optimization of soil-adjusted vegetation indices. Remote Sensing of Environment, 1996, 55(2): 95-107. doi: 10.1016/0034-4257(95)00186-7
[49]	GITELSON A A, VIÑA A, CIGANDA V S, RUNDQUIST D, ARKEBAUER T J. Remote estimation of canopy content in crops. Geophysical Research Letters, 2005, 32(8): 1-4.
[50]	HUETE A, JUSTICE C, LEEUWEN W V. MODIS vegetation index (MOD13) algorithm theoretical basis document. US: NASA Goddard Space Flight Center, 1999.
[51]	DEERING D W, ROUSE J W, HASS R H, SCHELL J A. Measuring “Forage Production” of grazing units from Landsat MSS data. Proceedings of the 10^th International Symposium on Remote Sensing of Environment, Ann Arbor, 1975: 169-1178.
[52]	ERUNOVA M, PISMAN T I, SHEVYRNOGOV A P. The technology for detecting weeds in agricultural crops based on vegetation index VARI (PlanetScope). Journal of Siberian Federal University. Engineering & Technologies, 2021, 14(3): 347-353.
[53]	LAMM R D, SLAUGHTER D C, GILES D K. Precision weed control system for cotton. Transactions of the American Society of Agricultural and Biological Engineers, 2002, 45(1): 231-238.
[54]	HABOUDANE D, MILLER J R, PATTEY E, ZARCO-TEJADA P J, STRACHAN I B. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sensing of Environment, 2004, 90(3): 337-352. doi: 10.1016/j.rse.2003.12.013
[55]	HUETE A R, HUA G, QI J, CHEHBOUNI A G, LEEUWEN W J. Normalization of multidirectional red and NIR reflectances with the SAVI. Remote Sensing of Environment, 1992, 41(2/3): 143-154. doi: 10.1016/0034-4257(92)90074-T
[56]	JORDAN C F. Derivation of leaf-area index from quality of light on the forest floor. Ecology, 1969, 50: 663-666. doi: 10.2307/1936256
[57]	REYNIERS M, WALVOORT D J J, DE BAARDEMAAKER J. A linear model to predict with a multi-spectral radiometer the amount of nitrogen in winter wheat. International Journal of Remote Sensing, 2006, 27(19): 4159-4179. doi: 10.1080/01431160600791650
[58]	DU B, LUND P D, WANG J, KOLHE M, HU E. Comparative study of modelling the thermal efficiency of a novel straight through evacuated tube collector with MLR, SVR, BP and RBF methods. Sustainable Energy Technologies and Assessments, 2021, 44(1): 101029. doi: 10.1016/j.seta.2021.101029
[59]	王鑫梅, 张劲松, 孟平, 杨洪国, 孙圣. 基于无人机遥感影像的核桃冠层氮素含量估算. 农业机械学报, 2021, 52(2): 178-187.
	WANG X M, ZHANG J S, MENG P, YANG H G, SUN S. Estimation of nitrogen content in walnut canopy based on UAV remote sensing image. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(2): 178-187.(in Chinese)
[60]	李航. 机器学习方法. 北京: 清华大学出版社, 2022.
	LI H. Machine Learning Method. Beijing: Tsinghua University Press, 2022.(in Chinese)
[61]	周志华. 机器学习. 北京: 清华大学出版社, 2016.
	ZHOU Z H. Machine Learning. Beijing: Tsinghua University Press, 2016.(in Chinese)
[62]	JEUNG M, BAEK S, BEOM J, CHO K H, HER Y, YOON K. Evaluation of random forest and regression tree methods for estimation of mass first flush ratio in urban catchments. Journal of Hydrology, 2019, 575: 1099-1110. doi: 10.1016/j.jhydrol.2019.05.079
[63]	FERNÁNDEZ-HABAS J, CAÑADA M C, MORENO A M G, LEAL- MURILLO J R, GONZÁLEZ-DUGO M P, OAR B A, GÓMEZ- GIRÁLDEZ P J, FERNÁNDEZ-REBOLLO P. Estimating pasture quality of Mediterranean grasslands using hyperspectral narrow bands from field spectroscopy by random forest and PLS regressions. Computers and Electronics in Agriculture, 2022, 192: 106614. doi: 10.1016/j.compag.2021.106614
[64]	LIEPE M U, BELOMESTNYKH S. RF parameter and field stability requirements for the Cornell ERL prototype. Proceedings of the 2003 Particle Accelerator Conference, 2003, 2: 1329-1331.
[65]	BARROW D K, CRONE S F. A comparison of AdaBoost algorithms for time series forecast combination. International Journal of Forecasting, 2016, 32(4): 1103-1119. doi: 10.1016/j.ijforecast.2016.01.006
[66]	WANG L L, GUO Y L, FAN M H, LI X. Wind speed prediction using measurements from neighboring locations and combining the extreme learning machine and the AdaBoost algorithm. Energy Reports, 2022, 8: 1508-1518.
[67]	ZHOU Y, LU Z, CHENG K. Adaboost-based ensemble of polynomial chaos expansion with adaptive sampling. Computer Methods in Applied Mechanics and Engineering, 2022, 388: 114238. doi: 10.1016/j.cma.2021.114238
[68]	WU S, NAGAHASHI H. Parameterized AdaBoost: Introducing a parameter to speed up the training of real Adaboost. Institute of Electrical and Electronics Engineers Signal Processing Letters, 2014, 21: 687-691.
[69]	PANAHI M, SADHASIVAM N, POURGHASEMI H R, REZAIE F, LEE S. Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression (SVR). Journal of Hydrology, 2020, 588: 125033. doi: 10.1016/j.jhydrol.2020.125033
[70]	Scientific Platform Serving for Statistics Professional 2021. SPSSPRO. (Version 1.0.11) [Online Application Software]. https://www.spsspro.com.
[71]	ALNUWAISER M A, JAVED M F, KHAN M I, AHMED M W, GALAL A M. Support vector regression and ANN approach for predicting the ground water quality. Journal of the Indian Chemical Society, 2022, 99: 10538.
[72]	LI Y, SUN H, YAN W, ZHANG X. Multi-output parameter-insensitive kernel twin SVR model. Neural networks, 2020, 121: 276-293. doi: S0893-6080(19)30302-8 pmid: 31586856
[73]	YI Y, WANG L, CHEN Z. Adaptive global kernel interval SVR-based machine learning for accelerated dielectric constant prediction of polymer-based dielectric energy storage. Renewable Energy, 2021, 176: 81-88. doi: 10.1016/j.renene.2021.05.045
[74]	JIANG Q, XU L, SUN S, WANG M, XIAO H. Retrieval model for total nitrogen concentration based on UAV hyper spectral remote sensing data and machine learning algorithms-A case study in the Miyun reservoir, China. Ecological Indicators, 2021, 124: 107356. doi: 10.1016/j.ecolind.2021.107356
[75]	LIN L, LIU X. Mixture-based weight learning improves the random forest method for hyperspectral estimation of soil total nitrogen. Computers and Electronics in Agriculture, 2022, 192: 106634. doi: 10.1016/j.compag.2021.106634
[76]	LINARDATOS P, PAPASTEFANOPOULOS V, KOTSIANTIS S B. Explainable AI: A review of machine learning interpretability methods. Entropy, 2021, 23: 18. doi: 10.3390/e23010018
[77]	申哲, 张认连, 龙怀玉, 徐爱国. 基于机器学习方法的宁夏南部土壤质地空间分布研究. 中国农业科学, 2022, 55(15): 2961-2972. doi: 10.3864/j.issn.0578-1752.2022.15.008
	SHEN Z, ZHANG R L, LONG H Y, XU A G. Research on spatial distribution of soil texture in southern Ningxia based on machine learning. Scientia Agricultura Sinica, 2022, 55(15): 2961-2972.(in Chinese) doi: 10.3864/j.issn.0578-1752.2022.15.008
[78]	王来刚, 郑国清, 郭燕, 贺佳, 程永政. 融合多源时空数据的冬小麦产量预测模型研究. 农业机械学报, 2022, 53(1): 198-204, 458.
	WANG L G, ZHENG G Q, GUO Y, HE J, CHENG Y Z. Prediction of winter wheat yield based on fusing multi-source spatio-temporal data. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(1): 198-204, 458.(in Chinese)
[79]	SARKER I H. Machine learning: Algorithms, real-world applications and research directions. SN Computer Science, 2021, 2(3): 160. doi: 10.1007/s42979-021-00592-x

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

BP		RF		Adaboost		SVR
参数名 Parameters	参数值 Parameter value	参数名 Parameters	参数值 Parameter value	参数名 Parameters	参数值 Parameter value	参数名 Parameters	参数值 Parameter value
数据切分 Data cut	0.5	数据切分 Data cut	0.5	数据切分 Data cut	0.5	数据切分 Data cut	0.5
数据洗牌 Data shuffling	是 Yes	数据洗牌 Data shuffling	是 Yes	数据洗牌 Data shuffling	是 Yes	数据洗牌 Data shuffling	是 Yes
交叉验证 Cross validation	3折 3-fold cross validation	交叉验证 Cross validation	3折 3-fold cross validation	交叉验证 Cross validation	3折 3-fold cross validation	交叉验证 Cross validation	3折 3-fold cross validation
激活函数 Activation function	Identity	节点分裂评价准则 Identity node split evaluation criterion	mse	基分类器数量 Number of base classifiers	100	惩罚系数 Penalty factor	1
求解器 Sovler	lbfgs	内部节点分裂最小样本数 Minimum number of samples for internal node splitting	2	损失函数 Loss function	linear	核函数 Kernel function	linear
学习率 Learning rate	0.1	叶子节点最小样本数 Minimum number of samples of leaf nodes	1	基分类器 Base classifier	决策树 Decision tree	核函数系数 Kernel function coefficient	scale
L2正则项 L2 regular term	1	树的最大深度 Maximum depth of tree	10	学习率 Learning rate	1	核函数最高项次数 Maximum number of terms in kernel function	3
迭代次数 Number of iterations	1000	叶子节点的最大数量 Maximum number of leaf nodes	50			误差收敛条件 Error convergence condition	0.001
隐藏第1层神经元数量 Number of hidden layers 1st neurons	100	决策树数量 Number of decision trees	100			最大迭代次数 Maximum number of iterations	1000

反射率 Reflectance		植被指数 Vegetation index		植被指数 Vegetation index		植被指数 Vegetation index		植被指数 Vegetation index
B	-0.59**	GNDVI	-0.02	RERDVI	0.80**	TVI	0.57**	SAVI	0.79**
G	-0.09**	GOSAVI	-0.06	CARI	0.79**	VARI	0.76**	GBNDVI	-0.30**
R	-0.68**	NDVI	0.68**	OSAVI	0.57**	EXG	0.47**	RDVI	0.79**
Rededge	-0.20**	MSR	0.66**	NDRGI	0.60**	RVI	0.64**	DVI	0.35**
Nir	0.78**	REOSAVI	0.57**	EVI	0.46**	MTVI	0.80**	Viopt	-0.26**

波段 Band	con	cor	dis	ent	hom	mean	sm	var
B	-0.22**	0.21**	-0.25**	-0.24**	0.26**	-0.05	0.25**	-0.16**
G	-0.22**	-0.58**	-0.22**	-0.16**	0.22**	-0.32**	0.16**	-0.20**
R	-0.33**	0.09	-0.36**	-0.38**	0.36**	-0.22*	0.37**	-0.33**
Rededge	-0.08	-0.63**	-0.07	0.04	0.06	0.05	-0.05	-0.06
Nir	0.12*	-0.56**	0.11*	0.40**	-0.20**	0.79**	-0.39**	0.21**

方法Method	数据Dataset	R²	RMSE (%)	MAE (%)
BP	训练集Training dataset	0.84	0.40	0.30
BP	测试集Test dataset	0.71	0.48	0.37
RF	训练集Training dataset	0.96	0.17	0.13
RF	测试集Test dataset	0.81	0.42	0.29
Adaboost	训练集Training dataset	1.00	0.02	0.01
Adaboost	测试集Test dataset	0.79	0.44	0.32
SVR	训练集Training dataset	0.70	0.52	0.40
SVR	测试集Test dataset	0.66	0.54	0.40

UAV Multispectral Image-Based Nitrogen Content Prediction and the Transferability Analysis of the Models in Winter Wheat Plant

RichHTML

PDF

Abstract

Cite this article

share this article

Figures/Tables 11

References 79

Related Articles 15

Metrics

Comments

Recommended 0

[1]	FENG ZiHeng,SONG Li,ZHANG ShaoHua,JING YuHang,DUAN JianZhao,HE Li,YIN Fei,FENG Wei. Wheat Powdery Mildew Monitoring Based on Information Fusion of Multi-Spectral and Thermal Infrared Images Acquired with an Unmanned Aerial Vehicle [J]. Scientia Agricultura Sinica, 2022, 55(5): 890-906.
[2]	WANG ShuTing,KONG YuGuang,ZHANG Zan,CHEN HongYan,LIU Peng. SPAD Value Inversion of Cotton Leaves Based on Satellite-UAV Spectral Fusion [J]. Scientia Agricultura Sinica, 2022, 55(24): 4823-4839.
[3]	MA Xiao,CHEN PengFei. Improvement of Row Detection Method Before Wheat Canopy Closure Using Multispectral Images of UAV Image [J]. Scientia Agricultura Sinica, 2022, 55(20): 3926-3938.
[4]	ZHOU Meng,HAN XiaoXu,ZHENG HengBiao,CHENG Tao,TIAN YongChao,ZHU Yan,CAO WeiXing,YAO Xia. Remote Sensing Estimation of Cotton Biomass Based on Parametric and Nonparametric Methods by Using Hyperspectral Reflectance [J]. Scientia Agricultura Sinica, 2021, 54(20): 4299-4311.
[5]	FEI ShuaiPeng,YU XiaoLong,LAN Ming,LI Lei,XIA XianChun,HE ZhongHu,XIAO YongGui. Research on Winter Wheat Yield Estimation Based on Hyperspectral Remote Sensing and Ensemble Learning Method [J]. Scientia Agricultura Sinica, 2021, 54(16): 3417-3427.
[6]	LI MeiXuan,ZHU XiCun,BAI XueYuan,PENG YuFeng,TIAN ZhongYu,JIANG YuanMao. Remote Sensing Inversion of Nitrogen Content in Apple Canopy Based on Shadow Removal in UAV Multi-Spectral Remote Sensing Images [J]. Scientia Agricultura Sinica, 2021, 54(10): 2084-2094.
[7]	FengZhi SHI,RuiYan WANG,YuHuan LI,Hong YAN,XiaoXin ZHANG. LAI Estimation Based on Multi-Spectral Remote Sensing of UAV and Its Application in Saline Soil Improvement [J]. Scientia Agricultura Sinica, 2020, 53(9): 1795-1805.
[8]	ZHAO Jing,LI ZhiMing,LU LiQun,JIA Peng,YANG HuanBo,LAN YuBin. Weed Identification in Maize Field Based on Multi-Spectral Remote Sensing of Unmanned Aerial Vehicle [J]. Scientia Agricultura Sinica, 2020, 53(8): 1545-1555.
[9]	ZHANG ZhenHua,DING JianLi,WANG JingZhe,GE XiangYu,WANG JinJie,TIAN MeiLing,ZHAO QiDong. Digital Soil Properties Mapping by Ensembling Soil-Environment Relationship and Machine Learning in Arid Regions [J]. Scientia Agricultura Sinica, 2020, 53(3): 563-573.
[10]	WANG KeJian,LI Li,LÜ Qiang,YI ShiLai,ZHENG YongQiang,XIE RangJin,MA YanYan,HE ShaoLan,DENG Lie. UAV Spray Technology for the Citrus Orchard: Taking Control of the Diaphorina citri and Phyllocnistis citrella as Examples [J]. Scientia Agricultura Sinica, 2020, 53(17): 3509-3517.
[11]	GONG ChangWei,MA Yu,YANG Rui,RUAN YanWei,WANG XueGui,LIU Yue. Effect of Nozzle Type on the Spray Performance of Plant Protection Unmanned Aerial Vehicle (UAV) [J]. Scientia Agricultura Sinica, 2020, 53(12): 2385-2398.
[12]	LIU HuiFang,HE Zheng,JIA Biao,LIU Zhi,LI ZhenZhou,FU JiangPeng,MU RuiRui,KANG JianHong. Photosynthetic Response Characteristics of Maize Under Drip Irrigation Based on Machine Learning [J]. Scientia Agricultura Sinica, 2019, 52(17): 2939-2950.
[13]	CHEN PengFei, LIANG Fei. Cotton Nitrogen Nutrition Diagnosis Based on Spectrum and Texture Feature of Images from Low Altitude Unmanned Aerial Vehicle [J]. Scientia Agricultura Sinica, 2019, 52(13): 2220-2229.
[14]	ZHANG ChunLan, YANG GuiJun, LI HeLi, TANG FuQuan, LIU Chang, ZHANG LiYan. Remote Sensing Inversion of Leaf Area Index of Winter Wheat Based on Random Forest Algorithm [J]. Scientia Agricultura Sinica, 2018, 51(5): 855-867.
[15]	WANG Fei,YANG ShengTian,WEI Yang,YANG XiaoDong,DING JianLi. Influence of Sub-Region Priority Modeling Constructed by Random Forest and Stochastic Gradient Treeboost on the Accuracy of Soil Salinity Prediction in Oasis Scale [J]. Scientia Agricultura Sinica, 2018, 51(24): 4659-4676.