Welcome to Acta Agronomica Sinica,

Acta Agronomica Sinica ›› 2022, Vol. 48 ›› Issue (9): 2300-2314.doi: 10.3724/SP.J.1006.2022.11089

• TILLAGE & CULTIVATION·PHYSIOLOGY & BIOCHEMISTRY • Previous Articles     Next Articles

Hyperspectral remote sensing monitoring of wheat powdery mildew based on feature band selection and machine learning

FENG Zi-Heng1,2(), LI Xiao3,*(), DUAN Jian-Zhao2, GAO Fei4, HE Li2, YANG Tian-Chong2, RONG Ya-Si2, SONG Li2, YIN Fei1, FENG Wei2   

  1. 1. Information and Management Science College of Henan Agricultural University, Zhengzhou 450046, Henan, China
    2. Agronomy College of Henan Agriculture University / State Key Laboratory of Wheat and Maize Crop Science, Zhengzhou 450046, Henan, China
    3. College of Science, Henan Agricultural University, Zhengzhou 450046, Henan, China
    4. Plant Protection College of Henan Agricultural University, Zhengzhou 450046, Henan, China
  • Received:2021-10-12 Accepted:2022-02-25 Online:2022-09-12 Published:2022-03-15
  • Contact: LI Xiao E-mail:fzhfzh88@163.com;lixiao-1112@126.com
  • Supported by:
    National Natural Science Foundation of China(31971791);National Key Research and Development Program of China(2017YFD0301105)

Abstract:

Powdery mildew seriously harms wheat plant growth and restricts grain yield formation. In this regard, accurate monitoring powdery mildew is of great significance for the precise prevention and control and ensuring national food security. During the booting, anthesis and gain filling stages of wheat, wheat canopy spectrum data were obtained using a ground based hyperspectrometer, and the original spectrum was pretreated including first derivative, second derivative, logarithmic transformation, reciprocal transformation, and continuous removal method. The characteristic bands of five transformed spectral data and the OR data were extracted based on the combination of the CARS algorithm and the SPA algorithm. Finally, powdery mildew disease index (mDI) as a wheat monitoring model was established using Partial Least Squares Regression (PLSR), Ridge regression (RR), and Gaussian process regression (GPR). The results showed that the FD method gave the best comprehensive performance in Pearson correlation, two-band optimized combination, and machine learning technique, and it was a better preprocessing technique for processing of disease spectrum data. After spectral data transformation, the CARS-SPA combined algorithm could extract the characteristic bands more effectively, and the characteristic bands were 411, 450, 476, 543, 561, 594, 624, 671, 726, 780, 835, and 950 nm, respectively. Comparing all spectral preprocessing models and different machine learning methods, GPR model performed the best, followed by RR and PLSR methods. FD-GPR combined model generated the highest estimation accuracy, the averaged R2, RMSE, and MAE in the modeling set and the verification set under FD-GPR combination model were 0.805, 2.532, and 2.164 respectively, compared with the OR-GPR combined model. The averaged R2 increased by 12%, and the RMSE and MAE decreased by 19.6% and 17.6%, respectively, indicating that the GPR model had a good estimation ability to monitor wheat powdery mildew. In conclusion, using the FD method to preprocess the spectral data, the CARS-SPA combined algorithm to extract the characteristic bands, and the GPR method to build the estimated model, can improve the remote sensing monitoring accuracy of wheat powdery mildew. The research results provide ideas and methods for remote sensing monitoring of crop disease.

Key words: wheat powdery mildew, spectral transformation, feature band selection, machine learning, remote sensing monitoring

Fig. 1

Spatial layout of the experiment site"

Table 1

Statistical analysis of the disease indices measured at different growth stages and in different trials"

试验
Experiment
时期
Growth stage
平均值
Mean
最小值
Min.
最大值
Max.
标准差
Standard deviation
样本数量
Number of samples
试验1
Exp.1
孕穗期Booting 7.13 0 14.80 4.13 21
开花期Anthesis 11.05 0 20.70 5.22 44
灌浆期Filling 14.40 1.48 24.04 5.04 33
全生育期All stages 11.34 0 24.04 5.57 98
试验2
Exp.2
孕穗期Booting 7.13 0 14.59 5.01 10
开花期Anthesis 10.56 1.03 19.05 5.20 20
灌浆期Filling 12.89 3.04 23.36 5.29 17
全生育期All stages 10.67 0 23.36 5.51 47

Table 2

Common hyperspectral vegetation index used in this study"

植被指数
Vegetation index
公式
Formula
参考文献
Reference
PRI PRI=(R531-R570)/(R531+R570) [29]
RVSI RVSI=(R714+R752)/2-R733 [9]
SIPI SIPI=(R800-R445)/(R800+R680) [30]
ARI ARI=(R550)-1-(R700)-1 [31]
HI HI=(R534-R698)/(R534+R698)-0.5R704 [7]
PMI PMI=(R520-R584)/(R520+R584)+R724 [7]
NSRI NSRI=R890/R780 [32]
DGND DGND=(RD584×RH550-RD550×RH584)/(RD584×RH550+RD550×RH584) [8]
NDVI1 NDVI1=(R784-R636)/(R784+R636) [33]
RPMI RPMI=R744/R762-0.5R710 [34]

Fig. 2

Spectral reflectance changes under different disease indexes (a), spectral changes of different pretreatment methods (b), and correlation analysis (c)"

Fig. 3

Absolute values of correlation coefficients between spectral transform data and disease index"

Fig. 4

Two-band optimized combination based on the original spectrum, first-order derivative, and second-order derivative a-c: ND, SR, and SD based on OR; d-f: ND, SR, and SD based on FD; g-i: ND, SR, and SD based on SD."

Fig. 5

Two-band optimized combination based on the logarithmic, reciprocal and continuous removal method transformation A-c: ND, SR, and SD based on LOG; d-f: ND, SR, and SD based on 1/R; g-i: ND, SR, and SD based on CR."

Table 3

Optimized two-band combinations form and monitoring performance"

光谱变换Spectrum transform 归一化植被指数
Normalized difference
vegetation index (ND)
简单比值植被指数
Simple ratio vegetation index
(SR)
简单差值植被指数
Simple difference vegetation index (SD)
波段Wavelength R2 波段Wavelength R2 波段Wavelength R2
OR 786,785 0.398 786,785 0.398 450,444 0.462
FD 785,766 0.537 767,785 0.515 655,560 0.375
SD 705,691 0.298 749,691 0.344 709,664 0.392
LOG 450,444 0.430 444,450 0.430 786,785 0.398
1/R 786,785 0.398 785,786 0.398 786,785 0.384
CR 698,411 0.300 411,700 0.303 706,404 0.287

Table 4

Coefficient of determination (R2) between vegetation index and disease index at different growth stages"

植被指数
Vegetation index
孕穗期
Booting
开花期
Anthesis
灌浆期
Filling
全时期
All stages
PRI 0.329 0.452 0.392 0.329
RVSI 0.378 0.221 0.250 0.313
SIPI 0.314 0.281 0.280 0.283
ARI 0.358 0.432 0.470 0.276
HI 0.340 0.443 0.492 0.362
PMI 0.249 0.252 0.116 0.223
NSRI 0.219 0.492 0.154 0.303
DGND 0.453 0.624 0.533 0.604
RPMI 0.387 0.552 0.498 0.471
NDVI1 0.300 0.477 0.142 0.301

Fig. 6

Selection process of the feature bands (a), and specific bands selection (b) by CARS algorithm"

Fig. 7

Changes in the number of variables and RMSE (a), and optimal wavebands selected (b) using SPA algorithm"

Table 5

Selection of characteristic bands for different spectral transform data"

光谱变换
Spectrum transform
主要波段选择
Major band selection (CARS)
最佳波段选择
Optimum band selection (SPA)
OR 400, 422, 452, 453, 470, 473, 528, 529, 549, 574, 586, 604, 620, 621, 674, 680, 683, 725, 726, 728, 761, 768, 780, 783, 830, 947, 950, 962 400, 470, 529, 586, 604, 621, 674, 683, 728, 761, 783, 830, 947
FD 411, 412, 450, 451, 453, 470, 476, 488, 494, 543, 544, 561, 574, 594, 610, 624, 660, 671, 721, 726, 746, 780, 813, 824, 835, 862, 950 411, 450, 476, 543, 561, 594, 624, 671, 726, 780, 835, 950
SD 420, 435, 502, 526, 550, 576, 650, 686, 705, 718, 720, 745, 749, 760, 768, 880, 894, 896, 920, 940, 943, 974, 976, 980 435, 576, 686, 705, 720, 760, 880, 896, 820, 976, 980
LOG 423, 458, 466, 467, 471, 560, 564, 568, 569, 570, 623, 658, 659, 682, 706, 711, 743, 762, 765, 768, 770 423, 458, 471, 564, 623, 682, 711, 743, 765
1/R 423, 430, 470, 493, 500, 514, 520, 564, 566, 567, 568, 590, 592, 613, 634, 661, 662, 718, 722, 749, 750, 755, 757, 758, 769, 875, 886 423, 493, 520, 568, 568, 613, 634, 661, 722, 755, 875
CR 431, 471, 472, 499, 500, 501, 584, 610, 613, 637, 663, 679, 683, 719, 798, 819, 847, 851, 937, 938 431, 472, 501, 584, 637, 719, 798, 812, 847, 938

Table 6

Performance of machine learning model based on the different spectral transformation input variable selection"

光谱变换Spectrum transform 变量个数Number of variables 模型算法Modeling method 建模集Calibration set 验证集Validation set
R2 RMSE MAE R2 RMSE MAE
OR 13 PLSR 0.684 3.317 2.734 0.676 3.303 2.713
RR 0.703 3.140 2.666 0.686 3.108 2.641
GPR 0.722 3.108 2.641 0.715 3.189 2.608
FD 12 PLSR 0.748 2.886 2.466 0.757 2.775 2.340
RR 0.789 2.710 2.319 0.782 2.737 2.357
GPR 0.806 2.635 2.303 0.804 2.429 2.024
SD 11 PLSR 0.702 3.187 2.712 0.687 3.298 2.725
RR 0.721 3.116 2.698 0.703 3.201 2.684
GPR 0.743 2.985 2.524 0.725 3.016 2.606
LOG 9 PLSR 0.647 3.765 3.365 0.629 3.796 3.385
RR 0.668 3.658 3.213 0.659 3.764 3.367
GPR 0.701 3.165 2.726 0.692 3.231 2.786
1/R 11 PLSR 0.642 3.748 3.327 0.635 3.783 3.363
RR 0.675 3.416 2.964 0.667 3.517 3.051
GPR 0.695 3.349 2.879 0.681 3.389 2.863
CR 10 PLSR 0.746 2.901 2.466 0.732 2.968 2.487
RR 0.751 2.853 2.319 0.741 2.916 2.423
GPR 0.764 2.785 2.303 0.756 2.814 2.379

Fig. 8

Test results of machine learning model based on the first derivative data transformation"

Fig. 9

Performance of three modelling approaches based on FD data transformation at different stages"

[1] Zhang N, Yang G, Pan Y, Yang X, Chen L, Zhao C. A review of advanced technologies and development for hyperspectral-based plant disease detection in the past three decades. Remote Sens, 2020, 12: 3188.
doi: 10.3390/rs12193188
[2] 黄文江, 师越, 董莹莹, 叶回春, 邬明权, 崔贝, 刘林毅. 作物病虫害遥感监测研究进展与展望. 智慧农业, 2019, 1(4): 1-11.
Huang W J, Shi Y, Dong Y Y, Ye H C, Wu M Q, Cui B, Liu L Y. Progress and prospects of crop diseases and pests monitoring by remote sensing. Smart Agric, 2019, 1(4): 1-11 (in Chinese with English abstract)
[3] Feng W, Qi S, Heng Y R, Zhou L, Wu Y P, Liu W D, He L, Li X. Canopy vegetation indices from in situ hyperspectral data to assess plant water status of winter wheat under powdery mildew stress. Front Plant Sci, 2017, 8: 1219.
doi: 10.3389/fpls.2017.01219 pmid: 28751904
[4] Shi Y, Huang W J, Gonzalez-Moreno P, Luke B, Dong Y, Zheng Q, Ma H Q, Liu L Y. Wavelet-based rust spectral feature set (WRSFs): a novel spectral feature set based on continuous wavelet transformation for tracking progressive host-pathogen interaction of yellow rust on wheat. Remote Sens, 2018, 10: 525.
doi: 10.3390/rs10040525
[5] 沈文颖, 李映雪, 冯伟, 张海艳, 张元帅, 谢迎新, 郭天财. 基于因子分析-BP神经网络的小麦叶片白粉病反演模型. 农业工程学报, 2015, 31(22): 183-190.
Shen W Y, Li Y X, Feng W, Zhang H Y, Zhang Y S, Xie Y X, Guo T C. Inversion model for severity of powdery mildew in wheat leaves based on factor analysis-BP neural network. Trans CSAE, 2015, 31(22): 183-190 (in Chinese with English abstract)
[6] Franceschini M, Bartholomeus H, Apeldoorn D F V, Suomalainen J, Kooistra L. Feasibility of unmanned aerial vehicle optical imagery for early detection and severity assessment of late blight in potato. Remote Sens, 2019, 11: 224.
doi: 10.3390/rs11030224
[7] Mahlein A K, Rumpf T, Welke P, Dehne H W, Plumer L, Steiner U, Oerke E C. Development of spectral indices for detecting and identifying plant diseases. Remote Sens Environ, 2013, 128: 21-30.
doi: 10.1016/j.rse.2012.09.019
[8] Feng W, Shen W, He L, Duan J Z, Guo B, Li Y, Wang C Y, Guo T. Improved remote sensing detection of wheat powdery mildew using dual-green vegetation indices. Prec Agric, 2016, 17: 608-627.
doi: 10.1007/s11119-016-9440-2
[9] Naidu R A, Perry E M, Pierce F J, Mekuria T. The potential of spectral reflectance technique for the detection of Grapevine leafroll associated virus-3 in two red-berried wine grape cultivars. Comput Electr Agric, 2009, 66: 38-45.
doi: 10.1016/j.compag.2008.11.007
[10] 兰玉彬, 朱梓豪, 邓小玲, 练碧桢, 黄敬易, 黄梓效, 胡洁. 基于无人机高光谱遥感的柑橘黄龙病植株的监测与分类. 农业工程学报, 2019, 35(3): 92-100.
Lan Y B, Zhu Z H, Deng X L, Lian B Z, Huang J Y, Huang Z X, Hu J. Monitoring and classification of citrus Huanglongbing based on UAV hyperspectral remote sensing. Trans CSAE, 2019, 35(3): 92-100 (in Chinese with English abstract)
[11] Izzuddin A. Analysis of airborne hyperspectral image using vegetation indices, red edge position and continuum removal for detection of ganoderma disease in oil palm. J Oil Palm Res, 2018, 30: 416-428.
[12] Zarco-Teja P J, Camino C, Beck P, Calderon R, Hornero A, Hernández-Clemente R, Kattenborn T, Montes-Borrego M, Susca L, Morelli M. Previsual symptoms of Xylella fastidiosa infection revealed in spectral plant-trait alterations. Nat Plants, 2018, 4: 432-439.
doi: 10.1038/s41477-018-0189-7 pmid: 29942047
[13] Poblete T, Camino C, Beck P, Hornero A, Zarco-Tejada P J. Detection of Xylella fastidiosa infection symptoms with airborne multispectral and thermal imagery: assessing bandset reduction performance from hyperspectral analysis. ISPRS J Photogr Remote Sens, 2020, 162: 27-40.
doi: 10.1016/j.isprsjprs.2020.02.010
[14] Ghosal S, Blystone D, Singh A K, Ganapathysubramanian B, Sarkar S. An explainable deep machine vision framework for plant stress phenotyping. Proc Natil Acad Sci USA, 2018, 115: 4613-4618.
doi: 10.1073/pnas.1716999115
[15] 肖文, 曹英丽, 冯帅, 刘亚帝, 江凯伦, 于正鑫, 闫丽. 基于分窗Gram-Schmidt变换和PSO-SVR算法的水稻纹枯病病情指数检测. 光谱学与光谱分析, 2021, 41: 2181-2187.
Xiao W, Cao Y L, Feng S, Liu Y D, Jiang K L, Yu Z X, Yan L. Detection of rice sheath blight disease index based on split-window gram-schmidt transformation and PSO-SVR algorithm. Spectr Spectr Anal, 2021, 41: 2181-2187 (in Chinese with English abstract)
[16] Moghaddam S, Mokhtarzade M, Beirami B A. A feature extraction method based on spectral segmentation and integration of hyperspectral images. Int J Appl Earth Observ Geoinform, 2020, 89: 102097.
[17] Huang Y, Li Z L, Risinger A L, Enslow B T, Zeman C J, Gong J, Yang Y J, Schanze K S. Fluorescence spectral shape analysis for nucleotide identification. Proc Natl Acad Sci USA, 2019, 116: 2018207113.
[18] Maimaitijiang M, Sagan V, Sidike P, Hartling S, Fritschi F B. Soybean yield prediction from UAV using multimodal data fusion and deep learning. Remote Sens Environ, 2019, 237: 111599.
[19] Hu Q, Sulla-Menashe D, Xu B D, Yin H, Tang H J, Yang P, Wu W B. A phenology-based spectral and temporal feature selection method for crop mapping from satellite time series. Int J Appl Earth Observ Geoinform, 2019, 80: 218-229.
doi: 10.1016/j.jag.2019.04.014
[20] Tian L, Xue B W, Wang Z Y, Li D, Yao X, Cao Q, Zhu Y, Cao W X, Cheng T. Spectroscopic detection of rice leaf blast infection from asymptomatic to mild stages with integrated machine learning and feature selection. Remote Sens Environ, 2021, 257: 112350.
[21] Feng W, Wu Y P, He L, Ren X, Wang Y, Hou G, Wang Y H, Liu W D, Guo T C. An optimized non-linear vegetation index for estimating leaf area index in winter wheat. Prec Agric, 2019, 20: 1157-1176.
doi: 10.1007/s11119-019-09648-8
[22] 中国农业科学院. 农作物病害遥感监测技术规范第二部分: 小麦白粉病. NY/T2738.2-2015, 2015.
Chinese Academy of Agricultural Sciences. Technical Specification on Remote Sensing Monitoring for Crop Diseases-Part 2: Wheat Powder Mildew, NY/T2738.2-2015, 2015. (in Chinese with English abstract)
[23] Hong G, El-Hamid H T. Hyperspectral imaging using multivariate analysis for simulation and prediction of agricultural crops in Ningxia, China. Comput Electr Agric, 2020, 172: 105355.
[24] Sun J, Zhou X, Hu Y, Wu X H, Zhang X D, Wang P. Visualizing distribution of moisture content in tea leaves using optimization algorithms and NIR hyperspectral imaging. Comput Electr Agric, 2019, 160: 153-159.
doi: 10.1016/j.compag.2019.03.004
[25] Jia M, Li W, Wang K, Zhou C, Tian Y C, Zhu Y, Cao W X, Yao X. A newly developed method to extract the optimal hyperspectral feature for monitoring leaf biomass in wheat. Comput Electr Agric, 2019, 165: 104942.
[26] Ramoelo A, Skidmore A K, Cho M A, Mathieu R, Heitkönig I, Dudeni-Tlhone N, Schlerf M, Prins H H T. Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data. ISPRS J Photogra Remote Sens, 2013, 82: 27-40.
doi: 10.1016/j.isprsjprs.2013.04.012
[27] Zandler H, Brenning A, Samimi C. Quantifying dwarf shrub biomass in an arid environment: comparing empirical methods in a high dimensional setting. Remote Sens Environ, 2015, 158: 140-155.
doi: 10.1016/j.rse.2014.11.007
[28] Fernández-Guisuraga J M, Verrelst J, Calvo L, Suárez-Seoane S. Hybrid inversion of radiative transfer models based on high spatial resolution satellite reflectance data improves fractional vegetation cover retrieval in heterogeneous ecological systems after fire. Remote Sens Environ, 2021, 255: 112304.
[29] Gamon J, Penuelas J, Field C. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sens Environ, 1992, 41(1): 35-44.
doi: 10.1016/0034-4257(92)90059-S
[30] Penuelas J, Frédéric B, Filella I. Semi-empirical indices to assess carotenoids/chlorophyll A ratio from leaf spectral reflectance. Photosynthetica, 1995, 31: 221-230.
[31] Gitelson A A, Merzlyak M N, Chivkunova O B. Optical properties and nondestructive estimation of anthocyanin content in plant leaves. Photochem Photobiol, 2010, 74: 38-45.
doi: 10.1562/0031-8655(2001)074<0038:OPANEO>2.0.CO;2
[32] Liu L, Huang W, Pu R, Wang J. Detection of internal leaf structure deterioration using a new spectral ratio index in the near-infrared shoulder region. J Integr Agric, 2014, 13: 760-769.
doi: 10.1016/S2095-3119(13)60385-8
[33] Huang L S, Ding W J, Liu W J, Zhao J L, Huang W J, Xu C, Zhang D Y, Liang D. Identification of wheat powdery mildew using in-situ hyperspectral data and linear regression and support vector machines. J Plant Pathol, 2019, 101: 1035-1045.
doi: 10.1007/s42161-019-00334-2
[34] He L, Qi S L, Duan J Z, Guo T C, Feng W, He D X. Monitoring of wheat powdery mildew disease severity using multiangle hyperspectral remote sensing. IEEE Trans Geosci Remot Sens, 2020, 59: 979-990.
doi: 10.1109/TGRS.2020.3000992
[35] 谢亚平, 陈丰农, 张竞成, 周斌, 王海江, 吴开华. 基于高光谱技术的农作物常见病害监测研究. 光谱学与光谱分析, 2018, 38: 2233-2240.
Xie Y P, Chen F N, Zhang J C, Zhou B, Wang H J, Wu K H. Study on monitoring of common diseases of crops based on hyperspectral technology. Spectr Spectr Anal, 2018, 38: 2233-2240 (in Chinese with English abstract)
[36] Graeff S, Link J, Claupein W. Identification of powdery mildew (Erysiphe graminis sp. tritici) and take-all disease (Gaeumannomyces graminis sp. tritici) in wheat (Triticum aestivum L.) by means of leaf reflectance measurements. Centr Eur J Biol, 2006, 1: 275-288.
[37] 冯伟, 王晓宇, 宋晓, 贺利, 王永华, 郭天财. 基于冠层反射光谱的小麦白粉病严重度估测. 作物学报, 2013, 39: 1469-1477.
Feng W, Wang X Y, Song X, He L, Wang Y H, Guo T C. Estimation of severity level of wheat powdery mildew based on canopy spectral reflectance. Acta Agron Sin, 2013, 39: 1469-1477 (in Chinese with English abstract)
doi: 10.3724/SP.J.1006.2013.01469
[38] 汪六三, 黄子良, 王儒敬. 基于近红外光谱和机器学习的大豆种皮裂纹识别研究. 农业机械学报, 2021, 52(6): 361-368.
Wang L S, Huang Z L, Wang R J. Identification of soybean seed coat crack based on near infrared spectroscopy and machine learning. Trans CSAM, 2021, 52(6): 361-368 (in Chinese with English abstract)
[39] 张娟娟, 席磊, 杨向阳, 许鑫, 郭伟, 程涛, 马新明. 砂姜黑土有机质含量高光谱估测模型构建. 农业工程学报, 2020, 36(17): 135-141.
Zhang J J, Xi L, Yang X Y, Xu X, Guo W, Cheng T, Ma X M. Construction of hyperspectral estimation model for organic matter content in Shajiang black soil. Trans CSAE, 2020, 36(17): 135-141 (in Chinese with English abstract)
[40] Gao J L, Meng B P, Liang T G, Feng Q S, Ge J, Yin J P, Wu C X, Cui X, Hou M J, Liu J, Xie H J. Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China. ISPRS J Photogr Remote Sens, 2019, 147: 104-117.
doi: 10.1016/j.isprsjprs.2018.11.015
[41] Jie P, Ju Y W, Zhang H, Wang X T. Detection of Bursaphelenchus xylophilus infection in Pinus massoniana from hyperspectral data. Nematology, 2014, 16: 1197-1207.
doi: 10.1163/15685411-00002846
[42] Zhao J, Fang Y, Chu G, Yan H, Hu L, Huang L. Identification of leaf-scale wheat powdery mildew (Blumeria graminis f. sp. tritici) Combining hyperspectral imaging and an SVM classifier. Plants, 2020, 9: 936.
doi: 10.3390/plants9080936
[43] Pane C, Manganiello G, Nicastro N, Cardi T, Carotenuto F. Powdery mildew caused by Erysiphe cruciferarum on wild rocket (Diplotaxis tenuifolia): hyperspectral imaging and machine learning modeling for non-destructive disease detection. Agriculture, 2021, 11: 337.
doi: 10.3390/agriculture11040337
[44] Yuan L, Huang Y B, Loraamm R W, Nie C W, Wang J H, Zhang J C. Spectral analysis of winter wheat leaves for detection and differentiation of diseases and insects. Field Crops Res, 2014, 156: 199-207.
doi: 10.1016/j.fcr.2013.11.012
[45] Zhang J, Cheng T, Guo W, Xu X, Qiao H B, Xie Y M, Ma X M. Leaf area index estimation model for UAV image hyperspectral data based on wavelength variable selection and machine learning methods. Plant Methods, 2021, 17: 49.
doi: 10.1186/s13007-021-00750-5
[46] 刘畅, 杨贵军, 李振海, 汤伏全, 王建雯, 张春兰, 张丽妍. 融合无人机光谱信息与纹理信息的冬小麦生物量估测. 中国农业科学, 2018, 51: 3060-3073.
Liu C, Yang G J, Li Z H, Tang F Q, Wang J W, Zhang C L, Zhang L Y. Biomass estimation in winter wheat by UAV spectral information and texture information fusion. Sci Agric Sin, 2018, 51: 3060-3073 (in Chinese with English abstract)
[47] Han Z, Deng L. Application driven key wavelengths mining method for aflatoxin detection using hyperspectral data. Comput Electr Agric, 2018, 153: 248-255.
doi: 10.1016/j.compag.2018.08.018
[48] Zheng Q, Huang W J, Cui X M, Shi Y, Liu L Y. New spectral index for detecting wheat yellow rust using sentinel-2 multispectral imagery. Sensors, 2018, 18: 868.
doi: 10.3390/s18030868
[49] Chan A, Barnes C, Swinfield T, Coomes D. Monitoring ash dieback (Hymenoscyphus fraxineus) in British forests using hyperspectral remote sensing. Remote Sens Ecol Conserv, 2020, 7: 306-320.
doi: 10.1002/rse2.190
[50] Xie R, Darvishzadeh R, Skidmore A K, Heurich M, Holzwarth S, Gara W, Reusen I. Mapping leaf area index in a mixed temperate forest using Fenix airborne hyperspectral data and Gaussian processes regression. Int J Appl Earth Observ Geoinform, 2021, 95: 102242.
[51] Verrelst J, Rivera-Caicedo P, Reyes-Muñoz P, Morata M, Amin E, Tagliabue G, Panigada C, Hank T, Berger K. Mapping landscape canopy nitrogen content from space using PRISMA data. ISPRS J Photogr Remote Sens, 2021, 178: 382-395.
doi: 10.1016/j.isprsjprs.2021.06.017
[1] LI Jin-Min, CHEN Xiu-Qing, YANG Qi, SHI Liang-Sheng. Deep learning models for estimation of paddy rice leaf nitrogen concentration based on canopy hyperspectral data [J]. Acta Agronomica Sinica, 2021, 47(7): 1342-1350.
[2] JING Xia, ZOU Qin, BAI Zong-Fan, HUANG Wen-Jiang. Research progress of crop diseases monitoring based on reflectance and chlorophyll fluorescence data [J]. Acta Agronomica Sinica, 2021, 47(11): 2067-2079.
[3] ZOU Jing-Wei,QIU Dan,SUN Yan-Ling,ZHENG Chao-Xing,LI Jing-Ting,WU Pei-Pei,WU Xiao-Fei,WANG Xiao-Ming,ZHOU Yang,LI Hong-Jie . Pm52: Effectiveness of the Gene Conferring Resistance to Powdery Mildew in Wheat Cultivar Liangxing 99 [J]. Acta Agron Sin, 2017, 43(03): 332-342.
[4] JIANG Yan-Tao,XU Tao,DUAN Xia-Yu*,ZHOU Yi-Lin. Effect of Variety Mixure Planting on Powdery Mildew Controlling as Well as Yield and Protein Contents in Common Wheat [J]. Acta Agron Sin, 2015, 41(02): 276-285.
[5] FENG Wei,WANG Xiao-Yu,SONG Xiao,HE Li,WANG Yong-Hua,GUO Tian-Cai. Estimation of Severity Level of Wheat Powdery Mildew Based on Canopy Spectral Reflectance [J]. Acta Agron Sin, 2013, 39(08): 1469-1477.
[6] XING Li-Ping,QIAN Chen,LI Ming-Hao,CAO Ai-Zhong,WANG Xiu-E,CHEN Pei-Du. Transformation of Antisense Wheat Mlo (Ta-Mlo) Gene and Wheat Powdery Mildew Resistance Analysis of Transgenic Plants [J]. Acta Agron Sin, 2013, 39(03): 431-439.
[7] LIU Zi-Ji, ZHU Jie, HUA Wei, YANG Zuo-Min, SUN Ji-Shen, LIU Zhi-Yong. Comparative Genomics Analysis and Constructing EST Markers Linkage Map of Powdery Mildew Resistance Gene pm42 in Wheat [J]. Acta Agron Sin, 2011, 37(09): 1569-1576.
[8] WANG Hua-Zhong, ZHANG Zhen, HE Xiang, YUE Ji-Yu. Dissecting and QTL Mapping of Component Traits of Resistance to Wheat Powdery Mildew at Early Infection Stage [J]. Acta Agron Sin, 2011, 37(07): 1219-1228.
[9] ZHANG Zhen, LIU Xin-Hong, CUI Hong-Cui, WANG Hua-Zhong. Primary Infection Suppression of Blumeria graminis f. sp. Tritici and Host Cell Responses Regulated by Pm21 Gene in Wheat [J]. Acta Agron Sin, 2011, 37(01): 67-73.
[10] CAO Shi-Qi,LUO Hui-Sheng,WU Cui-Peng,JIN he-Lin, ANG Xiao-Ming,ZHU Zhen-Dong,JIA Qiu-Zhen,HUANG Jin,ZHANG Bo,CHANG Xun-Wu. Postulation of Powder Mildew Resistance Genes in 64 Wheat Cultivars (Lines) in Gansu Province, China [J]. Acta Agron Sin, 2010, 36(12): 2107-2115.
[11] ZHANG Kun-Pu;ZHAO Liang;HAI Yan;CHEN Guang-Feng;TIAN Ji-Chun. QTL Mapping for Adult-Plant Resistance to Powdery Mildew, Lodging Resistance and Internode Length below Spike in Wheat [J]. Acta Agron Sin, 2008, 34(08): 1350-1357.
[12] WANG Zhen-Ying;ZHAO Hong-Mei;HONG Jing-Xin;CHEN Li-Yuan;ZHU Jie;LI Gang;PENG Yong-Kang;XIE Chao-Jie;LIU Zhi-Yong;SUN Qi-Xin;YANG Zuo-Min. Identification and Analysis of Four Novel Molecular Markers Linked to Powdery Mildew Resistance Gene Pm21 in 6VS Chromosome Short Arm of Haynaldia villosa [J]. Acta Agron Sin, 2007, 33(04): 605-611.
[13] GAO An-Li;HE Hua-Gang;CHEN Quan-Zhan;ZHANG Shou-Zhong;CHEN Pei-Du. Pyramiding Wheat Powdery Mildew Resistance Genes Pm2, Pm4a and Pm21 by Molecular Marker-assisted Selection [J]. Acta Agron Sin, 2005, 31(11): 1400-1405.
[14] Gao Shengguo. Identification and Analysis of Resistance of NAU 92R Wheat Lines [J]. Acta Agron Sin, 1999, 25(03): 389-391.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!