Detection of wheat powdery mildew based on hyperspectral reflectance through SPA and PLS-LDA

Imran Haider Khan, Haiyan Liu, Tao Cheng, YongChao Tian, Qiang Cao, Yan Zhu, Weixing Cao, Xia Yao

Abstract


Abstract: The accurate recognition and quantitative assessment at the early stage of wheat powdery mildew (Blumeria graminis f. sp. tritici) are vital for precision crop management for spraying the fungicides, reducing the cost, protecting the environment and enhancing the quality of crop.  However, early disease detection remained highly difficult due to the subtle changes in the physiology and phenology of the plants at early infection stage.  In this study, two wheat cultivars with different disease resistances were inoculated by the powdery mildew, hyperspectral reflectance and physiological parameters of leaves were obtained after inoculation at early stem elongation stage.  The major contribution of this study is to extract sensitive wavebands and vegetation indices using sub-window permutation analysis (SPA) by fully exploiting the hyperspectral data for early disease identification.  Extracted sensitive features by SPA were then used as input in partial least squares-linear discriminant analysis (PLS-LDA) recognition model to classify the healthy and diseased wheat leaves.  Finally, validation was carried out with independent data to verify the accuracy of the recognition model.  The results indicated that (1) the pigment contents and photosynthetic capacity were changed slightly at the early infection stage but decreased rapidly with the aggravation of the disease severity; (2) the visible and the near infrared bands were the most sensitive to the disease at early infection stage; (3) the overall accuracy of the PLS-LDA model constructed with the sensitive features extracted by SPA method performed better than features selected conventionally by correlation analysis.  The calibration and validation accuracies at 5% disease severity were 85.12 and 84.43% for model based on wavelength features and were 82.14 and 85.63 for model constructed with spectral indices features extracted by SPA, respectively.  In conclusion, SPA is a new effective strategy for feature selection which has not been yet used in plant disease research, having the benefit of considering cooperative effect among different variables and demonstrated the potential of early disease detection.  Such a technique can be an efficient and economical substitute to conventional methods, especially in case of high throughput hyperspectral crop sensing.

Keywords: wheat powdery mildew, early detection, hyperspectral reflectance, fungicide spraying, sub-window permutation analysis (SPA), PLS-LDA

DOI: 10.33440/j.ijpaa.20200301.67

 

Citation: Khan I H, Liu H Y, Cheng T, Tian Y C, Cao Q, Zhu Y, Cao W X, Yao X.  Detection of wheat powdery mildew based on hyperspectral reflectance through SPA and PLS-LDA.  Int J Precis Agric Aviat, 2020; 3(1): 13–22.


Full Text:

PDF

References


Huang L, Ding W, Liu W, Zhao J, Huang W, Xu C, Zhang D, Liang D. Identification of wheat powdery mildew using in-situ hyperspectral data and linear regression and support vector machines. Journal of Plant Pathology, 2019; 101(4): 1–11. doi: 10.1007/s42161-019-00334-2.

Mohd Asaari M S, Mishra P, Mertens S, Dhondt S, Inzé D, Wuyts N, Scheunders P. Close-range hyperspectral image analysis for the early detection of stress responses in individual plants in a high-throughput phenotyping platform. ISPRS journal of photogrammetry and remote sensing, 2018; 138: 121–138. doi: 10.1016/j.isprsjprs.2018.02.003.

Christ B J, Petersen G, Ressler L, Warmer E. Early detection of potato late blight using hyperspectral remote sensing, 2000.

Rumpf T, Mahlein A K, Steiner U, Oerke E C, Dehne H W, Plümer L. Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance. Computers and electronics in agriculture, 2010; 74(1): 91–99. doi: 10.1016/j.compag.2010.06.009.

Lorenzen B, Jensen A. Changes in leaf spectral properties induced in barley by cereal powdery mildew. Remote Sensing of Environment, 1989; 27(2): 201–209. doi: 10.1016/0034-4257(89)90018-7.

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. Central European Journal of Biology, 2006; 1(2): 275–288. doi: 10.2478/s11535-006-0020-8.

Baret F, Vanderbilt V C, Steven M D, Jacquemoud S. Use of spectral analogy to evaluate canopy reflectance sensitivity to leaf optical properties. Remote Sensing of Environment, 1994; 48(2): 253–260. doi: 10.1016/ 0034-4257(94)90146-5.

Feng W, Wang X Y, Song X, He L, Wang C, Guo T. Hyperspectral estimation of canopy chlorophyll density in winter wheat under stress of powdery mildew. Transactions of the Chinese Society of Agricultural Engineering, 2013; 29(13): 114–123. doi: 10.3969/ j.issn.1002-6819.2013.13.016.

Miller J R, Wu J, Boyer M G, Belanger M, Hare E W. Seasonal patterns in leaf reflectance red-edge characteristics. International Journal of Remote Sensing, 1991; 12(7): 1509–1523. doi: 10.1080/ 01431169108955186.

Devadas R, Lamb D W, Simpfendorfer S, Backhouse D. Evaluating ten spectral vegetation indices for identifying rust infection in individual wheat leaves. Precision Agriculture, 2009; 10(6): 459–470. doi: 10.1007/ s11119-008-9100-2.

Huang W, Lamb D W, Niu Z, Zhang Y , Liu L , Wang J . Identification of yellow rust in wheat using in-situ spectral reflectance measurements and airborne hyperspectral imaging. Precision Agriculture, 2007; 8(4): 187–197. doi: 10.1007/s11119-007-9038-9.

Huang W, Guan Q, Luo J, Zhang J, Zhao J, Liang D, Huang L, Zhang D. New optimized spectral indices for identifying and monitoring winter wheat diseases. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014; 7(6): 2516–2524. doi: 10.1109/JSTARS.2013.2294961.

Mahlein A K, Rumpf T, Welke P, Dehne H W, Plümer L, Steiner U, Oerke E C. Development of spectral indices for detecting and identifying plant diseases. Remote Sensing of Environment, 2013; 128: 21–30. doi: 10.1016/j.rse.2012.09.019.

Zheng Q, Huang W, Cui X, Dong Y, Shi Y, Ma H, Liu L. Identification of wheat yellow rust using optimal three-band spectral indices in different growth stages. Sensors, 2019; 19(1): 35. doi: 10.3390/s19010035.

Zhang J C, Pu R L, Wang J H, Huang W J, Yuan L, Luo J H. Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements. Computers and Electronics in Agriculture, 2012; 85: 13–23. doi: 10.1016/j.compag.2012.03.006.

Cao X, Luo Y, Zhou Y, Duan X, Cheng D. Detection of powdery mildew in two winter wheat cultivars using canopy hyperspectral reflectance. Crop Protection, 2013; 45: 124–131. doi: 10.1016/j.cropro.2012.12.002.

Sankaran S, Mishra A, Ehsani R, Davis C. A review of advanced techniques for detecting plant diseases. Computers and Electronics in Agriculture, 2010; 72(1): 1–13. doi: 10.1016/j.compag.2010.02.007.

Liu Z Y, Huang J F, Shi J J, Tao R X, Zhou W, Zhang L L. Characterizing and estimating rice brown spot disease severity using stepwise regression principal component regression and partial least-square regression. Journal of Zhejiang University Science B, 2007; 8(10): 44–50. doi: 10.1631/jzus.2007.B0738.

Liu Z Y, Qi J G, Wang N N, Zhu Z R, Luo J, Liu L J, Tang J, Cheng J A. Hyperspectral discrimination of foliar biotic damages in rice using principal component analysis and probabilistic neural network. Precision Agriculture, 2018; 19: 973–991. doi: 10.1007/s11119-018-9567-4.

Cheng T, Rivard B, Sánchez-Azofeifa G A, Feng J, Calvo-Polanco M. Continuous wavelet analysis for the detection of green attack damage due to mountain pine beetle infestation. Remote Sensing of Environment, 2010; 114(4): 899–910. doi: 10.1016/j.rse.2009.12.005.

Shi Y, Huang W, González-Moreno P, Luke B, Dong Y, Zheng Q, Ma H, Liu L. 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 Sensing, 2018; 10(4): 525. doi: 10.3390/rs10040525.

Muhammed H H. Hyperspectral crop reflectance data for characterising and estimating fungal disease severity in wheat. Biosystems Engineering, 2005; 91(1): 9–20. doi: 10.1016/j.biosystemseng.2005.02.007.

Muhammed H H, Larsolle A. Feature vector based analysis of hyperspectral crop reflectance data for discrimination and quantification of fungal disease severity in wheat. Biosystems engineering, 2003; 86(2): 125–134. doi: 10.1016/S1537-5110(03)00090-4.

Moshou D, Bravo C, West J, Wahlen S, McCartney A, Ramon H. Automatic detection of ‘yellow rust’in wheat using reflectance measurements and neural networks. Computers and electronics in agriculture, 2004; 44(3): 173–188. doi: 10.1016/j.compag.2004.04.003.

Moshou D, Bravo C, Oberti R, West J, Bodria L, McCartney A, Ramon H. Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps. Real-Time Imaging, 2005; 11(2): 75–83. doi: 10.1016/j.rti.2005.03.003.

Yuan L, Zhang J, Zhao J, Huang L, Yang X, Wang J. Mapping of powdery mildew using multi-spectral HJ-CCD image in Beijing suburban area. Optik-International Journal for Light and Electron Optics, 2013; 124(21): 4734–4738. doi: 10.1016/j.ijleo.2013.01.103.

Li H D, Liang Y Z, Xu Q S, Cao D S. Model population analysis for variable selection. Journal of Chemometrics, 2010; 24(7-8): 418–423. doi: 10.1002/cem.1300.

Sun T, Wu Y, Li X. Discrimination of camellia oil adulteration by NIR spectra and subwindow permutation analysis. Acta Optica Sinica, 2015; 35(6): 350–370. doi: 10.3788/AOS201535.0630005. (in Chinese).

Wang Q, Li H D, Xu Q S, Liang Y Z. Noise incorporated subwindow permutation analysis for informative gene selection using support vector machines. The Analyst, 2011; 136(7): 1456–1463. doi: 10.1039/c0an00667j.

Li H D, Zeng M M, Tan B B, Liang Y Z, Xu Q S, Cao D S. Recipe for revealing informative metabolites based on model population analysis. Metabolomics, 2010; 6(3): 353–361. doi: 10.1007/s11306-010-0213-z.

Hatchell D C. ASD Technical guide. Analytical Spectral Devices Inc, 1999; 5335.

Lichtenthaler H K. Chlorophylls and carotenoids: pigments of photosynthetic biomembranes. Methods in enzymology, 1987; 148: 350–382. doi: 10.1016/0076-6879(87)48036-1.

Thenkabail P S, Smith R B, Pauw E D. Hyperspectral vegetation indices and their relationships with agricultural crop characteristics. Remote sensing of Environment, 2000; 71(2): 158–182. doi: 10.1016/s0034-4257(99)00067-x.

Broge N H, Leblanc E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote sensing of environment, 2001; 76(2): 156–172. doi: 10.1016/s0034-4257(00)00197-8.

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.

Kim M S, Daughtry C S T, Chappelle E W, McMurtrey J E, Walthall C L. The use of high spectral resolution bands for estimating absorbed photosynthetically active radiation (A par), 1994.

Haboudane D, Miller J R, Tremblay N, Zarco-Tejada P J, Dextraze L. 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. doi: 10.1016/s0034-4257(02)00018-4.

Daughtry C S T, Walthall C L, Kim M S, De Colstoun E B, McMurtrey Iii 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.

Merton R, Huntington J. Early simulation results of the ARIES-1 satellite sensor for multi-temporal vegetation research derived from AVIRIS, 1999; 9–11.

Merzlyak M N, Gitelson A A, Chivkunova O B, Rakitin V Y U. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening. Physiologia plantarum, 1999; 106(1): 135–141. doi: 10.1034/j.1399-3054.1999.106119.x.

Gitelson A A, Merzlyak M N, Chivkunova O B. Optical properties and nondestructive estimation of anthocyanin content in plant leaves. Photochemistry and photobiology, 2001; 74(1): 38–45. doi: 10.1562/ 0031-8655(2001)074<0038:opaneo>2.0.co;2.

Penuelas J, Baret F, Filella I. Semi-empirical indices to assess carotenoids/chlorophyll a ratio from leaf spectral reflectance. Photosynthetica, 1995; 31(2): 221–230.

Peñuelas J, Gamon J A, Fredeen A L, Merino J, Field C B. Reflectance indices associated with physiological changes in nitrogen-and water-limited sunflower leaves. Remote sensing of Environment, 1994; 48(2): 135–146. doi: 10.1016/0034-4257(94)90136-8.

Gong P, Pu R, Heald R C. Analysis of in situ hyperspectral data for nutrient estimation of giant sequoia. International Journal of Remote Sensing, 2002; 23(9): 1827–1850. doi: 10.1080/01431160110075622.

Barker M, Rayens W. Partial least squares for discrimination. Journal of Chemometrics: A Journal of the Chemometrics, 2003; 17(3): 166–173. doi: 10.1002/cem.785.

Peñuelas J, Filella I. Visible and near-infrared reflectance techniques for diagnosing plant physiological status. Trends in plant science, 1998; 3(4): 151–156. doi: 10.1016/S1360-1385(98)01213-8.

Cao X, Zhou Y, Duan X, Cheng D. Relationships between canopy reflectance and chlorophyll contents of wheat infected with powdery mildew in fields. Acta Phytopathologica Sinica, 2009; 39(3): 290–296. doi: CNKI:SUN:ZWBL.0.2009-03-010. (in Chinese)

Wang X, Feng W, Yang Y, Hou C, Wang C, Guo T. Relationship of physiological indices and yield loss of wheat with severity level of powdery mildew. Journal of Triticeae Crops, 2012; 32(6): 1192–1198. doi: 10.7606/j.issn.1009-1041.2012.06.032. (in Chinese)

Li Y R, Shang H S. Changes in water relations of wheat leaves in the infection process of stripe rust. Acta Phytopathologica Sinica, 2000; 26(6): 471–475. doi: 10.3321/j.issn:1671-3877.2000.06.002. (in Chinese)

Wang B H, Huang M Y, Ma Z H, Wang J H. Effects of stripe rust on chlorophyll fluorescence and photosynthesis of winter wheat. Acta Agriculturae Boreali—Sinica, 2004; 19(2): 92–94. doi: 10.3321/j.issn:1000-7091.2004.02.023. (in Chinese)

Duniway J M, Durbin R D. Some effects of Uromyces phaseoli on the transpiration rate and stomatal response of bean leaves. Phytopathology, 1971; 61(1): 114–119. doi: 10.1094/Phyto-61-114.

Smith R C G, Heritage A D, Stapper M, Barrs H.D. Effect of stripe rust (Puccinia striiformis West.) and irrigation on the yield and foliage temperature of wheat. Field Crops Research, 1986; 14(1): 39–51. doi: 10.1016/0378-4290(86)90045-6.

Huang M Y, Wang J H, Huang W J, Huang Y D, Zhao C J, Wan A M. Hyperspectral character of stripe rust on winter wheat and monitoring by remote sensing. Transactions of the CSAE, 2003; 19(6) 154–158. doi: 10.3321/j.issn:1002-6819.2003.06.037. (in Chinese)

Chen B, Wang K, Li S, Jin X, Chen J, Zhang D. The effects of disease stress on spectra reflectance and chlorophyll fluorescence characteristics of cotton leaves. Transactions of the CSAE, 2011; 27(9): 86–93. doi: 10.3969/j.issn.1002-6819.2011.09.017. (in Chinese)

Liu L, Song X, Li C, Qi L, Huang W, Wang J. Monitoring and evaluation of the diseases of and yield winter wheat from multi-temporal remotely-sensed data. Transactions of the CSAE, 2009; 25(1): 137–143. doi: CNKI:SUN:NYGU.0.2009-01-033. (in Chinese)

[56] Guo J B, Huang C, Wang H G, Sun Z Y, Ma Z H. Disease index inversion of wheat stripe rust on different wheat varieties with hyperspectral remote sensing. Spectroscopy and Spectral Analysis, 2009; 29(12): 3353–3357. doi: 10.3964/j.issn.1000-0593(2009)12-3353-05. (in Chinese)

Zhang D Y, Zhang J C, Huang W J. Investigation of the hyperspectral image characteristics of wheat leaves under different stress. Spectroscopy and Spectral Analysis, 2011; 31(4): 1101–1105. doi: 10.3964/ j.issn.1000-0593(2011)04-1101-05. (in Chinese)

Jing X, Huang W J. Hyperspectral inversion models on verticillium wilt severity of cotton leaf. Spectroscopy and Spectral Analysis, 2009; 29(12): 3348–3352. doi: 10.3964/j.issn.1000-0593(2009)12-3348-05. (in Chinese)

Cheng S X, Shao Y N, Wu D, He Y. Determination of rice leaf blast disease level based on visible near infrared spectroscopy. Journal of Zhejiang University (Agriculture and Life Sciences), 2011; 37(3): 307–311. doi: 10.3785/j.issn.1008-9209 .2011 .03.011. (in Chinese)

Bushnell W R. Structural and physiological alterations in susceptible host tissue. The cereal rusts, 1984; 1: 477–507. doi: 10.1016/ B978-0-12-148401-9.50021-2.


Refbacks

  • There are currently no refbacks.