Advertisement

Journal of Plant Pathology

, Volume 101, Issue 4, pp 1035–1045 | Cite as

Identification of wheat powdery mildew using in-situ hyperspectral data and linear regression and support vector machines

  • Linsheng Huang
  • Wenjuan Ding
  • Wenjing Liu
  • Jinling ZhaoEmail author
  • Wenjiang Huang
  • Chao Xu
  • Dongyan Zhang
  • Dong Liang
Original Article
  • 102 Downloads

Abstract

To fully understand the spectral response characteristics of powdery mildew (PM) on winter wheat, in-situ hyperspectral data were collected and comparatively analyzed. The center distance method was first used to remove the abnormal spectral response bands using the red-edge position. Subsequently, the Relief-F algorithm and correlation analysis were jointly introduced to identify the best bands sensitive to the PM. The 636 nm in the visible region and the 784 nm in the near-infrared region were finally assured to develop a new vegetation index (NDVI1) according to the generation mechanism of normalized difference vegetation index (NDVI). Besides, a total of ten other vegetation indices commonly used in previous studies were calculated for comparatively evaluating the performance of NDVI1. Two types of sample data (only diseased samples, and both diseased and healthy samples) and three classifiers were comparatively used to estimate the disease, including a linear regression, support vector machine (SVM) and least squares support vector machine (LS-SVM) models. The results show that the linear regression model based on the NDVI1 except for the Modified Simple Ratio (MSR) is generally the best for the two sample types, giving a coefficient of determination (R2) of 0.75 and 0.49, respectively. Conversely, the SVM and LS-SVM models provide the best estimation accuracy using the K-fold cross-validation. In general, the overall classification accuracy of the SVM is higher than that of the LS-SVM, but the LS-SVM is more efficient regarding running time. The results of this study can provide a useful guideline for wheat PM estimation using the ground-based hyperspectral data.

Keywords

Hyperspectral remote sensing Relief-F Wheat powdery mildew SVM LS-SVM 

Notes

Acknowledgements

The work presented here was supported by Anhui Provincial Science and Technology Project (16030701091), Anhui Provincial Natural Science Foundation (1608085MF139) and National Natural Science Foundation of China (61661136004).

Funding

This study was funded by Anhui Provincial Science and Technology Project (grant number 16030701091).

Compliance with ethical standards

Conflict of interest

Linsheng Huang declares that he has no conflict of interest. Wenjuan Ding declares that she has no conflict of interest. Wenjing Liu declares that she has no conflict of interest. Jinling Zhao declares that he has no conflict of interest. Wenjiang Huang declares that he has no conflict of interest. Chao Xu declares that he has no conflict of interest. Dongyan Zhang declares that he has no conflict of interest. Dong Liang declares that he has no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

References

  1. Adankon MM, Cheriet M (2009) Model selection for the LS-SVM. Application to handwriting recognition. Pattern Recogn 42:3264–3270Google Scholar
  2. Anguita D, Ghio A, Oneto L, Ridella S (2012) In-sample and out-of-sample model selection and error estimation for support vector machines. IEEE T Neur Net Lear 23:1390–1406Google Scholar
  3. Apan A, Held A, Phinn S, Markley J (2004) Detecting sugarcane ‘orange rust’ disease using EO-1 Hyperion hyperspectral imagery. Int J Remote Sens 25:489–498Google Scholar
  4. Asaari MSM, Mishra P, Mertens S, Dhondt S, Inzé D, Wuyts N, Scheunders P (2018) Close-range hyperspectral image analysis for the early detection of stress responses in individual plants in a high-throughput phenotyping platform. ISPRS J Photogramm 138:121–138Google Scholar
  5. Ashourloo D, Aghighi H, Matkan AA, Mobasheri MR, Rad AM (2016) An investigation into machine learning regression techniques for the leaf rust disease detection using hyperspectral measurement. IEEE J Sel Top Appl Earth Observ Remote Sens 9:4344–4351Google Scholar
  6. Bioucas-Dias JM, Plaza A, Camps-Valls G, Scheunders P, Nasrabadi N, Chanussot J (2013) Hyperspectral remote sensing data analysis and future challenges. IEEE Geosc Rem Sen M 1:6–36Google Scholar
  7. Cao X, Luo Y, Zhou Y, Duan X, Cheng D (2013) Detection of powdery mildew in two winter wheat cultivars using canopy hyperspectral reflectance. Crop Prot 45:124–131Google Scholar
  8. Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM T Intel Sys Tec 2:27Google Scholar
  9. Chen D, Shi Y, Huang W, Zhang J, Wu K (2018) Mapping wheat rust based on high spatial resolution satellite imagery. Comput Electron Agric 152:109–116Google Scholar
  10. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297Google Scholar
  11. Cui D, Zhang Q, Li M, Hartman GL, Zhao Y (2010) Image processing methods for quantitatively detecting soybean rust from multispectral images. Biosyst Eng 107:186–193Google Scholar
  12. Curran PJ, Dungan JL, Macler BA, Plummer SE (1991) The effect of a red leaf pigment on the relationship between red edge and chlorophyll concentration. Remote Sens Environ 35:69–76Google Scholar
  13. Daughtry CST, Walthall CL, Kim MS, Colstoun EBD (2000) Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sens Environ 74:229–239Google Scholar
  14. Demir B, Ertürk S (2008) Phase correlation based redundancy removal in feature weighting band selection for hyperspectral images. Int J Remote Sens 29:1801–1807Google Scholar
  15. Dhau I, Adam E, Mutanga O, Ayisi KK (2018) Detecting the severity of maize streak virus infestations in maize crop using in situ hyperspectral data. T Roy Soc South Afr 73:8–15Google Scholar
  16. Er MJ, Wu S, Lu J, Toh HL (2002) Face recognition with radial basis function (RBF) neural networks. IEEE T Neural Networ 13:697–710Google Scholar
  17. Feng W, Yao X, Zhu Y, Tian YC, Cao WX (2008) Monitoring leaf nitrogen status with hyperspectral reflectance in wheat. Eur J Agron 28:394–404Google Scholar
  18. Filella I (1995) Evaluating wheat nitrogen status with canopy reflectance indices and discriminant analysis. Crop Sci 35:1400–1405Google Scholar
  19. Filella I, Peñuelas J (1994) The red-edge position and shape as indicators of plant chlorophyll content, biomass and hydric status. Int J Remote Sens 15:1459–1470Google Scholar
  20. Franke J, Menz G (2007) Multi-temporal wheat disease detection by multi-spectral remote sensing. Precis Agric 8:161–172Google Scholar
  21. Gamon JA, Penuelas J, Field CB (1992) A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sens Environ 41:35–44Google Scholar
  22. Ghiasi MM, Yarveicy H, Arabloo M, Mohammadi AH, Behbahani RM (2016) Modeling of stability conditions of clathrate hydrates using least squares support vector machine approach. J Mol Liq 223:1081–1092Google Scholar
  23. Gitelson AA, Merzlyak MN, Chivkunova OB (2001) Optical properties and nondestructive estimation of anthocyanin content in plant leaves. Photochem Photobiol 74:38–45PubMedGoogle Scholar
  24. Gold C, Sollich P (2002) Model selection for support vector machine classification. Neurocomputing 55:221–249Google Scholar
  25. Graeff S, Link J, Claupein W (2006) 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. Open Life Sci 1:275–288Google Scholar
  26. Griffey CA, Das MK, Stromberg EL (1993) Effectiveness of adult-plant resistance in reducing grain yield loss to powdery mildew in winter wheat. Plant Dis 77:618–622Google Scholar
  27. Haboudane D, Miller JR, Pattery E, Zarco-Tejada PJ, Strachan IB (2004) Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: modeling and validation in the context of precision agriculture. Remote Sens Environ 90:337–352Google Scholar
  28. Hsam SLK, Huang XQ, Ernst F, Hartl L, Zeller FJ (1998) Chromosomal location of genes for resistance to powdery mildew in common wheat (triticum aestivum l. em thell.). 5. alleles at the pm1 locus. Theor Appl Genet 96:1129–1134Google Scholar
  29. Hua W, Liu Z, Zhu J, Xie C, Yang T, Zhou Y, Duan X, Sun Q, Liu Z (2009) Identification and genetic mapping of pm42, a new recessive wheat powdery mildew resistance gene derived from wild emmer (Triticum turgidum var. dicoccoides). Theor Appl Genet 119:223–230PubMedGoogle Scholar
  30. Huang W, Davidw L, Zheng N, Zhang Y, Liu L, Wang J (2007) Identification of yellow rust in wheat using in-situ spectral reflectance measurements and airborne hyperspectral imaging. Precis Agric 8:187–197Google Scholar
  31. Huang W, Guan Q, Luo J, Zhang J, Zhao J, Liang D, Huang L, Zhang D (2014) New optimized spectral indices for identifying and monitoring winter wheat diseases. IEEE J Sel Top Appl Earth Observ Remote Sens 7:2516–2524Google Scholar
  32. Ilic M, Ilic S, Jovic S, Panic S (2018) Early cherry fruit pathogen disease detection based on data mining prediction. Comput Electron Agric 150:418–425Google Scholar
  33. Iosifidis A, Gabbouj M (2016) Multi-class support vector machine classifiers using intrinsic and penalty graphs. Pattern Recogn 55:231–246Google Scholar
  34. Jin X, Song K, Du J, Liu H, Wen Z (2017) Comparison of different satellite bands and vegetation indices for estimation of soil organic matter based on simulated spectral configuration. Agric For Meteorol 244:57–71Google Scholar
  35. Khan F, Enzmann F, Kersten M (2016) Multi-phase classification by a least-squares support vector machine approach in tomography images of geological samples. Solid Earth 7:481–492Google Scholar
  36. Mahlein AK, Rumpf T, Welke P, Dehne HW, Plümer L, Steiner U, Oerke EC (2013) Development of spectral indices for detecting and identifying plant diseases. Remote Sens Environ 128:21–30Google Scholar
  37. Masoni A, Ercoli L, Mariotti M (1996) Spectral properties of leaves deficient in iron, sulfur, magnesium, and manganese. Agron J 88:937–943Google Scholar
  38. Merton R, Huntington J (1999) Early simulation results of the Aries-1 satellite sensor for multi-temporal vegetation research derived from AVIRIS. Summaries of the Eight JPL airborne earth science workshop, Pasadena 1999:299–307Google Scholar
  39. Mewes T, Franke J, Menz G (2011) Spectral requirements on airborne hyperspectral remote sensing data for wheat disease detection. Precis Agric 12:795–812Google Scholar
  40. Muhammed HH (2005) Hyperspectral crop reflectance data for characterising and estimating fungal disease severity in wheat. Biosyst Eng 91:9–20Google Scholar
  41. Muhammed HH, Larsolle A (2003) Feature vector based analysis of hyperspectral crop reflectance data for discrimination and quantification of fungal disease severity in wheat. Biosyst Eng 86:125–134Google Scholar
  42. Pelckmans K, Suykens JA, Van Gestel T, De Brabanter J, Lukas L, Hamers B, De Moor B, Vandewalle J (2002) LS-SVMlab: a matlab/c toolbox for least squares support vector machines. Tutorial. KULeuven-ESAT, Leuven, BelgiumGoogle Scholar
  43. Penuelas J, Gamon JA, Fredeen AL, Merino J (1994) Reflectance indices associated with physiological changes in nitrogen- and water-limited sunflower leaves. Remote Sens Environ 48:135–146Google Scholar
  44. Penuelas J, Baret F, Filella I (1995) Semi-empirical indices to assess carotenoids/chlorophyll a ratio from leaf spectral reflectance. Photosynthetica 31:221–230Google Scholar
  45. Reyes O, Morell C, Ventura S (2015) Scalable extensions of the ReliefF algorithm for weighting and selecting features on the multi-label learning context. Neurocomputing 161:168–182Google Scholar
  46. Robnik-Šikonja M, Kononenko I (2003) Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn 53:23–69Google Scholar
  47. Rouse JW, Haas RH, Schell JA, Deering DW (1973) Monitoring vegetation systems in the great plains with ERTS. In: Freden SC, Mercanti EP, Becker MA (eds). The third previous ERTS Symposium, Washington 1973:309–317Google Scholar
  48. Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plümer L (2010) Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance. Comput Electron Agric 74:91–99Google Scholar
  49. Shi Y, Huang W, Zhou X (2017) Evaluation of wavelet spectral features in pathological detection and discrimination of yellow rust and powdery mildew in winter wheat with hyperspectral reflectance data. J Appl Remote Sens 11:026025Google Scholar
  50. Tsai F, Philpot W (1998) Derivative analysis of hyperspectral data. Remote Sens Environ 66:41–51Google Scholar
  51. Vapnik VN (1999) An overview of statistical learning theory. IEEE T Neural Networ 10:988–999Google Scholar
  52. Yang H, Zhang D, Huang L, Zhao Z (2014) Wavelet-based threshold denoising for imaging hyperspectral data. Int J Agric Biol Eng 7:36–42Google Scholar
  53. Zhang M, Qin Z, Liu X, Ustin SL (2003) Detection of stress in tomatoes induced by late blight disease in California, USA, using hyperspectral remote sensing. Int J Appl Earth Obs 4:295–310Google Scholar
  54. Zhang J, Pu R, Huang W, Yuan L, Luo J, Wang J (2012a) Using in-situ hyperspectral data for detecting and discriminating yellow rust disease from nutrient stresses. Field Crop Res 134:165–174Google Scholar
  55. Zhang J, Pu R, Wang J, Huang W, Yuan L, Luo JH (2012b) Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements. Comput Electron Agric 85:13–23Google Scholar
  56. Zhang J, Wang N, Yuan L, Chen F, Wu K (2017) Discrimination of winter wheat disease and insect stresses using continuous wavelet features extracted from foliar spectral measurements. Biosyt Eng 162:20–29Google Scholar
  57. Zhao JL, Zhao CJ, Hao Y, Zhang DY, Dong YY, Lin Y (2013) Identification and characterization of spectral response properties of rice canopy infested by leaf folder. Int J Agric Biol 15:694–700Google Scholar
  58. Zhu H, Chu B, Zhang C, Liu F, Jiang L, He Y (2017) Hyperspectral imaging for presymptomatic detection of tobacco disease with successive projections algorithm and machine-learning classifiers. Sci Rep 7:4125PubMedPubMedCentralGoogle Scholar
  59. Ziarko W (1993) Variable precision rough set model. J Comput Syst Sci 46:39–59Google Scholar

Copyright information

© Società Italiana di Patologia Vegetale (S.I.Pa.V.) 2019

Authors and Affiliations

  1. 1.National Engineering Research Center for Agro-Ecological Big Data Analysis & ApplicationAnhui UniversityHefeiChina
  2. 2.Key Laboratory of Digital Earth Sciences, Institute of Remote Sensing and Digital EarthChinese Academy of SciencesBeijingChina

Personalised recommendations