Skip to main content

Advertisement

SpringerLink
Log in

A hyperspectral GA-PLSR model for prediction of pine wilt disease

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Pine wilt disease caused by a forest-invasive alien species, the pine wood nematode (Bursaphelenchus xylophilus) is considered as one of the most destructive pest problems. In recent years, spectroscopic technologies have shown great potentials for the assessment of forest damage due to their nondestructive, noninvasive, cost-effective, and rapidly responsive nature. This paper first identified the hyperspectral characteristics of pine wilt disease by measuring and analyzing the changes in spectral reflectance of healthy and infected Pinus massoniana trees. Then 16 spectral features were extracted from the spectral bands covering the green region (510~580 nm), the red region (620~680 nm), the red edge (680~760 nm), the near-infrared region (780~1100 nm), and coded as genes composing the chromosome of a genetic algorithm (GA). Based on the optimal spectral features with suitable fitness from the GA, a partial least squares regression (PLSR) prediction model was built with highest determination coefficient R2c = 0.91, R2v = 0.82, relative prediction deviation RPD = 3.3 and lowest root mean square error RMSEc = 0.23, RMSEv = 0.33 on the calibration and validation datasets. Compared with other PLSR models, our proposed GA-based approach significantly improves the prediction accuracy with few input spectral features.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Abu-Kalaf N, Salman M (2014) Visible/near infrared(VIS/NIR) spectroscopy and multivariate data analysis (MVDA) for identification and quantification of olive leaf spot (OLS) disease. Palest Tech Univ Res J 2:(1):1–8

    Google Scholar 

  2. Bolón-Canedo V, Alonso-Betanzos A (2018) Recent advances in ensembles for feature selection. Springer, Berlin, Heidelberg

    Book  Google Scholar 

  3. Carnegie AJ, Venn T, Lawson S, Nagel M, Wardlaw T, Cameron N, Last I (2018) An analysis of pest risk and potential economic impact of pine wilt disease to Pinus plantations in Australia. Aust For 81(1):24–36

    Article  Google Scholar 

  4. Cheng T, Riaño D, Ustin SL (2014) Detecting diurnal and seasonal variation in canopy water content of nut tree orchards from airborne imaging spectroscopy data using continuous wavelet analysis. Remote Sens Environ 143:39–53

    Article  Google Scholar 

  5. Coops N, Stanford M, Old K, Dudzinski M, Culvenor D, Stone C (2003) Assessment of Dothistroma needle blight of Pinus radiata using airborne hyperspectral imagery. Phytopathology 93(12):1524–1532

    Article  Google Scholar 

  6. Duan F, Yang S, Huang D, Hu Y, Wu Z, Zhou W (2014) Craniofacial reconstruction based on multi-linear subspace analysis. Multimed Tools Appl 73(2):809–823

    Article  Google Scholar 

  7. Guo T, Han L, He L, Yang X (2014) A GA-based feature selection and parameter optimization for linear support higher-order tensor machine. Neurocomputing 144:408–416

    Article  Google Scholar 

  8. Hernández-Clemente R, Navarro-Cerrillo RM, Suárez L, Morales F, Zarco-Tejada PJ (2011) Assessing structural effects on PRI for stress detection in conifer forests. Remote Sens Environ 115(9):2360–2375

    Article  Google Scholar 

  9. Holland JH (1992) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT, Cambridge

    Book  Google Scholar 

  10. Huang M, Gong J, Li S, Zhang B, Huang X (2012) Study on pine wilt disease hyper-spectral time series and sensitive features. Remote Sens Technol Applic 27(6):954–960

    Google Scholar 

  11. Hyun MW, Kim JH, Suh DY, Lee SK, Kim SH (2007) Fungi isolated from pine wood nematode, its vector Japanese pine sawyer, and the nematode-infected Japanese black pine wood in Korea. Mycobiology 35(3):159–161

    Article  Google Scholar 

  12. Ju Y, Pan J, Wang X, Zhang H (2014) Detection of Bursaphelenchus xylophilus infection in Pinus massoniana from hyperspectral data. Nematology 16(10):1197–1207

    Article  Google Scholar 

  13. Kim SR, Lee WK, Lim CH, Kim M, Kafatos MC, Lee SH, Lee SS (2018) Hyperspectral analysis of pine wilt disease to determine an optimal detection index. Forests 9(3):115–127

    Article  Google Scholar 

  14. Kwon TS, Shin JH, Lim JH, Kim YK, Lee EJ (2011) Management of pine wilt disease in Korea through preventative silvicultural control. For Ecol Manag 261(3):562–569

    Article  Google Scholar 

  15. Larsolle A, Muhammed HH (2007) Measuring crop status using multivariate analysis of hyperspectral field reflectance with application to disease severity and plant density. Precis Agric 8(1–2):37–47

    Article  Google Scholar 

  16. Li S, Wu H, Wan D, Zhu J (2011) An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine. Knowl-Based Syst 24(1):40–48

    Article  Google Scholar 

  17. Liu J (2013) Spectral features analysis of Pinus massoniana with pest of dendrolimus punctatus walker and levels detection. Spectrosc Spectr Anal 33(2):428–433

    Google Scholar 

  18. Lu J, Zhao T, Zhang Y (2008) Feature selection based-on genetic algorithm for image annotation[J]. Knowl-Based Syst 21(8):887–891

    Article  Google Scholar 

  19. Luther JE, Franklin SE, Hudak J, Meades JP (1997) Forecasting the susceptibility and vulnerability of balsam fir stands to insect defoliation with Landsat thematic mapper data. Remote Sens Environ 59(1):77–91

    Article  Google Scholar 

  20. Mota MM, Braasch H, Bravo MA, Penas AC, Burgermeister W, Metge K, Sousa E (1999) First report of Bursaphelenchus xylophilus in Portugal and in Europe. Nematology 1(7):727–734

    Article  Google Scholar 

  21. Mutanga O, Skidmore AK, Prins HHT (2004) Predicting in situ pasture quality in the Kruger National Park, South Africa, using continuum-removed absorption features. Remote Sens Environ 89(3):393–408

    Article  Google Scholar 

  22. Van Nguyen T, Park YS, Jeoung CS, Choi WI, Kim YK, Jung IH, Chon TS (2017) Spatially explicit model applied to pine wilt disease dispersal based on host plant infestation. Ecol Model 353:54–62.

  23. Nijat K, Shi Q, Wang J, Rukeya S, Ilyas N, Gulnur I (2017) Estimation of spring wheat chlorophyll content based on hyperspectral features and PLSR model. Trans Chin Soc Agric Eng 33(22):208–216

    Google Scholar 

  24. Ren WY, Dan WU, Qin L (2016) Preliminary study on data collecting and processing of unmanned airship low altitude hyperspectral remote sensing. Ecol Environ Monit Three Gorges 1:52–57

    Google Scholar 

  25. Sankaran S, Mishra A, Maja JM, Ehsani R (2011) Visible-near infrared spectroscopy for detection of Huanglongbing in citrus orchards. Comput Electron Agric 77(2):127–134

    Article  Google Scholar 

  26. Shi Z, Wang Q, Peng J, Ji W, Liu H, Li X, Rossel RAV (2014) Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations. Sci Chin Earth Sci 57(7):1671–1680

    Article  Google Scholar 

  27. Sousa E, Naves P, Vieira M (2013) Prevention of pine wilt disease induced by Bursaphelenchus xylophilus and Monochamus galloprovincialis by trunk injection of emamectin benzoate. Phytoparasitica 41(2):143–148

    Article  Google Scholar 

  28. Suzuki K (2002) Pine wilt disease-a threat to pine forest in Europe. Dendrobiology 48:71–74

    Google Scholar 

  29. Wang Z, Zhang XL, An SJ (2007) Spectral characteristics analysis of Pinus Massoniana suffered by Bursaphelenchus Xylophilus. Remote Sens Technol Applic 22(3):367–370

    Google Scholar 

  30. Wang Z, Shao YH, Wu TR (2013) A GA-based model selection for smooth twin parametric-margin support vector machine. Pattern Recogn 46(8):2267–2277

    Article  Google Scholar 

  31. Wang J, Cui L, Gao W, Shi T, Chen Y, Gao Y (2014) Prediction of low heavy metal concentrations in agricultural soils using visible and near-infrared reflectance spectroscopy. Geoderma 216(4):1–9

    Article  Google Scholar 

  32. White JC, Coops NC, Hilker T, Wulder MA, Carroll AL (2007) Detecting mountain pine beetle red attack damage with EO-1 Hyperion moisture indices. Int J Remote Sens 28(10):2111–2121

    Article  Google Scholar 

  33. Wu N, Liu J, Yan R, Zhou G (2012) Using spectral feature parameters to estimate the chlorophyll content of Chinese fir under disease stress. Plant Prot 38(4):72–76

    Google Scholar 

  34. Wu J, Gao Z, Liu Q, Li Z, Zhong B (2018) Methods for sandy land detection based on multispectral remote sensing data. Geoderma 316:89–99

    Article  Google Scholar 

  35. Zhang T (2011) Changes of reflectance spectra of pine needles in different stage after being infected by pine wood nematode. Spectrosc Spectr Anal 31(5):1352–1356

    Google Scholar 

  36. Zhang S, Qin J, Tang X, Wan Y, Huang J, Song Q, Min J (2019) Spectral characteristics and evaluation model of Pinus Massoniana suffering from Bursaphelenchus xylophilus disease. Spectrosc Spectr Anal 39(3):865–872

    Google Scholar 

  37. Zhu Z, Li J, Guo Y, Cheng X, Tang Y, Guo L, Li X, Lu Y, Zeng X (2018) Accuracy improvement of boron by molecular emission with a genetic algorithm and partial least squares regression model in laser-induced breakdown spectroscopy 2018. J Anal At Spectrom 33(2):205–209

    Article  Google Scholar 

Download references

Acknowledgements

This research was funded by National Natural Science Foundation of China, grant number 61601060, China Scholarship Council Foundation, grant number 201709955001, Chongqing Science and technology commission Foundation, grant number cstc2016jcyjA0437, Chongqing Municipal Education Commission Foundation, grant number KJZH17132 and Defense science and Technology Bureau, grant number 32-Y20A18-9001-15-17-3.

Author information

Authors and Affiliations

  1. College of Big Data and Intelligent Engineering, Yangtze Normal University, Chongqing, 408100, China

    Sulan Zhang & Jinlong Huang

  2. Queensland Alliance for Agriculture & Food Innovation, Centre for Horticultural Science, The University of Queensland, Brisbane, 4072, Australia

    Sulan Zhang & Jim Hanan

  3. Hyperspectral Remote Sensing Monitoring Center for Ecological Environment of the Three Gorges Reservoir Area, Yangtze Normal University, Chongqing, 408100, China

    Sulan Zhang & Lin Qin

  4. College of Electronic Information Engineering, Yangtze Normal University, Chongqing, 408100, China

    Lin Qin

Authors
  1. Sulan Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinlong Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jim Hanan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lin Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jinlong Huang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, S., Huang, J., Hanan, J. et al. A hyperspectral GA-PLSR model for prediction of pine wilt disease. Multimed Tools Appl 79, 16645–16661 (2020). https://doi.org/10.1007/s11042-019-07976-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-019-07976-5

Keywords

Search

Navigation