Early Detection of Fire Blight Disease of Pome Fruit Trees Using Visible-NIR Spectrometry and Dimensionality Reduction Methods

Document Type : Research Article-en

Authors

• N. Bagheri ¹
• H. Mohamadi-Monavar ²

¹ Agricultural Engineering Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran

² Department of Biosystem Engineering, Faculty of Agriculture, Bu-ali Sina University, Hamadan, Iran

https://doi.org/10.22067/jam.v10i1.71911

Abstract

Fire Blight (FB) is the most destructive bacterial disease of pome fruit trees around the world. In recent years, spectrometry has been shown to be an accurate and real-time sensing technology for plant disease detection. So, the main objective of this research is early detecting FB of pear trees by using Visible-Near-infrared spectrometry. To get this goal, the reflectance spectra of healthy leaves (ND), non-symptomatic (NS), and symptomatic diseased leaves (SY) were captured in the visible–NIR spectral regions. In order to keep the important information of spectra and reduce the dimension of data, three linear and non-linear manifold-based learning techniques were applied such as, Principal Component Analysis (PCA), Sammon mapping and Multilayer auto-encoder (MAE). The output of manifold-based learning techniques was used as an input of the SIMCA (Soft independent modeling by class analogy) classification model to discriminate NS and ND leaves. Based on the results, the best classification accuracy obtained by using PCA on the 1st derivative spectra, with accuracy of 95.8%, 89.3%, and 91.6% for ND, NS, and SY samples, respectively. These results support the capability of manifold-based learning techniques for early detection of FB via spectrometry method.

Keywords

• Classification
• Early detection
• Fire blight
• Near-infrared
• Spectrometry

20.1001.1.22286829.1399.10.1.4.0

Open Access

©2020 The author(s). This article is licensed under Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source.

References

1. Bagheri, N. Mohamadi-Monavar, H. Azizi, A. Ghasemi, A. 2018. Detection of Fire Blight disease in pear trees by hyperspectral data. European Journal of Remote Sensing 51 (1): 1-10.

2. Baranowski, P., W. Mazurek, J. Wozniak, and U. Majewska. 2012. Detection of early bruises of apple using hyperspectral and thermal imaging. Food Engineering 110: 345-355.

3. Barbedo, J. G. A., C. S. Tibola, and J. M. C. Fernandes. 2015. Detecting Fusarium head blight in wheat kernels using hyperspectral imaging. Biosystems Engineering 131: 65-76.

4. Barnes, R. J., M. S. Dhanoa, and S. J. Lister. 1989. Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Applied Spectroscopy 43: 772-777.

5. Basri, K. N., M. N. Hussain, J. Bakar, Z. Sharif, M. F. Abdul-Khir, and A. S. Zoolfakar. 2017. Classification and quantification of palm oil adulteration via portable NIR spectroscopy. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 173: 335-342.

6. Bravo, C., D. Moshou, J. West, A. McCartney, and H. Ramon. 2003. Early disease detection in wheat fields using spectral reflectance. Biosystems Engineering 84 (2): 137-145.

7. Cayuela, J. A., and J. F. Garcia. 2017. Sorting olive oil based on alpha-tocopherol and total tocopherol content using near-infrared spectroscopy (NIRS) analysis. Food Engineering: 1-10.

8. Delalieux, S., J. Van Aardt, W. Keulemans, E. Schrevens, and P. Coppin. 2007. Detection of biotic stress (Venturia inaequalis) in apple trees using hyperspectral data: non-parametric statistical approaches and physiological implications. European Journal of Agronomy 27 (1): 130-143.

9. DeMers, D., and G. Cottrell. 1993. Non-linear dimensionality reduction. In Advances in Neural Information Processing Systems, 5: pages 580-587, San Mateo, CA, USA, 1993. Morgan Kaufmann.

10. De Maesschalck, R., A. Candolfi, D. L. Massart, and S. Heuerding. 1999. Decision criteria for soft independent odeling of class analogy applied to near infrared data, Chemometrics and Intelligent Laboratory Systems 47: 65-77. DOI: 10.1016/S0169-7439(98)00159-2.

11. Fleiss, J. L. 1981. Statistical Methods for Rates and Proportions, second ed. Wiley-Interscience.

12. Futch, S. H., S. Weingarten, and M. Irey. 2009. Determining greening infection levels using multiple survey methods in Florida citrus. Proceedings of Florida State Horticulture Society 122: 152-157.

13. Gaucher, M., T. D. Bernonville, S. Guyot, J. F. Dat, and M. N. Brisset. 2013. Same ammo, different weapons: Enzymatic extracts from two apple genotypes with contrasted susceptibilities to fire blight (Erwinia amylovora) differentially convert phloridzin and phloretin in vitro, Plant Physiology and Biochemistry 72: 178-189.

14. Geladi, P., D. MacDougall, and H. Martens. 1985. Linearization and scatter-correction for near-infrared reflectance spectra of meat. Applied Spectroscopy 39: 491-500.

15. Ghodsi, A. 2006. Dimensionality Reduction “A Short Tutorial”, Department of Statistics and Actuarial Science, University of Waterloo, Ontario, Canada.

16. Huang, S., L. Qi, X. Ma, K. Xue, W. Wang, and X. Zhu. 2015. Hyperspectral image analysis based on BoSW model for rice panicle blast grading. Computers and Electronics in Agriculture 118: 167-17.

17. Jolliffe, I. T. 2002. Principal Component Analysis, second ed. Springer, New York, USA.

18. King E. O., M. K. Ward, and D. E. Raney. 1954. Two simple media for the demonstration of pyocyanin and fluorescein. Journal of Laboratory and Clinical Medicine 44: 301-307.

19. Laurindo, B. S., R. D. F. Laurindo, A. M. Azevedo, F. T. Delazari, J. C. Zanuncio, and D. J. Henriques da Silva. 2017. Optimization of the number of evaluations for early blight disease in tomato accessions using artificial neural networks, Scientia Horticulturae 218: 171-176.

20. Lee, J. A., and M. Verleysen. 2007. Nonlinear Dimensionality Reduction. Springer, New York, USA.

21. Liu, Z. Y., H. F. Wu, and J. F. Huang. 2010. Application of neural networks to discriminate fungal infection levels in rice panicles using hyperspectral reflectance and principal components analysis. Computers and Electronics in Agriculture 72: 99-106.

22. Lorente, D., P. Escandell-Montero, S. Cubero, J. Gomez-Sanchis, and J. Blasco. 2015. Visible-NIR reflectance spectroscopy and manifold learning methods applied to the detection of fungal infections on citrus fruit. Food Engineering 163: 17-24.

23. Mahlein, A. K., T. Rumpf, P. Welke, H. W. Dehne, L. Plümer, U. Steiner, and E. C. Oerke. 2013. Development of spectral indices for detecting and identifying plant diseases. Remote Sensing of Environment 128: 21-30.

24. Mohammadi Moghaddam, T., S. M. A. Razavi, M. Taghizadeh, A. Sazgarnia, and B. Pradhan. 2015. Vis-NIR hyperspectral imaging and multivariate analysis for prediction of the moisture content and hardness of Pistachio kernels roasted in different conditions. Journal of Agricultural Machinery 5 (2): 281-291. (In Farsi).

25. Moshou, D., C. Bravo, J. West, S. Wahlen, A. McCartney, and H. Ramon. 2004. Automatic detection of ‘yellow rust’ in wheat using reflectance measurements and neural networks. Computers and Electronics in Agriculture 44 (3): 173-188.

26. Naidu, R. A., E. M. Perry, F. J. Pierce, and T. Mekuria. 2009. The potential of spectral reflectance technique for the detection of Grapevine leafroll-associated virus-3 in two red-berried wine grape cultivars. Computers and Electronics in Agriculture 66: 38-45.

27. Negri, A., D. Allegra, L. Simoni, F. Rusconi, C. Tonelli, L. Espan, and M. Galbiati. 2015. Comparative analysis of fruit aroma pattern in the domesticated wild strawberries “Profumata di Tortona” (F. moschata) and “Regina delle Valli” (F. vesca), Frontiers in Plant Science 6: 1-13.

28. Phadikar, S., J. Sil, and A. K. Das. 2013. Rice diseases classification using feature selection and rule generation techniques. Computers and Electronics in Agriculture 90: 76-86.

29. Purcell, D. E., M. G. O’ Shea, R. A. Johnson, and S. Kokot. 2009. Near-infrared spectroscopy for the prediction of disease rating for Fiji leaf gall in sugarcane clones. Applied Spectroscopy 63 (4): 450-457.

30. Sammon, J. W. 1969. A nonlinear mapping for data structure analysis. IEEE Transactions on Computers 18: 401-409.

31. Sankaran, S., A. Mishra, R. Ehsani, and C. Davis. 2010. A review of advanced techniques for detecting plant diseases. Computers and Electronics in Agriculture 72 (1): 1-13.

32. Savitzky, A., and M. J. E. Golay. 1964. Smoothing and differentiation of data by simplified least square procedures. Analytical Chemistry 36 (8): 1627-1639.

33. Spinelli, F., M. Noferini, and G. Costa. 2006. Near infrared spectroscopy (NIRs): Perspective of fire blight detection in asymptomatic plant material. Proceeding of 10th International Workshop on Fire Blight. Acta Hort 704: 87-90.

34. Tian, T. S. 2010. Dimensionality Reduction for Classification with High-Dimensional Data. PhD thesis, VDM Verlag, Saarbrücken, Germany.

35. Vanden Branden, K., and M. Hubert. 2005. Robust classification in high dimensions based on the SIMCA method, Chemom. Intell. Lab. Syst. 79: 10-21 available at: http://dx.doi.org/10.1016/j.chemolab.2005.03.002.

36. Vitale, F., M. Bevilacqua, R. Bucci, A. D. Magri, A. L. Magri, and F. Marini. 2013. A rapid and non-invasive method for authenticating the origin of pistachio samples by NIR spectroscopy and chemometrics.

37. Yang, C. M., C. H. Cheng, and R. K. Chen. 2007. Changes in spectral characteristics of rice canopy infested with brown planthopper and leaffolder. Crop Science 47: 329-335.

38. Yuan, L., J. C. Zhang, K. Wang, R. W. Loraamm, W. J. Huang, J. H. Wang, and J. L. Zhao. 2013. Analysis of spectral difference between the foreside and backside of leaves in yellow rust disease detection for winter wheat. Precision Agriculture, published online, 7 May 2013.

39. Zhang, J. C., R. L. Pu, J. H. Wang, W. J. Huang, L. Yuan, and J. H. Luo. 2012. Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements. Computers and Electronics in Agriculture 85: 2-13.