Abstract
Purpose
Powdery mildew as one of the common vegetable diseases has very rapid infection. Its outbreak will bring about disastrous consequences to vegetable output; thus, it is of key importance to do rapid identification and prevention of powdery mildew.
Methods
In this test, 100 bitter gourd leaves were collected as research samples, and the data of near-infrared spectra, fluorescence spectra, and chromatic values L*a*b*, and the classic K-S algorithm was adopted to divide the sample sets; then, the quantitative forecasting and qualitative discrimination models were established. First, Pearson’s correlation analysis was carried out to find the feasibility of taking a* as the modeling parameter, through cross-validation; the quantitative forecasting model was optimized by the PLSR (partial least squares regression) method. The model is also optimized by extracting the spectral feature bands using the continuous projection SPA method.
Results
The optimization results showed that the MSC + SPA + PLSR quantitative forecasting model of near-infrared spectra could effectively improve model precision, which was significantly higher than that of fluorescence spectra. Classification Leaner was used to establish the quantitative forecasting model. Compared with the model of near-infrared spectra, the SPA + SVM qualitative discrimination model of fluorescence spectra could improve the identification precision of powdery mildew of bitter gourd as high as 98% through training.
Conclusion
This study proposed different combination methods based on quantitative forecasting and qualitative discrimination and could provide a method and reference to the identification of powdery mildew of bitter gourd.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available on request from the corresponding author, Ning, upon reasonable request.
References
Araújo, M. C. U., Saldanha, T. C. B., & Galvão, R. K. H. (2001). The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometrics and Intelligent Laboratory Systems, 57(2), 65–73. https://doi.org/10.1016/S0169-7439(01)00119-8
Di, W. P. Y., Bian, X. H., Wang, Z. F., & Liu, W. (2019). Study on spectral pretreatment method selection. Spectroscopy and Spectral Analysis, 39(9), 2800–2806. https://doi.org/10.3964/j.issn.1000-0593(2019)09-2800-07
Feng, L., Chen, S. S., Feng, B., & Liu, F. (2012). Early identification method of soybean pod anthrax based on spectroscopic technique. Transactions of the Chinese Society of Agricultural Engineering, 28(1), 139–144. https://doi.org/10.3969/j.issn.1002-6819.2012.01.026
Feng, Z. H., Song, L., & Duan, J. Z. (2021). Monitoring wheat powdery mildew based on hyperspectral, thermal infrared, and RGB image data fusion. Sensors, 22(1), 31–31. https://doi.org/10.3390/s22010031
Gao, Y. F., Fu, L. Y., Qu, J., Wang, J. X., **ng, Z. N., & Weng, L. H. (2019). Influence of improved KS algorithm based on similarity measure on near infrared spectral analysis model. Electronics Optics & Control, 26(6), 18–21. https://doi.org/10.3969/j.issn.1671-637X.2019.06.004
Li, H. B., He, G. Z., & Guo, Q. T. (2015). Search method for similarity of organic mass spectrometry based on Pearson correlation coefficient. Chemolyticometrics, 24(3), 33–37. https://doi.org/10.3969/j.issn.1008-6145.2015.03.009
Liu, Y. D., & Niu, H. M. (2011). Small sample KNN classification algorithm based on k-nearest neighbor graph. Computer Engineering, 37(9), 198–200. https://doi.org/10.3969/j.issn.1000-3428.2011.09.069
Liu, Z. B., & Wang, S. T. (2011). Improved linear discriminant analysis algorithm. Computer Applications, 31(1), 250–253. https://doi.org/10.3724/SP.J.1087.2011.00250
Liu, X. Y., **ong, J. L., Zang, Z., & Lin, H. (2012). Correlation analysis between chlorophyll content and hyperspectral data of Pinus massoniana. Guangdong Agricultural Sciences, 39(10), 35–37. https://doi.org/10.3969/j.issn.1004-874X.2012.10.012. 50.
Long, T., Li, J. Y., Long, Y. B., & Yan, X. J. (2021). Spectral response and intelligent classification identification of wheat leaves under powdery mildew stress. Journal of South China Agricultural University, 42(3), 86–93. https://doi.org/10.7671/j.issn.1001-411X.202009001
Pan, C. H., **ao, D. Q., Lin, T. Y., & Wang, C. T. (2018). Classification and identification of main vegetable pests in South China based on SVM and regional growth algorithm. Transactions of the Chinese Society of Agricultural Engineering, 34(8). https://doi.org/10.11975/j.issn.1002-6819.2018.08.025
Ranulfi, A. C., Cardinali, M. C. B., Kubota, T. M. K., Astúa, J. F., Ferreira, E. J., Bellete, B. S., Silva, M. F., Boas, P. R. V., Magalhaes, A. B., & Milori, D. M. B. P. (2016). Laser-induced fluorescence spectroscopy applied to early diagnosis of citrus Huanglongbing. Biosystems Engineering, 144, 133–144. https://doi.org/10.1016/j.biosystemseng.2016.02.010
Römer, C., Bürling, K., Hunsche, M., Rumpf, T., Noga, G., & Plümer, L. (2011). Robust fitting of fluorescence spectra for pre-symptomatic wheat leaf rust detection with support vector machines. Computers and Electronics in Agriculture, 79(2), 180–188. https://doi.org/10.1016/j.compag.2011.09.011
Sankaran, S., & Ehsani, R. (2013). Detection of huanglongbing-infected citrus leaves using statistical models with a fluorescence sensor. Applied Spectroscopy, 67(4), 463–469. https://doi.org/10.1366/12-06790
Sun, H. & Yang, J. (2019). Domain-specific image classification using ensemble learning utilizing open-domain knowledge. 2019 International Conference on Computing, Networking and Communications (ICNC), 593–596. https://doi.org/10.1109/ICCNC.2019.8685507
Varshney, T., Chug, A., & Singh, A. P. (2021). Deep learning models for prediction of tomato powdery mildew disease. 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India, pp. 1036–1041. https://doi.org/10.1109/SPIN52536.2021.9566132.
Wang, F., Li, Y. Y., Peng, Y. K., Sun, H. W., & Li, L. (2018). Nondestructive testing method for lycopene content based on visible/near-infrared transmission spectroscopy. Chinese Journal of Analytical Chemistry, 46(9), 1424–1431. https://doi.org/10.11895/j.issn.0253-3820.181164
Wang, X. Y., Zhu, C. G., Fu, Z. T., Zhang, L. X., & Li, X. X. (2019). Identification of cucumber powdery mildew based on visible spectrum analysis. Spectroscopy and Spectral Analysis, 39(06), 1864–1869. https://doi.org/10.3964/j.issn.1000-0593(2019)06-1864-06
Włodarska, K., Khmelinskii, I., & Sikorska, E. (2018). Evaluation of quality parameters of apple juices using near-infrared spectroscopy and chemometrics. Journal of Spectroscopy, 2018, 1–8. https://doi.org/10.1155/2018/5191283
Wu, D., Liu, W. F., Hu, S., Hu, L. Z., & Hu, J. H. (2017). K-means clustering color image segmentation based on Lab space. Electronic science and technology, 30(10), 29–32. https://doi.org/10.16180/j.cnki.issn1007-7820.2017.10.009
Wu, Y. J., Hong, W. Y., Zhang, Z. M., Wu, Y., & Miao, Q. (2022). Epidemic dynamic and prediction model of cucumber powdery mildew under protected culti-vation. Acta Agriculturae Zhejiangensis, 34(1), 104–111. https://doi.org/10.3969/j.issn.1004-1524.2022.01.13
Yang, Z., Jiang, Z. H., & Lv, B. (2012). Near-infrared spectroscopy analysis of rosewood. Spectroscopy and Spectral Analysis, 32(9), 2405–2408. https://doi.org/10.3964/j.issn.1000-0593(2012)09-2405-04
Yu, W. J., Wang, C. X., Qiao, L., & Wang, S. L. (2020). Construction of PLSR prediction model for chromaticity of **gyuan yellow beef based on hyperspectral imaging technology. Zhejiang Journal of Agricultural Sciences, 32(3), 527–533. https://doi.org/10.3969/j.issn.1004-1524.2020.03.19
Zhang, H. Y., Liu, Y., & Ma, L. M. (2017). Comparison and application research of decision tree algorithm [J]. North China Electric Power Technology, 6, 42–47. https://doi.org/10.16308/j.cnki.issn1003-9171.2017.06.008
Zhang, N., Yang, G., Pan, Y., Yang, X., Chen, L., & Zhao, C. (2020). A review of advanced technologies and development for hyperspectral-based plant disease detection in the past three decades. Remote Sensing, 12(19), 3188. https://doi.org/10.3390/rs12193188
Zhang, Z. S. Y., Gu, H. W., & **e, K. W. (2021). Pretreatment and combination method based on near-infrared spectroscopy. Advances in Laser and Optoelectronics, 58(16), 464–471. https://doi.org/10.3788/LOP202158.1617001
Funding
This research program is supported by the Liaoning Revitalization Tatents Program (XLYC2007043) and the Scientific Research Fund Project of Liaoning Province (LJKZZ20220087).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare no competing interests.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gao, J.Y., Wei, D.Z., Wang, X. et al. Detection of Powdery Mildew of Bitter Gourd Based on NIR/Fluorescence Spectra. J. Biosyst. Eng. 48, 319–328 (2023). https://doi.org/10.1007/s42853-023-00193-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42853-023-00193-x