10.14489/td.2025.11.pp.045-053

2025, 11 November

DOI: 10.14489/td.2025.11.pp.045-053

Yudaev V. A., Balabanov P. V., Grebennikova N. M., Divin A. G., Egorov A. S., Lyubimova D. A.
METHODOLOGY FOR DIAGNOSING HERBICIDE INJURIES TO SUNFLOWER BASED ON THE ANALYSIS OF HYPERSPECTRAL IMAGES OF ITS PLANT TISSUES
(pp. 45-53)

Abstract. The paper proposes a technique for diagnosing damage to plant tissues of the Spartak sunflower variety caused by a reaction to the herbicide tribenuron-methyl. Diagnostics is based on the analysis of hyperspectral images of control objects obtained in the wavelength range from 350 to 1002 nm. The technique involves collecting and analyzing hyperspectral images at growth stages. An information-measuring system based on the Cubert X20 Plus camera was used to obtain hyperspectral images. As a result of analyzing the obtained images using the PCA method, informative wavelengths of 502, 670, 718, 770 and 930 nm were determined. Using machine learning methods such as linear discriminant analysis, random forest, logistic regression, k-nearest neighbors (kNN) and SVM, machine learning models were obtained for classifying objects in the camera's field of view by category. To select the optimal model, a complex quality indicator was used, including two criteria ‒ time and quality of classification. An optimal machine learning model obtained on the basis of linear discriminant analysis is determined.

Keywords: hyperspectral images, non-destructive control, herbicide injuries, crops, sunflower, classification, models, machine learning, information and measuring system.

+ - About the Authors Click to collapse

V. A. Yudaev, P. V. Balabanov, N. M. Grebennikova, A. G. Divin, A. S. Egorov, D. A. Lyubimova (Tambov State Technical University, Tambov, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра. , Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Ye, W., Yan, T., Zhang, C., et al. (2022). Detection of pesticide residue level in grape using hyperspectral imaging with machine learning. Foods, 11, 1–16. https://doi.org/10.3390/foods11111609
2. Armenta, S., Garrigues, S., & de la Guardia, M. (2007). Partial least squares-near infrared determination of pesticides in commercial formulations. Vibrational Spectroscopy, 44, 273–278. https://doi.org/10.1016/j.vibspec.2006.12.005
3. Brunet, D., Woignier, T., Lesueur-Jannoyer, M., et al. (2009). Determination of soil content in chlordecone (organochlorine pesticide) using near infrared reflectance spectroscopy (NIRS). Environmental Pollution, 157, 3120–3125. https://doi.org/10.1016/j.envpol.2009.05.026
4. Makio, T., Hiroaki, I., Tomohiro, T., et al. (2007). Classification of pesticide residues in the agricultural products based on diffuse reflectance IR spectroscopy. SICE Annual Conference, 216–219. https://doi.org/10.1109/SICE.2007.4420979
5. Khanmohammadi, M., Armenta, S., Garrigues, S., & de la Guardia, M. (2008). Mid-and near-infrared determination of metribuzin in agrochemicals. Vibrational Spectroscopy, 46, 82–88. https://doi.org/10.1016/j.vibspec.2007.10.005
6. Scholten, R. C., Hill, J., Werner, W., et al. (2019). Hyperspectral VNIR-spectroscopy and imagery as a tool for monitoring herbicide damage in wilding conifers. Biological Invasions, 21, 3395–3413. https://doi.org/10.1007/s10530-019-02055-0
7. Shao, Y., Jiang, L., Zhou, H., et al. (2016). Identification of pesticide varieties by testing microalgae using Visible/Near Infrared Hyperspectral Imaging technology. Scientific Reports, 6, 1–11. https://doi.org/10.1038/srep24221
8. Scherrer, B., Sheppard, J. W., Jha, P., et al. (2019). Hyperspectral imaging and neural networks to classify herbicide-resistant weeds. Journal of Applied Remote Sensing, 13, 1–15. https://doi.org/10.1117/1.JRS.13.044516
9. Cong, S., Liu, C., Zhu, Z., & Hu, A. (2021). Study on identification of multiple pesticide residues in lettuce leaves based on hyperspectral technology. Advances in Artificial Intelligence and Security: 7th International Conference, ICAIS, 537–550. https://doi.org/10.1007/978-3-030-78621-2_45
10. Ghosh, S., Alkafaas, S. S., Bornman, C., et al. (2022). The application of rapid test paper technology for pesticide detection in horticulture crops: A comprehensive review. Beni-Suef University Journal of Basic and Applied Sciences, 11, 1–28. https://doi.org/10.1186/s43088-022-00248-6

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

DOI: 10.14489/td.2025.11.pp.045-053

Copy the article DOI and follow the link https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-kontrol-diagnostika

Please specify the article DOI in the order comments.