Intelligent plant health monitoring and early disease warning system for vertical greenhouses

The present research is aimed at systematizing scientific knowledge about crop diseases and integrating them into automated control systems for vertical greenhouses. The relevance of the work is due to the need to reduce economic losses in crop production by developing methods for early detection of diseases and optimizing phytosanitary measures. Sweet basil, characterized by high susceptibility to phytopathogens under intensive cultivation technologies, was used as a model object. To create the platform, a specialized data set was formed: 254 images of the basil, annotated with the location and area of pathological changes. The data set has been supplemented with the augmentation method to increase the diversity of the sample. Based on a comprehensive analysis, the architecture of a monitoring system consisting of three modules is proposed: sensory (image and microclimate data collection), analytical (based on convolutional neural networks to assess disease dynamics) and a decision support interface (generation of agronomic recommendations). Training of the model using transfer learning showed a detection accuracy of 74.7 %. To minimize false positives, the proposed post-processing algorithm can be modified to take into account the spatial-temporal correlation of the data. The developed prototype confirms the prospects of integrating computer vision and agronomic knowledge to create predictive systems. The results have the potential to adapt to other protected soil crops, contributing to the development of precision agriculture and reducing anthropogenic stress on agroecosystems.

1. Vasilyev S.A., Limonov S.Ye., Mishin S.A. Intelligent Field Sensor Station for Monitoring Agrophysical Parameters and Phenotyping in Precision Agriculture System. Agricultural Machinery and Technologies. 2024;18(4):79–85. (In Russ.). https://doi.org/10.22314/2073-7599-2024-18-4-79-85

2. Kalichkin V.K., Maksimovich K.Yu., Aleshchenko O.A., Aleshchenko V.V. Crop Yield Prediction: Data Structure and Ai-Powered Methods. Agricultural Machinery and Technologies. 2025;19(2):33–44. (In Russ.). https://doi.org/10.22314/2073-7599-2025-19-2-33-44

3. Mahlein A.-K. Plant Disease Detection by Imaging Sensors – Parallels and Specific Demands for Precision Agriculture and Plant Phenotyping. Plant Disease. 2016;100(2):241–251. https://doi.org/10.1094/PDIS-03-15-0340-FE

4. Solovchenko A., Dorokhov A., Shurygin B., et al. Linking Tissue Damage to Hyperspectral Reflectance for Non-Invasive Monitoring of Apple Fruit in Orchards. Plants. 2021;10(2). https://doi.org/10.3390/plants10020310

5. Anantrasirichai N., Hannuna S., Canagarajah N. Towards automated mobile-phone-based plant pathology management. arXiv. URL: https://arxiv.org/abs/1912.09239 [Accessed 1st January 2024].

6. Abade A., Ferreira P.A., de Barros Vidal F. Plant diseases recognition on images using convolutional neural networks: A systematic review. Computers and Electronics in Agriculture. 2021;185. https://doi.org/10.1016/j.compag.2021.106125

7. Miller S.A., Beed F.D., Harmon C.L. Plant Disease Diagnostic Capabilities and Networks. Annual Review of Phytopathology. 2009;47:15–38. https://doi.org/10.1146/annurev-phyto-080508-081743

8. Wang Z., Chi Zh., Feng D.D. Shape based leaf image retrieval. IEE Proceedings – Vision Image and Signal Processing. 2003;150(1):34–43.

9. Anantrasirichai N., Hannuna S., Canagarajah N. Automatic Leaf Extraction from Outdoor Images. arXiv. URL: https://arxiv.org/abs/1709.06437 [Accessed 1st January 2024].

10. Motorin O.A., Gorbachev M.I., Petrenko A.P., Suvorov G.A. On the introduction of modern information technology solutions in agriculture. Agricultural Risk Management. 2019;(4):105–122. (In Russ.). https://doi.org/10.53988/24136573-2019-04-09

11. Kochkarov A.A., Kulikov A.K., Rumyantsev B.V. Agrobiotechnologies: Experience in using and prospects for using artificial intelligence. In: Horizons of mathematical modeling and theory of self-organization. On the occasion of the 95th anniversary of the birth of S.P. Kurdyumova, 21 November 2023, Moscow, Russia. Moscow: IPM im. M.V. Keldysha; 2024. P. 144–153. (In Russ.). https://doi.org/10.20948/k95-8

12. Mohanty Sh.P., Hughes D.P., Salathé M. Using Deep Learning for Image-Based Plant Disease Detection. Frontiers in Plant Science. 2016;7. https://doi.org/10.3389/fpls.2016.01419

13. Hong G., Luo M.R., Rhodes P.A. A study of digital camera colorimetric characterization based on polynomial modeling. Color Research and Application. 2001;26(1):76–84. https://doi.org/10.1002/1520-6378(200102)26:1<76::AID-COL8>3.0.CO;2-3

14. Hannuna S.L., Kunkel T., Anantrasirichai N., Canagarajah N. Colour Correction for Assessing Plant Pathology Using Low Quality Cameras. In: BIOINFORMATICS 2011: Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms, 26–29 January 2011, Rome, Italy. SciTePress; 2011. P. 326–331.

15. Altieri M.A. Agroecology: The Science of Sustainable Agriculture. Boca Raton: CRC Press; 2018. 448 p.