Machine Learning Models for Early Detection of Plant Diseases Using Multispectral Imaging: A Comprehensive Review
DOI:
https://doi.org/10.17140/phoj.11.01.353Keywords:
Machine Learning, Multispectral Imaging, Hyperspectral Imaging, Plant Disease Detection, Deep LearningAbstract
Plant diseases significantly affect crop productivity and global food security, making early detection essential for sustainable agriculture. Traditional visual diagnosis methods are often slow, subjective, and ineffective during early infection stages. Recent advances in multispectral and hyperspectral imaging combined with machine learning and deep learning techniques enable rapid, non-destructive, and accurate detection of plant diseases before visible symptoms appear. Spectral imaging captures physiological and biochemical changes in plants across visible, near-infrared, red-edge, and thermal bands, while algorithms such as SVM, Random Forest, CNN, RNN, and Vision Transformers effectively classify healthy and diseased plants. This review discusses imaging techniques, preprocessing methods, machine learning models, UAV-based sensing, explainable AI, and edge computing applications in precision agriculture, along with challenges and future directions for smart disease detection systems.
References
R. N. Strange and P. R. Scott. Plant disease: A threat to global food security. Annual Review of Phytopathology, 43:83–116, 2005.
S. Savary, L. Willocquet, S. J. Pethybridge, P. Es-ker, N. McRoberts, and A. Nelson. The global burden of pathogens and pests on major food crops. Nature Ecology and Evolution, 3(3):430– 439, 2019.
A. K. Mahlein. Plant disease detection by imaging sensors – Parallels and specific demands for pre-cision agriculture and plant phenotyping. Plant Limitations References Limited spectral [27][28] resolution High computational [33][42] complexity Sensitive to [34][44] parameter tuning Large ensemble [45] complexity Requires large datasets [55][60] Domain adaptation [51][58] issues Weather dependency [38][47][54] Computationally [52] intensive Disease, 100(2):241–251, 2016.
C. H. Bock, G. H. Poole, P. E. Parker, and T. R. Gottwald. Plant disease severity estimated visu-ally, by digital photography and image analysis, and by hyperspectral imaging. Critical Reviews in Plant Sciences, 29(2):59–107, 2020.
G. N. Agrios. Plant Pathology. 5th edition, Else-vier Academic Press, 2005.
N. W. Schaad, J. B. Jones, and W. Chun. Labora-tory Guide for Identification of Plant Pathogenic Bacteria. APS Press, 2003.
S. Sankaran, A. Mishra, R. Ehsani, and C. Davis. A review of advanced techniques for detecting plant diseases. Computers and Electronics in Agricul-ture, 72(1):1–13, 2010.
S. J. Pethybridge and S. C. Nelson. Leaf Doctor: A new portable application for quantifying plant disease severity. Plant Disease, 99(10):1310– 1316, 2015.
J. S. West, C. Bravo, R. Oberti, D. Lemaire, D. Moshou, and H. A. McCartney. The potential of optical canopy measurement for targeted con-trol of field crop diseases. Annual Review of Phy-topathology, 41:593–614, 2003.
M. Zhang, Z. Qin, X. Liu, and S. L. Ustin. Detec-tion of stress in tomatoes induced by late blight disease in California using hyperspectral remote sensing. International Journal of Applied Earth Observation and Geoinformation, 4(4):295–310, 2003.
A. M. Mutka and R. S. Bart. Image-based pheno-typing of plant disease symptoms. Frontiers in Plant Science, 5:734, 2015.
A. K. Mahlein, E. C. Oerke, U. Steiner, and H. W. Dehne. Recent advances in sensing plant diseases for precision crop protection. European Journal of Plant Pathology, 133:197–209, 2012.
K. Golhani, S. K. Balasundram, G. Vadamalai, and B. Pradhan. A review of neural networks in plant disease detection using hyperspectral data. Infor-mation Processing in Agriculture, 5(3):354–371, 2018.
G. A. Blackburn. Hyperspectral remote sensing of plant pigments. Journal of Experimental Botany, 58(4):855–867, 2007.
R. Calderón, J. A. Navas-Cortés, C. Lucena, and P. J. Zarco-Tejada. High-resolution airborne hyper-spectral and thermal imagery for early detection of Verticillium wilt of olive using fluorescence and plant temperature. Remote Sensing of Environ-ment, 139:231–245, 2013.
G. A. Carter and A. K. Knapp. Leaf optical proper-ties in higher plants: Linking spectral characteris-tics to stress and chlorophyll concentration. Amer-ican Journal of Botany, 88(4):677–684, 2001.
D. A. Sims and J. A. Gamon. Relationships between leaf pigment content and spectral re-flectance across species, leaf structures and de-velopmental stages. Remote Sensing of Environ-ment, 81(2–3):337–354, 2002.
P. J. Zarco-Tejada, J. R. Miller, A. Morales, A. Berjón, and J. Agüera. Hyperspectral indices and model simulation for chlorophyll estimation in open-canopy tree crops. Remote Sensing of Envi-ronment, 90(4):463–476, 2005.
S. Delalieux, B. Somers, S. Hereijgers, W. W. Ver-straeten, J. Keulemans, and P. Coppin. Hyper-spectral indices to diagnose leaf biotic stress of apple plants considering leaf phenology. Inter-national Journal of Remote Sensing, 30(8):1887– 1912, 2009.
J. Behmann, J. Steinrücken, and L. Plümer. Detec-tion of early plant stress responses in hyperspec-tral images. ISPRS Journal of Photogrammetry and Remote Sensing, 93:98–111, 2015.
S. P. Mohanty, D. P. Hughes, and M. Salathé. Using deep learning for image-based plant disease de-tection. Frontiers in Plant Science, 7:1419, 2016.
K. P. Ferentinos. Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145:311–318, 2018.
E. C. Too, L. Yujian, S. Njuki, and L. Yingchun. A comparative study of fine-tuning deep learning models for plant disease identification. Comput-ers and Electronics in Agriculture, 161:272–279, 2019.
A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2021.
S. Khan, M. Naseer, M. Hayat, S. W. Zamir, F. S. Khan, and M. Shah. Transformers in vision: A survey. ACM Computing Surveys, 54(10s):1–41, 2022.
A. Savitzky and M. J. E. Golay. Smoothing and dif-ferentiation of data by simplified least squares procedures. Analytical Chemistry, 36(8):1627– 1639, 1964.
I. T. Jolliffe. Principal Component Analysis. Springer, 2002.
J. W. Rouse, R. H. Haas, J. A. Schell, and D. W. Deering. Monitoring vegetation systems in the Great Plains with ERTS. NASA Special Publication, 351:309, 1974.
A. Chlingaryan, S. Sukkarieh, and B. Whelan. Ma-chine learning approaches for crop yield predic-tion and nitrogen status estimation in precision agriculture: A review. Computers and Electronics in Agriculture, 151:61–69, 2018.
K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis. Machine learning in agriculture: A review. Sensors, 18(8):2674, 2018.
S. Savary, P. S. Teng, L. Willocquet, and F. W. Nutter Jr. Quantification and modeling of crop losses: A review of purposes. Annual Review of Phytopathology, 44:89–112, 2006.
P. Skamnioti and S. J. Gurr. Against the grain: Safeguarding rice from rice blast disease. Trends in Biotechnology, 27(3):141–150, 2009.
A. K. Mahlein, U. Steiner, C. Hillnhütter, H. W. Dehne, and E. C. Oerke. Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases. Plant Methods, 8:3, 2012.
J. Zhang, C. Pu, X. Liu, et al. Detection of rice blast disease using hyperspectral imaging and sup-port vector machine. Remote Sensing, 10(5):698, 2018.
F. Qin, D. Liu, B. Sun, et al. Identification of rice diseases using deep convolutional neural net-works. Computers and Electronics in Agriculture, 162:898–905, 2019.
H. Wang, G. Li, Z. Ma, and X. Li. Application of deep learning for rice bacterial blight detection using multispectral imagery. Remote Sensing, 12(3):456, 2020.
Y. Lu, S. Yi, N. Zeng, et al. Transfer learning for rice disease classification using deep neural net-works. Computers and Electronics in Agriculture, 182:105995, 2021.
L. Feng, S. Zhang, Y. Zhang, et al. UAV-based mul-tispectral remote sensing for rice blast monitoring. Precision Agriculture, 21(4):1–18, 2020.
M. Kerkech, A. Hafiane, and R. Canals. Deep learn-ing approach with colorimetric spaces and veg-etation indices for vine disease detection in UAV images. Computers and Electronics in Agricul-ture, 155:237–243, 2018.
X. M. Chen. Epidemiology and control of stripe rust on wheat. Canadian Journal of Plant Pathol-ogy, 27(3):314–337, 2005.
J. M. Beddow, P. G. Pardey, Y. Chai, et al. Re-search investment implications of shifts in the global geography of wheat stripe rust. Nature Plants, 1:15132, 2015.
D. Moshou, C. Bravo, J. West, et al. Automatic de-tection of yellow rust in wheat using reflectance measurements and neural networks. Comput-ers and Electronics in Agriculture, 44(3):173–188, 2004.
T. Rumpf, A. K. Mahlein, U. Steiner, E. C. Oerke, H. W. Dehne, and L. Plümer. Early detection and classification of plant diseases with Sup-port Vector Machines based on hyperspectral re-flectance. Computers and Electronics in Agricul-ture, 74(1):91–99, 2010.
W. Huang, D. W. Lamb, Z. Niu, Y. Zhang, L. Liu, and J. Wang. Identification of yellow rust in wheat using in-situ spectral reflectance measurements and airborne hyperspectral imaging. Precision Agriculture, 8(4–5):187–197, 2007.
X. E. Pantazi, D. Moshou, T. Alexandridis, R. L. Whetton, and A. M. Mouazen. Wheat yield predic-tion using machine learning and advanced sens-ing techniques. Computers and Electronics in Agriculture, 121:57–65, 2016.
J. Ma, K. Du, F. Zheng, et al. A recognition method for cucumber diseases using leaf symptom im-ages based on deep convolutional neural net-work. Computers and Electronics in Agriculture, 154:18–24, 2018.
J. Su, W. Liu, and S. Guo. Detection of wheat yellow rust using UAV multispectral imagery and machine learning. Remote Sensing, 10(12):2020, 2018.
D. S. Mueller, K. A. Wise, A. J. Sisson, et al. Corn disease loss estimates from the United States and Ontario, Canada. Plant Health Progress, 17(3):211–222, 2016.
R. Calderón, J. A. Navas-Cortés, and P. J. Zarco-Tejada. Early detection of crop diseases using hy-perspectral imaging. Remote Sensing of Environ-ment, 139:231–245, 2013.
J. Abdulridha, O. Batuman, and Y. Ampatzidis. UAV-based remote sensing technique to detect cit-rus canker disease using multispectral imaging. Precision Agriculture, 20(5):1–17, 2019.
A. Pourreza, H. S. Lee, M. Raveh, et al. Hyperspec-tral imaging for citrus greening detection. Com-puters and Electronics in Agriculture, 117:42–49, 2015.
H. Al-Saddik, M. Simon, and Y. Cointault. Deep learning based approach for plant disease detec-tion. Plant Methods, 17:80, 2021.
C. Gessler, I. Pertot, and M. Perazzolli. Plas-mopara viticola: A review of knowledge on downy mildew of grapevine and effective disease management. Phytopathologia Mediterranea, 50(1):3–44, 2011.
S. Delalieux, B. Somers, P. Coppin, et al. Detec-tion of biotic stress in apple trees using hyperspec-tral imagery. International Journal of Remote Sensing, 30(8):1887–1912, 2009.
J. Albetis, S. Duthoit, F. Guttler, et al. Detec-tion of Flavescence dorée grapevine disease using unmanned aerial vehicle (UAV) multispectral im-agery. Remote Sensing, 9(4):308, 2017.
G. L. Hartman, J. C. Rupe, E. J. Sikora, et al. Com-pendium of Soybean Diseases and Pests. APS Press, 2015.
K. Nagasubramanian, S. Jones, S. Singh, et al. Hyperspectral band selection using genetic algo-rithm and support vector machines for early iden-tification of charcoal rot disease in soybean stems. Plant Methods, 14:86, 2018.
M. Tan and Q. Le. EfficientNet: Rethinking model scaling for convolutional neural networks. Pro-ceedings of the International Conference on Ma-chine Learning, 2019.
T. B. Sutton, H. S. Aldwinckle, A. M. Agnello, and J. F. Walgenbach. Compendium of Apple and Pear Diseases and Pests. APS Press, 2014.
J. D. Pujari, R. Yakkundimath, and A. S. Byadgi. Image processing based detection of fungal dis-eases in plants. Procedia Computer Science, 46:1802–1808, 2015.
L. Pádua, J. J. Sousa, E. Peres, and R. Morais. UAV-based hyperspectral imaging for precision agri-culture. Remote Sensing, 9(11):1110, 2017.
J. M. Bové. Huanglongbing: A destructive, newly-emerging, century-old disease of citrus. Journal of Plant Pathology, 88(1):7–37, 2006.
M. Kerkech, A. Hafiane, and R. Canals. Vine dis-ease detection in UAV multispectral images by deep learning. Precision Agriculture, 21(5):1–20, 2020.
M. Govari and A. Pexara. Nitrates and nitrites in meat products. Journal of the Hellenic Veterinary Medical Society, 66(3):127–140, 2015.
S. Bansal, A. Singh, M. Mangal, A. K. Mangal, and S. Kumar. Food adulteration: Sources, health risks, and detection methods. Critical Reviews in Food Science and Nutrition, 57(6):1174–1189, 2017.
A. Singh, M. Shukla, A. K. Seth, et al. Awareness and understanding of adulteration in common household kitchen items: A study in rural commu-nities. Journal of Family Medicine and Primary Care, 14(4):1403–1408, 2025.
M. Koul, R. R. Bisht, and A. Adit. Detection of adul-teration in daily food items: Insights into labora-tory procedures. Hans Shodh Sudha, 1(1):20–26, 2020.
A. Choudhary, N. Gupta, F. Hameed, and S. Choton. An overview of food adulteration: Con-cept, sources, impact, challenges and detec-tion. International Journal of Chemical Studies, 8(1):2564–2573, 2020.
S. Awasthi, K. Jain, A. Das, R. Alam, G. Surti, and N. Kishan. Analysis of food quality and food adul-terants from different departmental and local gro-cery stores by qualitative analysis for food safety. IOSR Journal of Environmental Science, Toxicol-ogy and Food Technology, 8(2):22–26, 2014.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
All content published in Public Health - Open Journal (PHOJ) is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license allows anyone to copy, distribute, transmit, and adapt the work — including for commercial purposes — provided appropriate credit is given to the original author(s) and source.
