ENHANCING POTATO CROP HEALTH MONITORING USING TWO STAGE CNN BASED DISEASE CLASSIFICATION MODELS
320 / 230
Keywords:
Potato disease, CNN, Deep Learning, Late blight, Early blightAbstract
Potato is one of the most extensively cultivated crops in India as well as worldwide and
serves as a staple food in many regions. Due to its agricultural and economic importance, effective
disease management is essential to ensure healthy crop yields. Traditional methods of disease detection
rely on manual visual inspection by farmers or agricultural experts, which often lack precision and are
prone to misdiagnosis, leading to substantial crop losses. This study proposes a deep learning-based
approach for automated disease detection in potato plants using a Convolutional Neural Network
(CNN). The novelty of this work lies in developing a two-stage CNN framework that first classifies
the potato leaf images as either healthy or unhealthy. Next, the unhealthy leaf images are further
classified as either early blight or late blight diseases. The proposed CNN models are optimized using
the Adam optimizer with a learning rate of 0.0001. Extensive experimentation on a dataset of 1,500
images demonstrates high classification accuracies of 98.3% and 99% for the two stages, respectively.
The results demonstrate that our proposed CNN models are highly effective for automated disease
detection and improve decision-making in potato crops.
Downloads
References
1. Adhikari, S. (2024). Advancements in Agricultural
2. Technology: Vision Transformer-Based Potato Leaf
3. Disease Classification. Journal of Soft Computing
4. Paradigm, 6(2), 169-185.
5. Bajpai, A., Sahu, S., & Tiwari, N. K. (2025). Integrating
6. Attention Mechanisms and Squeeze-and-Excitation
7. Blocks for Accurate Potato Leaf Disease Detection.
8. Potato Research, 1-21.
9. Chang, C. Y., & Lai, C. C. (2024). Potato leaf disease
10. detection based on a lightweight deep learning
11. model. Machine Learning and Knowledge Extraction,
12. 6(4), 2321-2335.
13. Chollet, F. (2017). Xception: Deep learning with
14. depthwise separable convolutions. IEEE Conference
15. on Computer Vision and Pattern Recognition (CVPR)
16. (pp. 1251-1258). IEEE.
17. Chowdhury, N., Sultana, J., Rahman, T., Chowdhury,
18. T., Khan, F. T., & Chakraborty, A. (2024). Potato
19. leaf disease detection through ensemble average
20. deep learning model and classifying the disease
21. severity. Indonesian Journal of Electrical Engineering
22. and Computer Science, 35(1), 494-502.
23. Dalal, N., & Triggs, B. (2005). Histograms of oriented
24. gradients for human detection. 2005 IEEE computer
25. society conference on computer vision and pattern
26. recognition (CVPR’05). 1, pp. 886--893. IEEE.
27. Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei,
28. L. (2009). ImageNet: A large-scale hierarchical image
29. database. IEEE Conference on Computer Vision and
30. Pattern Recognition (pp. 248--255). IEEE.
31. Fuadi, I., Putri, R. N., Nasien, D., & Oktarina, D. (2024).
32. Deep Learning Approaches for Potato Leaf Disease
33. Detection: Evaluating the Efficacy of Convolutional
34. Neural Network Architectures. Revue d’Intelligence
35. Artificielle, 38(2), 717.
36. Gülmez, B. (2024). A comprehensive review of
37. convolutional neural networks based disease
38. detection strategies in potato agriculture. Potato
39. Research, 1-35.
40. Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep
41. learning in agriculture: A survey. Computers and
42. Electronics in Agriculture, 147, 70--90.
43. Lanjewar, M. G., Morajkar, P., & Payaswini, P. (2024).
44. Modified transfer learning frameworks to identify
45. potato leaf diseases. Multimedia Tools and Applications,
46. 83(17), 50401-50423.
47. Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016).
48. Using deep learning for image-based plant disease
49. detection. Frontiers in plant science, 7, 215232.
50. Muhammad, A. P. (2025, March 15). Potato Leaf Disease
51. Dataset. Retrieved from Kaggle: https://www.
52. kaggle.com/datasets/muhammadardiputra/potatoleaf-
53. disease-dataset
54. Paul, H., Ghatak, S., Chakraborty, S., Pandey, S. K.,
55. Dey, L., Show, D., & Maity, S. (2024). A study and
56. comparison of deep learning based potato leaf
57. disease detection and classification techniques using
58. explainable AI. Multimedia Tools and Applications,
59. 83(14), 42485-42518.
60. Pujari, J. D., Yakkundimath, R., & Byadgi, A. S.
61. (2015). Image processing based detection of fungal
62. diseases in plants. Procedia Computer Science, 46,
63. 1802--1808.
64. Radwan, M., Alhussan, A. A., Ibrahim, A., & Tawfeek, S.
65. M. (2024). Potato Leaf Disease Classification Using
66. Optimized Machine Learning Models and Feature
67. Selection Techniques. Potato Research, 1-25.
68. Rashid, J., Khan, I., Ali, G., Almotiri, S. H., AlGhamdi, M.
69. A., & Masood, K. (2021). Multi-level deep learning
70. model for potato leaf disease recognition. Electronics,
71. 10(17), 2064.
72. Raza, A., Pitafi, A. H., Shaikh, M. K., & Ahmed, K.
73. (2025). Optimizing Potato Leaf Disease Recognition:
74. Insights DENSE-NET-121 and Gaussian Elimination
75. Filter Fusion. Heliyon, 11(3), e42318.
76. Reis, H. C., & Turk, V. (2024). Potato leaf disease
77. detection with a novel deep learning model based
78. on depthwise separable convolution and transformer
79. networks. Engineering Applications of Artificial
80. Intelligence, 133, 108307.
81. Shastri, A. A., Ahuja, K., Ratnaparkhe, M., &
82. Busnel, Y. (2021). Probabilistically sampled and
83. spectrally clustered plant species using phenotypic
84. characteristics. PeerJ, 9, e11927.
85. Shastri, A. A., Ahuja, K., Ratnaparkhe, M., Shah, A.,
86. Gagrani, A., & Lal, A. (2019). Vector quantized
87. spectral clustering applied to whole genome
88. sequences of plants. Evolutionary Bioinformatics, 15,
89. 1--7.
90. Shastri, A. A., Prajapati, Y., Katariya, H., Paliwal, M.,
91. & Sabale, K. (2025). Enhancing Clinical Outcomes
92. Using Deep Learning Solution for Accurate Lung
93. Cancer Classification. Sensing and Imaging, 26(1), 19.
94. Shastri, A. A., Tamrakar, D., & Ahuja, K. (2018). Densitywise
95. two stage mammogram classification using
96. texture exploiting descriptors. Expert Systems with
97. Applications, 99, 71--82.
98. Singh, V., & Misra, A. K. (2017). Detection of plant
99. leaf diseases using image segmentation and soft
100. computing techniques. Information processing in
101. Agriculture, 4(1), 41--49.
102. Sofuoğlu, C. İ., & Bırant, D. (2024). Potato plant leaf
103. disease detection using deep learning method.
104. Journal of Agricultural Sciences, 30(1), 153-165.
105. Strange, R. N., & Scott, P. R. (2005). Plant disease:
106. A threat to global food security. Anual Report of
107. Phytopathology, 43, 83-116.
108. Upadhyay, S., Jain, J., & Prasad, R. (2024). Early Blight
109. and Late Blight Disease Detection in Potato Using
110. Efficientnetb0. International Journal of Experimental
111. Research and Review, 38, 15-25.
112. Wahabzada, M., Mahlein, A. K., Bauckhage, C., Steiner,
113. U., Oerke, E. C., & Kersting, K. (2015). Plant disease
114. detection from image data using deep learning. AI
115. and Society, 30(3), 463--474.
116. Zhang, C., Wang, S., Wang, C., Wang, H., Du, Y.,
117. & Zong, Z. (2025). Research on a Potato Leaf
118. Disease Diagnosis System Based on Deep Learning.
119. Agriculture, 15(4), 424.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Potato Journal

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The copyright of the articles published in Potato Journal is vested with the Indian Council of Agricultural Research, which reserves the right to enter into any agreement with any organization in India or abroad, for reprography, photocopying, storage and dissemination of information. The Council has no objection to using the material, provided the information is not being utilized for commercial purposes and wherever the information is being used, proper credit is given to ICAR.