ENHANCING POTATO CROP HEALTH MONITORING USING TWO STAGE CNN BASED DISEASE CLASSIFICATION MODELS


320 / 230

Authors

https://doi.org/10.56093/potatoj.v52i2.167064

Keywords:

Potato disease, CNN, Deep Learning, Late blight, Early blight

Abstract

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

Download data is not yet available.

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

2026-03-09

How to Cite

Shastri, A., More, A. ., Soni, T., Ratnaparkhe, M., Rawat, S., Sabale, K., & Paliwal, M. (2026). ENHANCING POTATO CROP HEALTH MONITORING USING TWO STAGE CNN BASED DISEASE CLASSIFICATION MODELS. Potato Journal, 52(2). https://doi.org/10.56093/potatoj.v52i2.167064
Citation