Keywords
Deep learning
Image classification
Transfer learning
Sustainable agriculture
How to Cite
Abstract
As a strategic global crop, maize productivity is directly threatened by leaf diseases such as Southern Leaf Blight and Gray Leaf Spot, making early and accurate detection crucial for food security. Artificial intelligence, particularly deep learning, provides a powerful solution for the automated classification of plant diseases from images. This study developed an intelligent system to address this challenge, utilizing the publicly available PlantVillage dataset to evaluate five leading Convolutional Neural Network (CNN) architectures: DenseNet121, InceptionV3, MobileNetV2, ResNet-50, and VGG16. The models were optimized with established techniques, including transfer learning, data augmentation, and hyper-parameter tuning, while a Soft Voting Ensemble strategy was used to enhance combined performance. Evaluation across multiple metrics showed that InceptionV3 achieved the highest test accuracy at 94.47%. However, MobileNetV2 demonstrated the strongest performance across all metrics with a 95% cumulative accuracy and proved highly efficient, making it ideal for deployment on mobile devices. These findings confirm the significant potential of deep learning for building cost-effective and efficient diagnostic systems in agriculture, ultimately contributing to the reduction of crop losses and the promotion of sustainable farming practices.
References
Ahila Priyadharshini, R., S. Arivazhagan, M. Arun, and A. Mirnalini, 2019. Maize leaf disease classification using deep convolutional neural networks. Neural Computing and Applications, 31: 8887–8895.
Bayram, B., I. Kunduracioglu, S. Ince, and I. Pacal, 2025. A systematic review of deep learning in MRI-based cerebral vascular occlusion-based brain diseases. Neuroscience.
Bickel, J. T. and A. M. Koehler, 2021. Review of Pythium species causing damping-off in corn. Plant Health Progress, 22: 219–225.
Brahimi, F., A. Aid, M. Amad, A. Mehennaoui, and A. Baadache, 2024. Enhanced k-nearest neighbors for smart cardiovascular disease prediction in IoT system. Revue d’Intelligence Artificielle, 38.
Cakmak, Y. and I. Pacal, 2025. Enhancing breast cancer diagnosis: A comparative evaluation of machine learning algorithms using the Wisconsin dataset. Journal of Operations Intelligence, 3: 175–196.
Cakmak, Y., S. Safak, M. A. Bayram, and I. Pacal, 2024. Comprehensive evaluation of machine learning and ANN models for breast cancer detection. Computer and Decision Making: An International Journal, 1: 84–102.
Chen, J., J. Chen, D. Zhang, Y. Sun, and Y. A. Nanehkaran, 2020. Using deep transfer learning for image-based plant disease identification. Computers and Electronics in Agriculture, 173: 105393.
Chouhan, S. S., U. P. Singh, and S. Jain, 2024. Applications of computer vision and drone technology in Agriculture 4.0. Springer.
Committee, I. A. P. et al., 2023. USDA agricultural projections to 2032.
Demanyuk, O., G. Matusevich, S. Mazur, D. Shatsman, S. Bukhtyk, et al., 2023. Wheat, corn, and sunflower are the primary crops of Ukrainian exports. Agriculture and Plant Sciences: Theory and Practice, pp. 41–50.
Dinh, S.-Q. and D. C. Joyce, 2007. Prospects for cut-flower postharvest disease management with host defence elicitors. Stewart Postharvest Review, 3: 1–11.
Dong, X., Q. Wang, Q. Huang, Q. Ge, K. Zhao, et al., 2023. PDDDPretrain: A series of commonly used pre-trained models support image-based plant disease diagnosis. Plant Phenomics, 5: 0054.
Fang, X. and A. L. Katchova, 2023. Evaluating the OECD–FAO and USDA agricultural baseline projections. Q Open, 3: qoad029.
Ferentinos, K. P., 2018. Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145: 311–318.
Goyal, R., S. Kumari, A. Nath, and G. Kaur, 2025. IoRT and AI-driven solution for optimal herbicides spray on weeds in a dynamic agriculture environment. In International Conference on Advanced Information Networking and Applications, pp. 297–308, Springer.
He, K., X. Zhang, S. Ren, and J. Sun, 2016a. Deep residual learning for image recognition.
He, K., X. Zhang, S. Ren, and J. Sun, 2016b. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778.
Huang, G., Z. Liu, L. van der Maaten, and K. Q. Weinberger, 2017a. Densely connected convolutional networks.
Huang, G., Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, 2017b. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708.
Hughes, D., M. Salathé, et al., 2015. An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060.
˙Ince, S., I. Kunduracioglu, B. Bayram, and I. Pacal, 2025. U-Net-based models for precise brain stroke segmentation. Chaos Theory and Applications, 7: 50–60.
Jaya Krishna, V., A. S. Roy, M. Mahato, and S. Das, 2025. Artificial intelligence for precision agriculture and water management. In Integrated Land and Water Resource Management for Sustainable Agriculture Volume 2, pp. 1–20, Springer.
Kamilaris, A. and F. X. Prenafeta-Boldú, 2018. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147: 70–90.
Karaman, A., I. Pacal, A. Basturk, B. Akay, U. Nalbantoglu, et al., 2023. Robust real-time polyp detection system design based on YOLO algorithms by optimizing activation functions and hyperparameters with artificial bee colony (ABC). Expert Systems with Applications, 221: 119741.
Kaur, A., V. Kukreja, M. Kumar, A. Choudhary, and R. Sharma, 2024. A fine-tuned DenseNet model for an efficient maize leaf disease classification. 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI 2024).
Kurtulus, I. L., M. Lubbad, O. M. D. Yilmaz, K. Kilic, D. Karaboga, et al., 2024. A robust deep learning model for the classification of dental implant brands. Journal of Stomatology, Oral and Maxillofacial Surgery, 125: 101818.
Lecun, Y., Y. Bengio, and G. Hinton, 2015. Deep learning. Nature, 521: 436–444.
Lubbad, M., D. Karaboga, A. Basturk, B. Akay, U. Nalbantoglu, et al., 2024a. Machine learning applications in detection and diagnosis of urology cancers: A systematic literature review. Neural Computing and Applications, 36: 6355–6379.
Lubbad, M. A., I. L. Kurtulus, D. Karaboga, K. Kilic, A. Basturk, et al., 2024b. A comparative analysis of deep learning-based approaches for classifying dental implants decision support system. Journal of Imaging Informatics in Medicine, 37: 2559–2580.
Mahlein, A.-K., 2016. Plant disease detection by imaging sensors – parallels and specific demands for precision agriculture and plant phenotyping. Plant Disease, 100: 241–251.
Maurya, P. K., L. K. Verma, G. Thakur, and Mayank, 2025. Artificial intelligence for precision agriculture and water management. In Integrated Land and Water Resource Management for Sustainable Agriculture Volume 2, pp. 185–198, Springer.
Meng, R., Z. Lv, J. Yan, G. Chen, F. Zhao, et al., 2020. Development of spectral disease indices for southern corn rust detection and severity classification. Remote Sensing, 12: 3233.
Ozdemir, B., E. Aslan, and I. Pacal, 2025. Attention enhanced InceptionNext based hybrid deep learning model for lung cancer detection. IEEE Access.
Pacal, I., 2024. Enhancing crop productivity and sustainability through disease identification in maize leaves: Exploiting a large dataset with an advanced vision transformer model. Expert Systems with Applications, 238: 122099.
Pacal, ˙I., 2025. Diagnostic analysis of various cancer types with artificial intelligence.
Pacal, I., O. Akhan, R. T. Deveci, and M. Deveci, 2025. NextBrain: Combining local and global feature learning for brain tumor classification. Brain Research, p. 149762.
Pacal, I. and O. Attallah, 2025. InceptionNext-Transformer: A novel multi-scale deep feature learning architecture for multimodal breast cancer diagnosis. Biomedical Signal Processing and Control, 110: 108116.
Pacal, I., A. Karaman, D. Karaboga, B. Akay, A. Basturk, et al., 2022. An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets. Computers in Biology and Medicine, 141: 105031.
Pacal, I., I. Kunduracioglu, M. H. Alma, M. Deveci, S. Kadry, et al., 2024. A systematic review of deep learning techniques for plant diseases. Artificial Intelligence Review, 57: 304.
Philpott, T., 2020. Perilous bounty: The looming collapse of American farming and how we can prevent it. Bloomsbury Publishing USA.
Pignati, W., 2018. Use of agrochemicals in Brazil: The workers’ and environmental health perspective. Revista Brasileira de Medicina do Trabalho, 16: 37–38.
Ranum, P., J. P. Peña-Rosas, and M. N. Garcia-Casal, 2014. Global maize production, utilization, and consumption. Annals of the New York Academy of Sciences, 1312: 105–112.
Rui, W., W. Cheng, P. Hong-yu, et al., 2022. Intelligent diagnosis of northern corn leaf blight with deep learning model. Journal of Integrative Agriculture, 21: 1094–1105.
Sandler, M., A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, 2018a. MobileNetV2: Inverted residuals and linear bottlenecks.
Sandler, M., A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, 2018b. MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520.
Sathya Priya, R., N. Jagathjothi, M. Yuvaraj, N. Suganthi, R. Sharmila, et al., 2025. Remote sensing application in plant protection and its usage in smart agriculture to hasten decision making of the farmers. Journal of Plant Diseases and Protection, 132: 84.
Simonyan, K. and A. Zisserman, 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, G. and S. Sharma, 2025. A comprehensive review on the Internet of Things in precision agriculture. Multimedia Tools and Applications, 84: 18123–18198.
Sladojevic, S., M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, 2016. Deep neural networks based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, 2016: 3289801.
Surendran, U., K. C. V. Nagakumar, and M. P. Samuel, 2024. Remote sensing in precision agriculture. In Digital Agriculture: A Solution for Sustainable Food and Nutritional Security, pp. 201–223, Springer.
Szegedy, C., V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, 2016a. Rethinking the Inception architecture for computer vision.
Szegedy, C., V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, 2016b. Rethinking the Inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826.
Teixeira, E., K. C. Kersebaum, A.-G. Ausseil, R. Cichota, J. Guo, et al., 2021a. Understanding spatial and temporal variability of N leaching reduction by winter cover crops under climate change. Science of The Total Environment, 771: 144770.
Teixeira, E., K. C. Kersebaum, A.-G. Ausseil, R. Cichota, J. Guo, et al., 2021b. Understanding spatial and temporal variability of N leaching reduction by winter cover crops under climate change. Science of The Total Environment, 771: 144770.
Waheed, A., M. Goyal, D. Gupta, A. Khanna, A. E. Hassanien, et al., 2020. An optimized dense convolutional neural network model for disease recognition and classification in corn leaf. Computers and Electronics in Agriculture, 175: 105456.
Willer, H., J. Trávníček, and B. Schlatter, 2024a. The world of organic agriculture. Statistics and emerging trends 2024.
Willer, H., J. Trávníček, and B. Schlatter, 2024b. The world of organic agriculture. Statistics and emerging trends 2024.
Zeynalov, J., Y. Çakmak, and ˙I. Paçal, 2025. Automated apple leaf disease classification using deep convolutional neural networks: A comparative study on the Plant Village dataset. Journal of Computer Science and Digital Technologies, 1: 5–17.
Zhang, X., Y. Qiao, F. Meng, C. Fan, and M. Zhang, 2018. Identification of maize leaf diseases using improved deep convolutional neural networks. IEEE Access, 6: 30370–30377.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.