Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions

Cihan Ünal; Cengizhan Tumer; Elham Yasin; Ilkay Cinar; Murat Koklu

doi:10.15832/ankutbd.1837896

Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions

Abstract

Early and accurate diagnosis of potato leaf diseases is critical for preventing yield losses under real field conditions. This study proposes a hybrid deep feature–based machine learning framework that combines transfer learning and ensemble classifiers to automatically identify seven potato leaf disease classes from images. A total of 4,260 images from the publicly available Potato Leaf Disease Dataset were organized into seven categories: Bacteria, Virus, Pest, Fungi, Nematode, Phytophthora, and Healthy. Real-time image augmentation was performed using Keras ImageDataGenerator to improve strength to field variability. Deep feature vectors were extracted from three pre-trained convolutional neural networks (ResNet50, EfficientNetB0, and MobileNetV2), each followed by a lightweight dense head, and concatenated into 768-dimensional feature representations. After standardization, dimensionality reduction was applied via principal component analysis, and class imbalance in the training set was addressed using the SMOTE-ENN hybrid resampling method. On these deep features, 32 classical machine learning and ensemble models including SVMs, tree-based methods, boosting algorithms, multilayer perceptrons, and four ensemble schemes, were trained. Model performance was assessed by three-fold cross-validation on the training set and final evaluation on the held-out validation set using accuracy, precision, recall, and macro F1-score. Ensemble models outperformed individual classifiers. The best performance was obtained with the StackingClassifier_L2 model, which combines XGBoost, LightGBM, Random Forest, SVM with RBF kernel, and Extra Trees within a stacking framework. This model achieved an accuracy of 81.34% and a macro F1-score of 81.74% on the validation set. The proposed hybrid system, which integrates multi-backbone deep feature extraction with comprehensive classical and ensemble classifiers, provides a robust and practical solution for automatic potato leaf disease classification in uncontrolled field conditions. The results suggest that stacking-based ensembles on top of deep features can capture complex visual patterns more effectively than single models and may support decision-making in precision agriculture.

Keywords

References

Alhammad S M, Khafaga D S, El-Hady W M, Samy F M & Hosny K M (2025). Deep learning and explainable AI for classification of potato leaf in Artificial intelligence/articles/10.3389/frai.2024.1449329/full Intelligence, 7, 1449329. https://www.frontiersin.org/journals/artificial
Arshad F, Mateen M, Hayat S, Wardah M, Al-Huda Z, Gu Y H & Al-antari M A (2023). PLDPNet: End-to-end hybrid deep learning framework for potato leaf disease prediction. Alexandria Engineering Journal 78: 406-418. https://doi.org/10.1016/j.aej.2023.07.076
Arshaghi A, Ashourin M & Ghabeli L (2021). Detection and Classification of Potato Diseases Potato Using a New Convolution Neural Network Architecture. Traitement du Signal, 38(6). https://doi.org/10.18280/ts.380622
Asghar M, Khan Z F, Ramzan M, Khan M A, Baili J, Zhang Y, Nam Y & Nam Y C (2025). A lightweight hybrid model for scalable and robust plant leaf disease classification. Scientific Reports, 15(1), 32353. https://www.nature.com/articles/s41598-025-08788-4
Batool A, Hyder S B, Rahim A, Waheed N & Asghar M A (2020). Classification and identification of tomato leaf disease using deep neural network. 2020 International conference https://doi.org/10.1109/ICEET48479.2020.9048207 and on engineering and emerging technologies (ICEET), 1-6.
Bhavani G & Chalapathi M M V (2026). PotatoLeafNet: two-stage convolutional neural networks for effective Potato Leaf disease identification classification. Frontiers intelligence/articles/10.3389/frai.2025.1668839/full in Artificial Intelligence. https://www.frontiersin.org/journals/artificial
Brahimi M, Boukhalfa K & Moussaoui A (2017). Deep learning for tomato diseases: classification and symptoms visualization. Applied Artificial Intelligence, 31(4): 299-315. https://doi.org/10.1080/08839514.2017.1315516
Buslaev A, Iglovikov V I, Khvedchenya E, Parinov A, Druzhinin M & Kalinin A A (2020). Albumentations: fast and flexible image augmentations. Information, 11(2), 125. https://doi.org/10.3390/info11020125

Chang C-Y & Lai C-C (2024). Potato Leaf Disease Detection Based on a Lightweight Deep Learning Model. Machine Learning and Knowledge Extraction. https://ouci.dntb.gov.ua/en/works/lmYnz2Pl/
Goyal B, Pandey A K, Kumar R & Gupta M (2023). Disease detection in potato leaves using an efficient deep learning model. 2023 International Conference on Data Science and Network Security (ICDSNS), 01-05. https://doi.org/10.1109/ICDSNS58469.2023.10245369
Grati R, Abdallah E B, Boukadi K & Smaoui A (2024, January). Potato Leaf Disease Detection Approach Based on Transfer Learning with Spatial Attention. In ICINCO (2024). 146-155. https://www.scitepress.org/Papers/2024/130662/130662.pdf
Hang J, Zhang D., Chen, P., Zhang, J., & Wang, B. (2019). Classification of plant leaf diseases based on improved convolutional neural network. Sensors, 19(19), 4161. https://doi.org/10.3390/s19194161
He, K., Zhang X, Ren S & Sun J (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778. https://doi.org/10.1109/CVPR.2016.90
Hong H, Lin J & Huang F (2020). Tomato disease detection and classification by deep learning. 2020 International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), 25-29. https://doi.org/10.1109/ICBAIE49996.2020.00012
Iqbal M A & Talukder K H (2020). Detection of potato disease using image segmentation and machine learning. 2020 international conference on wireless communications signal https://doi.org/10.1109/WiSPNET48689.2020.9198563 processing and networking (WiSPNET), 43-47.
Islam M, Dinh A, Wahid K & Bhowmik P (2017). Detection of potato diseases using image segmentation and multiclass support vector machine. 2017 IEEE 30th canadian conference on electrical and computer engineering (CCECE), 1-4. https://doi.org/10.1109/CCECE.2017.7946594
Kang F, Li J, Wang C & Wang F (2023). A lightweight neural network-based method for identifying early-blight and late-blight leaves of potato. Applied sciences, 13(3), 1487. https://www.mdpi.com/2076-3417/13/3/1487
Lee T-Y, Lin I-A, Yu J-Y, Yang J-m & Chang Y-C (2021). High efficiency disease detection for potato leaf with convolutional neural network. SN Computer Science, 2(4), 297. https://doi.org/10.1007/s42979-021-00691-9
Mohanty S P, Hughes D P & Salathé M (2016). Using deep learning for image-based plant disease detection. Frontiers in plant science, 7, 215232. https://doi.org/10.3389/fpls.2016.01419
Mulugeta A T, Jifara W, Bogale E, Desiyo T & Mokonnen A (2025). Early Detection and Classification of Potato Leaf Disease Using Convolutional Neural Networks. Applied Computational Intelligence and Soft Computing, 2025(1), 7614841. https://doaj.org/article/c6de440e04aa449981fdaa76138f0188
Nazir T, Iqbal M M & Jabbar S (2023). EfficientPNet—An Optimized and Efficient Deep Learning Approach for Classifying Disease of Potato Plant Leaves. Agriculture. MDPI. 13(4), 1-18. https://ideas.repec.org/a/gam/jagris/v13y2023i4p841-d1119172.html
Patil P, Yaligar N & Meena S (2017). Comparision of performance of classifiers-svm, rf and ann in potato blight disease detection using leaf images. 2017 IEEE international conference on computational intelligence and computing research (ICCIC), 1-5. https://doi.org/10.1109/ICCIC.2017.8524301
Powers D M (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061. https://doi.org/10.48550/arXiv.2010.16061
Rashid J, Khan I, Ali G, Almotiri S H, AlGhamdi M A & Masood K (2021). Multi-level deep learning model for potato leaf disease recognition. Electronics, 10(17), 2064. https://doi.org/10.3390/electronics10172064
Catal Reis H (2026). CropHealthNet: potato disease detection using depthwise separable convolutional neural networks. Journal of Crop Health, 78(1), 29. https://link.springer.com/article/10.1007/s10343-026-01294-1
Roy S, Jain A, Dubey A K, Panwar A, Jain V, Kaur S, Shah M.A. & Mallik S (2025). SPUDNET5-R3: A Lightweight Hybrid and Explainable CNN Model for Potato Leaf Blight Detection. Research Square. https://ouci.dntb.gov.ua/en/works/4VPmKOPY/
Sandler M, Howard A, Zhu M, Zhmoginov A & Chen L-C (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition, 4510-4520. https://doi.org/10.1109/CVPR.2018.00474
Sangar G & Rajasekar V (2025). Optimized classification of potato leaf disease using EfficientNet-LITE and KE-SVM in diverse environments. Frontiers in plant science, 16, 1499909. https://www.frontiersin.org/journals/plant science/articles/10.3389/fpls.2025.1499909/full
Sardogan M, Tuncer A & Ozen Y (2018). Plant leaf disease detection and classification based on CNN with LVQ algorithm. 2018 3rd international conference on computer science and engineering (UBMK), 382-385. https://doi.org/10.1109/UBMK.2018.8566635
Shabrina N H, Indarti S, Maharani R, Kristiyanti D A, Irmawati I & Prastomo N M (2023). Potato Leaf Disease Dataset in Uncontrolled Environment (Version 1). Mendeley Data. https://doi.org/10.17632/ptz377bwb8.1
Shaheed K, Qureshi I, Abbas F, Jabbar S, Abbas Q, Ahmad H & Sajid M Z (2023). EfficientRMT-Net—an efficient ResNet-50 and vision transformers approach for classifying potato plant leaf diseases. Sensors, 23(23), 9516. https://doi.org/10.3390/s23239516
Shorten C & Khoshgoftaar T M (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1), 1-48. https://doi.org/10.1186/s40537-019-0197-0 conference
Shruthi U, Nagaveni V & Raghavendra B (2019). A review on machine learning classification techniques for plant disease detection. 2019 5th International on advanced computing & communication systems (ICACCS), 281-284. https://doi.org/10.1109/ICACCS.2019.8728415
Sinamenye J H, Chatterjee A & Shrestha R (2025). Potato plant disease detection: leveraging hybrid deep learning models. BMC Plant Biology, 25(1), 647. https://link.springer.com/article/10.1186/s12870-025-06679-4
Sinshaw N T, Assefa B G, Mohapatra S K & Beyene A M (2022). Applications of computer vision on automatic potato plant disease detection: A systematic literature review. Computational intelligence and neuroscience, 2022(1), 7186687. https://doi.org/10.1155/2022/7186687
Sokolova M & Lapalme G (2009). A systematic analysis of performance measures for classification tasks. Information processing & management, 45(4), 427-437. https://doi.org/10.1016/j.ipm.2009.03.002
Tambe U Y, Shobanadevi A, Shanthini A & Hsu H-C (2023). Potato Leaf Disease Classification using Deep Learning: A Convolutional Neural Network Approach. arXiv preprint arXiv:2311.02338. https://doi.org/10.48550/arXiv.2311.02338 Tan L, Lu J & Jiang H (2021). Tomato Leaf Diseases Classification Based on Leaf Images: A Comparison between Classical Machine Learning and Deep Learning Methods. AgriEngineering, 3(3), 542-558. https://doi.org/10.3390/agriengineering3030035
Tan M & Le Q (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning, 6105-6114. https://doi.org/10.48550/arXiv.1905.11946
Tarik M I, Akter S, Al Mamun A & Sattar A (2021). Potato disease detection using machine learning. 2021 Third international conference on intelligent communication technologies https://doi.org/10.1109/ICICV50876.2021.9388606 and virtual mobile networks (ICICV), 800-803.

Details

Primary Language

English

Subjects

Artificial Intelligence (Other)

Journal Section

Research Article

Authors

Cihan Ünal ^*
0000-0002-5255-4078
Türkiye

Cengizhan Tumer This is me
0009-0008-2791-4036
Türkiye

Elham Yasin
0000-0003-3246-6000
Iraq

Ilkay Cinar
0000-0003-0611-3316
Türkiye

Murat Koklu
0000-0002-2737-2360
Türkiye

Publication Date

October 12, 2026

Submission Date

December 8, 2025

Acceptance Date

April 30, 2026

Published in Issue

Year 2026 Volume: 32 Number: 4

DOI

https://doi.org/10.15832/ankutbd.1837896

IZ

https://izlik.org/JA96EL34DJ

Cite

RIS / Bibtex

APA

Ünal, C., Tumer, C., Yasin, E., Cinar, I., & Koklu, M. (2026). Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions. Journal of Agricultural Sciences, 32(4), 928-952. https://doi.org/10.15832/ankutbd.1837896

AMA

1.Ünal C, Tumer C, Yasin E, Cinar I, Koklu M. Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions. J Agr Sci-Tarim Bili. 2026;32(4):928-952. doi:10.15832/ankutbd.1837896

Chicago

Ünal, Cihan, Cengizhan Tumer, Elham Yasin, Ilkay Cinar, and Murat Koklu. 2026. “Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions”. Journal of Agricultural Sciences 32 (4): 928-52. https://doi.org/10.15832/ankutbd.1837896.

EndNote

Ünal C, Tumer C, Yasin E, Cinar I, Koklu M (October 1, 2026) Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions. Journal of Agricultural Sciences 32 4 928–952.

IEEE

[1]C. Ünal, C. Tumer, E. Yasin, I. Cinar, and M. Koklu, “Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions”, J Agr Sci-Tarim Bili, vol. 32, no. 4, pp. 928–952, Oct. 2026, doi: 10.15832/ankutbd.1837896.

ISNAD

Ünal, Cihan - Tumer, Cengizhan - Yasin, Elham - Cinar, Ilkay - Koklu, Murat. “Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions”. Journal of Agricultural Sciences 32/4 (October 1, 2026): 928-952. https://doi.org/10.15832/ankutbd.1837896.

JAMA

1.Ünal C, Tumer C, Yasin E, Cinar I, Koklu M. Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions. J Agr Sci-Tarim Bili. 2026;32:928–952.

MLA

Ünal, Cihan, et al. “Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions”. Journal of Agricultural Sciences, vol. 32, no. 4, Oct. 2026, pp. 928-52, doi:10.15832/ankutbd.1837896.

Vancouver

1.Cihan Ünal, Cengizhan Tumer, Elham Yasin, Ilkay Cinar, Murat Koklu. Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions. J Agr Sci-Tarim Bili. 2026 Oct. 1;32(4):928-52. doi:10.15832/ankutbd.1837896