Explainable Ensemble Transfer Learning with Adaptive Augmentation for Cassava Leaf Disease Detection
DOI:
https://doi.org/10.52436/1.jutif.2026.7.4.5480Keywords:
Adaptive Augmentation, Cassava Leaf Disease, Ensemble Model, Explainable Deep Learning, Grad-CAM, Transfer LearningAbstract
Cassava (Manihot esculenta) is a crucial commodity in tropical regions; yet, its output has markedly declined due to five primary categories of foliar diseases: Cassava Mosaic Disease (CMD), Cassava Brown Streak Disease (CBSD), Cassava Bacterial Blight (CBB), Cassava Green Mottle (CGM), and the healthy category. The constraints of deep learning models, which remain opaque, and data imbalances in the agriculture sector, pose significant hurdles to the development of precise and transparent diagnostic tools. This research seeks to establish an explainable deep learning framework utilizing ensemble transfer learning and adaptive augmentation to enhance the accuracy and interpretability of cassava leaf disease identification. The experimental investigation utilized 21,367 annotated photos from five disease categories within the Cassava Leaf Disease dataset. The dataset was first divided into training data (80%) and validation data (20%). The minority classes in the training data were augmented using Albumentations to rectify class distribution imbalances. As a result of this approach, an additional 51,280 photos were generated, resulting in a more balanced and representative class. The findings indicated that the ensemble averaging of ResNet50, DenseNet121, and EfficientNet-B0 achieved a validation accuracy of 86.75%, surpassing the performance of each individual model. Adaptive augmentation procedures enhance the model's generalization capabilities, while Gradient-weighted Class Activation Mapping (Grad-CAM) visualizes the leaf regions influencing classification judgments. The results validate that the use of adaptive augmentation, explainable AI, and ensemble transfer learning enhances the transparency and reliability of computer vision systems for detecting plant diseases. This study advances the creation of precise, interpretable, and pertinent AI models to enhance agricultural informatics.
Downloads
References
H. Tribiakto, “Enhancing Deep Learning-Based Classification of Cassava Leaf Diseases Using CLAHE and SMOTE,” Sistemasi, vol. 14, no. 6, p. 2698, 2025, doi: 10.32520/stmsi.v14i6.5530.
D. O. Oyewola, E. G. Dada, S. Misra, and R. Damaševičius, “Detecting Cassava Mosaic Disease Using a Deep Residual Convolutional Neural Network With Distinct Block Processing,” PeerJ Comput Sci, vol. 7, p. e352, 2021, doi: 10.7717/peerj-cs.352.
A. Ganguly, “Ensemble Learning for Plant Leaf Disease Detection: A Novel Approach for Improved Classification Accuracy,” 2023, doi: 10.21203/rs.3.rs-3257323/v1.
H. A. Jassim, Z. K. Taha, and A. K. Nawar, “A Twelve-layer Deep Convolution Neural Network for Fast, Efficient and Reliable Identification and Classification of Plant Diseases in Smart Farming,” Indonesian Journal of Electrical Engineering and Informatics, vol. 12, no. 4, pp. 802–817, Dec. 2024, doi: 10.52549/ijeei.v12i4.5455.
G. Owomugisha, F. Melchert, E. Mwebaze, J. A. Quinn, and M. Biehl, “Matrix Relevance Learning From Spectral Data for Diagnosing Cassava Diseases,” Ieee Access, vol. 9, pp. 83355–83363, 2021, doi: 10.1109/access.2021.3087231.
A. Pratondo, “Classification of Cassava (Manihot sp.) Leaf Variants Using Transfer Learning,” Indonesian Journal of Electrical Engineering and Informatics, vol. 11, no. 2, pp. 442–452, Jun. 2023, doi: 10.52549/ijeei.v11i2.4685.
L. C. Kimno, “Field Screening of Elite Cassava (Manihot Esculenta) Mutant Lines for Their Response to Mosaic and Brown Streak Viruses,” Journal of Experimental Agriculture International, vol. 45, no. 9, pp. 205–215, 2023, doi: 10.9734/jeai/2023/v45i92193.
P. Jha, “Implementation of Machine Learning Classification Algorithm Based on Ensemble Learning for Detection of Vegetable Crops Disease,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 1, 2024, doi: 10.14569/ijacsa.2024.0150157.
O. Abayomi‐Alli, R. Damaševičius, S. Misra, and R. Maskeliūnas, “Cassava Disease Recognition From low‐quality Images Using Enhanced Data Augmentation Model and Deep Learning,” Expert Syst, vol. 38, no. 7, 2021, doi: 10.1111/exsy.12746.
A. Nader, “Classification of Plant Leaf Disease Using Ensemble Deep Transfer Learning,” International Journal of Intelligent Computing and Information Sciences, vol. 24, no. 1, pp. 69–88, 2024, doi: 10.21608/ijicis.2024.278335.1331.
L. M. Close et al., “Three Years of High-Contrast Imaging of the PDS 70 B and C Exoplanets at Hα With MagAO-X: Evidence of Strong Protoplanet Hα Variability and Circumplanetary Dust,” Astron J, vol. 169, no. 1, p. 35, 2024, doi: 10.3847/1538-3881/ad8648.
A. Tabbakh and S. S. Barpanda, “A Deep Features Extraction Model Based on the Transfer Learning Model and Vision Transformer ‘TLMViT’ for Plant Disease Classification,” Ieee Access, vol. 11, pp. 45377–45392, 2023, doi: 10.1109/access.2023.3273317.
E. Göçeri, “Medical Image Data Augmentation: Techniques, Comparisons and Interpretations,” Artif Intell Rev, vol. 56, no. 11, pp. 12561–12605, 2023, doi: 10.1007/s10462-023-10453-z.
Y. I. Sulistya, E. T. B. Bangun, and D. A. Tyas, “CNN Ensemble Learning Method for Transfer Learning: A Review,” Ilkom Jurnal Ilmiah, vol. 15, no. 1, pp. 45–63, 2023, doi: 10.33096/ilkom.v15i1.1541.45-63.
G. Kalyani, K. Sai Sudheer, B. Janakiramaiah, and B. Narendra Kumar Rao, “Hyperparameter Optimization for Transfer Learning-based Disease Detection in Cassava Plants,” J Sci Ind Res (India), vol. 82, no. 5, pp. 536–545, May 2023, doi: 10.56042/jsir.v82i05.1089.
Y. Zhong, B. Huang, and C. Tang, “Classification of Cassava Leaf Disease Based on a Non-Balanced Dataset Using Transformer-Embedded ResNet,” Agriculture (Switzerland), vol. 12, no. 9, Sep. 2022, doi: 10.3390/agriculture12091360.
D. Hindarto, “Model Accuracy Analysis: Comparing Weed Detection in Soybean Crops With EfficientNet-B0, B1, and B2,” Jurnal Jtik (Jurnal Teknologi Informasi Dan Komunikasi), vol. 7, no. 4, pp. 734–744, 2023, doi: 10.35870/jtik.v7i4.1825.
H. A. Santoso, “Comparative Analysis of Convolutional Neural Network and DenseNet121 Transfer Learning in Agriculture Focusing on Crop Leaf Disease Identification,” Applied Computing and Informatics, 2024, doi: 10.1108/aci-03-2024-0132.
K. V, S. S, M. Sendil, K. Nagarajan, and D. Punetha, “Hybrid ensemble - deep transfer model for early cassava leaf disease classification,” Heliyon, vol. 10, no. 16, Aug. 2024, doi: 10.1016/j.heliyon.2024.e36097.
U. K. Lilhore et al., “Enhanced Convolutional Neural Network Model for Cassava Leaf Disease Identification and Classification,” Mathematics, vol. 10, no. 4, Feb. 2022, doi: 10.3390/math10040580.
M. Aasem and M. Iqbal, “Toward Explainable AI in Radiology: Ensemble-Cam for Effective Thoracic Disease Localization in Chest X-Ray Images Using Weak Supervised Learning,” Front Big Data, vol. 7, 2024, doi: 10.3389/fdata.2024.1366415.
M. Y. Attia and N. A. Noureldien, “Measuring Performance of Ensemble of Ensembles (EoE) Models,” 2023, doi: 10.21203/rs.3.rs-3192966/v1.
K. L. Bajema et al., “Severity and Long-Term Mortality of COVID-19, Influenza, and Respiratory Syncytial Virus,” JAMA Intern Med, vol. 185, no. 3, p. 324, 2025, doi: 10.1001/jamainternmed.2024.7452.
A. Iaruchyk et al., “Genomic Epidemiology of SARS-CoV-2 in Ukraine From May 2022 to March 2024 Reveals Omicron Variant Dynamics,” Viruses, vol. 17, no. 7, p. 1000, 2025, doi: 10.3390/v17071000.
Z. Ju, Y. Chen, Y. Qiang, X. Chen, C. Ju, and J. Yang, “A Systematic Review of Data Augmentation Methods for Intelligent Fault Diagnosis of Rotating Machinery Under Limited Data Conditions,” Meas Sci Technol, vol. 35, no. 12, p. 122004, 2024, doi: 10.1088/1361-6501/ad7a97.
L. J. Liu et al., “BlotDx: A Deep Learning Tool for Western Blot-Based Diagnostics,” 2025, doi: 10.21203/rs.3.rs-6605358/v1.
J. Yang, G. Wang, X. Xiao, M. Bao, and G. Tian, “Explainable Ensemble Learning Method for OCT Detection With Transfer Learning,” PLoS One, vol. 19, no. 3, p. e0296175, 2024, doi: 10.1371/journal.pone.0296175.
P. Singh, R. Khare, K. Sharma, A. Bhargava, and S. S. Negi, “Alpha to JN.1 Variants: SARS-CoV-2 Genomic Analysis Unfolding Its Various Lineages/Sublineages Evolved in Chhattisgarh, India From 2020 to 2024,” World J Virol, vol. 14, no. 2, 2025, doi: 10.5501/wjv.v14.i2.100001.
Y. Chen, D. Luo, and W. Xue, “Deep Learning for Drug–Target Interaction Prediction: A Comprehensive Review,” Chem Biol Drug Des, vol. 106, no. 4, 2025, doi: 10.1111/cbdd.70183.
M. P. Araujo and S. I. Carnovale, “Distribution of Dengue Serotypes in Argentina in the Last 2 Years,” Multidisciplinar (Montevideo), vol. 3, p. 57, 2025, doi: 10.62486/agmu202557.
Y. Kubota, S. Kodera, and A. Hirata, “A Novel Transfer Learning Framework for Non-Uniform Conductivity Estimation With Limited Data in Personalized Brain Stimulation,” Phys Med Biol, vol. 70, no. 10, p. 105002, 2025, doi: 10.1088/1361-6560/add105.
M. Eser, M. Bi̇lgi̇n, E. T. Yasin, and M. Köklü, “Using Pretrained Models in Ensemble Learning for Date Fruits Multiclass Classification,” J Food Sci, vol. 90, no. 3, 2025, doi: 10.1111/1750-3841.70136.
M. Liu, H. Liang, and M. Hou, “Research on Cassava Disease Classification Using the Multi-Scale Fusion Model Based on EfficientNet and Attention Mechanism,” Front Plant Sci, vol. 13, 2022, doi: 10.3389/fpls.2022.1088531.
S. Bozinovski, “Reminder of the First Paper on Transfer Learning in Neural Networks, 1976,” Informatica, vol. 44, no. 3, 2020, doi: 10.31449/inf.v44i3.2828.
N. Sharma et al., “U-Net Model With Transfer Learning Model as a Backbone for Segmentation of Gastrointestinal Tract,” Bioengineering, vol. 10, no. 1, p. 119, 2023, doi: 10.3390/bioengineering10010119.
I. A. Ahmed, E. M. Senan, H. S. A. Shatnawi, Z. M. Alkhraisha, and M. M. A. Al-Azzam, “Hybrid Techniques for the Diagnosis of Acute Lymphoblastic Leukemia Based on Fusion of CNN Features,” Diagnostics, vol. 13, no. 6, p. 1026, 2023, doi: 10.3390/diagnostics13061026.
A. C. Mandal, “Optimizing Deep Learning Based Retinal Diseases Classification on Optical Coherence Tomography Scans,” p. 70, 2023, doi: 10.1117/12.2672249.
M. Tan, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” 2019, doi: 10.48550/arxiv.1905.11946.
M. Harahap, “Skin Cancer Classification Using EfficientNet Architecture,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 4, pp. 2716–2728, 2024, doi: 10.11591/eei.v13i4.7159.
A. Helmut and D. T. Murdiansyah, “Multiclass Email Classification by Using Ensemble Bagging and Ensemble Voting,” Jiko (Jurnal Informatika Dan Komputer), vol. 6, no. 2, 2023, doi: 10.33387/jiko.v6i2.6394.
A. M. A. Siddik, A. M. Abdal, A. Lawi, and E. S. Rusdi, “Ensemble Transfer Learning for Hand-Sign Digit Image Classification,” Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 43, no. 1, pp. 95–111, 2024, doi: 10.37934/araset.43.1.95111.
ErnestMwebaze, J. Mostipak, Joyce, J. Elliott, and S. Dane, “Cassava Leaf Disease Classification,” 2020. [Online]. Available: https://kaggle.com/competitions/cassava-leaf-disease-classification
A. V Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, “Albumentations: Fast and Flexible Image Augmentations,” Information, vol. 11, no. 2, p. 125, 2020, doi: 10.3390/info11020125.
D. Schaudt, “Augmentation Strategies for an Imbalanced Learning Problem on a Novel COVID-19 Severity Dataset,” Sci Rep, vol. 13, no. 1, 2023, doi: 10.1038/s41598-023-45532-2.
M. A. Ottom, H. A. Rahman, and I. D. Dinov, “Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation,” IEEE J Transl Eng Health Med, vol. 10, pp. 1–8, 2022, doi: 10.1109/jtehm.2022.3176737.
E. Hallström, “CombiANT Reader - Deep Learning-Based Automatic Image Processing and Measurement of Distances to Robustly Quantify Antibiotic Interactions,” 2024, doi: 10.1101/2024.10.16.24315598.
V. King, “Use of Artificial Intelligence in the Prediction of Chiari Malformation Type 1 Recurrence After Posterior Fossa Decompressive Surgery,” Cureus, 2024, doi: 10.7759/cureus.60879.
J.-C. Chien, J.-D. Lee, C.-S. Hu, and C. Wu, “The Usefulness of Gradient-Weighted CAM in Assisting Medical Diagnoses,” Applied Sciences, vol. 12, no. 15, p. 7748, 2022, doi: 10.3390/app12157748.
H.-T. Vo, N. N. Thien, and K. C. Mui, “A Deep Transfer Learning Approach for Accurate Dragon Fruit Ripeness Classification and Visual Explanation Using Grad-Cam,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 11, 2023, doi: 10.14569/ijacsa.2023.01411137.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Agus Heri Yunial, Ahmad Fauzi
This work is licensed under a Creative Commons Attribution 4.0 International License.
</a
