Skip to main content
Article | Green Intelligent Systems and Applications | Volume 6 - Issue 1 - 2026 | 81−95 | https://doi.org/10.53623/gisa.v6i1.1063
© 2026 by the author(s), and is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License Creative Commons Attribution 4.0 International (CC BY 4.0) License

Potato Leaf Disease Classification Using MobileNetV3 Architecture With Adam and Stochastic Gradient Descent Optimizers

Author(s): Hafizh Pebrian , Ery Hartati
Author(s) information:
Faculty of Computer Science and Engineering, Universitas Multi Data Palembang, South Sumatra, Indonesia

Corresponding author

Green Intelligent Systems and Applications

Volume 6 - Issue 1 - 2026

 About the journal
Submit your article

Potato leaf diseases such as Early Blight and Late Blight reduced productivity and could cause crop failure if they were not detected early. This study analyzed the comparative performance of the Adam and Stochastic Gradient Descent (SGD) optimizers using the MobileNetV3-Large architecture for potato leaf disease classification. The dataset consisted of three categories: healthy leaves, Early Blight, and Late Blight, with a total of 4,072 images. All images were processed through preprocessing stages, including resizing to 224 × 224 pixels and pixel value normalization. The data were divided into training, validation, and testing sets with a ratio of 70:20:10. Random undersampling and data augmentation techniques were applied to the training data to address class imbalance and improve the model’s generalization capability. The model training process was conducted using a transfer learning approach with the MobileNetV3-Large architecture through two stages: feature extraction and fine-tuning. Model performance evaluation was based on accuracy, precision, recall, and F1-score metrics. The results showed that the Adam optimizer achieved a test accuracy of 98.75% with an F1-score of 0.9875, while the SGD optimizer achieved a test accuracy of 96.56% with an F1-score of 0.9635. The Adam optimizer also demonstrated faster and more stable convergence during the training process. This study was expected to serve as a reference for determining an appropriate optimizer for deep learning applications in image classification, particularly in plant disease detection.

Read Full-Text
Previous article
Next article

Majeed, A.; Siyar, S.; Sami, S. (2022). Late blight of potato: From the great Irish potato famine to the genomic era—An overview. Hellenic Plant Protection Journal, 15(1), 1–9. https://doi.org/10.2478/hppj-2022-0001.

Wolters, P. J.; Wouters, D.; Kromhout, E. J.; Huigen, D. J.; Visser, R. G. F.; Vleeshouwers, V. G. A. A. (2021). Qualitative and quantitative resistance against early blight introgressed in potato. Biology, 10(9). https://doi.org/10.3390/biology10090892.

Talab, H. K.; Mohammadzamani, D. (2025). Diagnosis and classification of two common potato leaf diseases (Early Blight and Late Blight) using image processing and machine learning. 15(1).

Tiwari, S.; Srivastava, A. (2024). Farmers’ knowledge and perception of late blight of potato and its management strategies in Kailali and Banke districts of Nepal. Plant Pathology & Quarantine, 14(1), 1–9. https://doi.org/10.5943/ppq/14/1/1.

Hasan, M. (2024). Identifikasi penyakit daun kentang menggunakan fitur GLCM dan algoritma Multi-SVM [Identification of potato leaf disease using GLCM features and Multi-SVM algorithm]. CONTEN: Computer and Network Technology, 4(1), 52–57. https://doi.org/10.31294/conten.v4i1.3465.

Amrulloh, I. T. A.; Sari, B. N.; Padilah, T. N. (2024). Evaluasi augmentasi data pada deteksi penyakit daun tebu dengan YOLOv8 [Evaluation of data augmentation in sugarcane leaf disease detection using YOLOv8]. JATI (Jurnal Mahasiswa Teknik Informatika), 8(4), 7547–7552. https://doi.org/10.36040/jati.v8i4.10267.

Fuadi, A.; Suharso, A. (2022). Perbandingan arsitektur MobileNet dan NASNetMobile untuk klasifikasi penyakit pada citra daun kentang [Comparison of MobileNet and NASNetMobile architectures for disease classification on potato leaf images]. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), 7(3), 701–710. https://doi.org/10.29100/jipi.v7i3.3026.

Chen, L.; Wei, J.; Wang, G.; Yang, X.; Qin, L. (2025). MobileNetV3–Transformer-Based Prediction of Highway Accident Severity. Applied Sciences. 2025; 15(23), 12694. https://doi.org/10.3390/app152312694 .

Fitriansyah, M. F.; Siregar, G. M. A. (2025). Optimasi menggunakan algoritma stochastic gradient descent (SGD): Studi bibliometrik [Optimization using stochastic gradient descent (SGD) algorithm: A bibliometric study]. Indexia, 7(1), 53–68. https://doi.org/10.30587/indexia.v7i1.9708.

Herwina, H.; Darmatasia, D.; Shiddiq, A. K. A.; Syahputra, T. D. (2022). Deteksi penyakit pada tanaman padi menggunakan MobileNet transfer learning berbasis Android [Disease detection in rice plants using Android-based MobileNet transfer learning]. Jagti, 2(2), 1–8. https://doi.org/10.24252/jagti.v2i2.41.

Maximilliano, W.; Rachmat, N. (2025). Comparative analysis of MobileNetV3-Large and Small for corn leaf disease classification. Brilliance: Research of Artificial Intelligence, 5(1), 325–332. https://doi.org/10.47709/brilliance.v5i1.6259.

Alhammad, S. M.; Khafaga, D. S. (2025). Deep learning and explainable AI for classification of potato leaf diseases. Frontiers in Artificial Intelligence. https://doi.org/10.3389/frai.2024.1449329.

Radwan, M.; Ali, A.; Abdelhameed, A. (2025). Potato leaf disease classification using optimized machine learning. Potato Research, 68(2), 897–921. https://doi.org/10.1007/s11540-024-09763-8.

Chang, C.-Y.; Lai, C.-C. (2024). Potato Leaf Disease Detection Based on a Lightweight Deep Learning Model. Machine Learning and Knowledge Extraction, 6(4), 2321–2335. https://doi.org/10.3390/make6040114.

Sinamenye, J. H.; Chatterjee, A.; Shrestha, R. (2025). Potato plant disease detection: Leveraging hybrid deep learning models. BMC Plant Biology. https://doi.org/10.1186/s12870-025-06679-4.

Simangunsong, J.; Simanjuntak, N. D.; Matondang, A. A. (2025). Penerapan transfer learning untuk klasifikasi citra bunga berbasis convolutional neural network [Application of transfer learning for flower image classification based on convolutional neural network]. Jurnal Minfo Polgan, 14(1), 1062–1067. https://doi.org/10.33395/jmp.v14i1.14980.

Taye, M. M. (2023). Understanding of machine learning with deep learning: Architectures, workflow, applications and future directions. Computers, 12(5), 91. https://doi.org/10.3390/computers12050091.

Yuliany, S.; Aradea; Rachman, A. N. (2022). Implementasi deep learning pada sistem klasifikasi hama tanaman padi menggunakan metode convolutional neural network (CNN) [Implementation of deep learning in rice plant pest classification system using convolutional neural network (CNN)]. Jurnal Buana Informatika, 13(1), 54–65. https://doi.org/10.24002/jbi.v13i1.5022.

Zhao, L.; Wang, L. (2022). A new lightweight network based on MobileNetV3. Transactions on Internet and Information Systems, 16(1), 1–15. https://doi.org/10.3837/tiis.2022.01.001.

Asy Syifa, S.; Amelia Dewi, I. (2022). Arsitektur ResNet-152 dengan perbandingan optimizer Adam dan RMSProp untuk mendeteksi penyakit paru-paru [ResNet-152 architecture with comparison of Adam and RMSProp optimizers for lung disease detection]. Journal MIND, 7(2), 139–150. https://doi.org/10.26760/mindjournal.v7i2.139-150.

Haqqi, M. S.; Kusumoputro, B. (2022). Komparasi metode optimasi Adam dan SGD dalam skema direct inverse control untuk sistem kendali data sikap dan ketinggian quadcopter [Comparison of Adam and SGD optimization methods in direct inverse control scheme for quadcopter attitude and altitude control system]. ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, dan Teknik Elektronika, 10(2), 458. https://doi.org/10.26760/elkomika.v10i2.458.

Utomo, P. B.; Faruqziddan, M.; Aulia, E. H. S.; Azzahra, S. D. (2024). Perbandingan skenario balancing oversampling dan undersampling dalam klasifikasi risiko kambuh kanker tiroid menggunakan algoritma SVM linear [Comparison of oversampling and undersampling balancing scenarios in thyroid cancer recurrence risk classification using linear SVM algorithm]. JAMI: Jurnal Ahli Muda Indonesia, 5(2), 172–182. https://doi.org/10.46510/jami.v5i2.320.

Read Full-Text
About this article

SUBMITTED: 20 February 2026
ACCEPTED: 15 March 2026
PUBLISHED: 18 March 2026
SUBMITTED to ACCEPTED: 23 days
DOI: https://doi.org/10.53623/gisa.v6i1.1063

Cite this article
Pebrian, H., & Hartati, E. . (2026). Potato Leaf Disease Classification Using MobileNetV3 Architecture With Adam and Stochastic Gradient Descent Optimizers. Green Intelligent Systems and Applications, 6(1), 81−95. https://doi.org/10.53623/gisa.v6i1.1063
Citations
0
Share this article