Hybrid Machine Learning Approach for Nutrient Deficiency Detection in Lettuce
DOI:
https://doi.org/10.38043/tiers.v6i2.7143Keywords:
Digital Image Analysis, Nutrient Deficiency, Optuna, SMOTE, SVMAbstract
Early detection of nutrient deficiencies in lettuce is essential for precision agriculture. However, this task remains challenging due to limited data availability and class imbalance, which reduce model sensitivity toward minority classes and hinder generalization. This study introduces a hybrid machine learning approach integrating SMOTE, Optuna, and SVM to enhance the accuracy of nutrient deficiency classification using digital leaf image analysis. The dataset, obtained from Kaggle, includes four categories: Nitrogen Deficiency (-N), Phosphorus Deficiency (-P), Potassium Deficiency (-K), and Fully Nutritional (FN). Image features were extracted using MobileNetV2 pretrained on ImageNet and classified with a Support Vector Machine. Three scenarios were tested: (1) SVM before SMOTE, (2) SVM after SMOTE, and (3) Optuna-SVM after SMOTE, evaluated using accuracy, precision, recall, and f1-score. The hybrid model achieved the best performance with accuracy 0.929, precision 0.946, recall 0.835, and f1-score 0.869, outperforming the other scenarios. This hybrid framework effectively addressed class imbalance and improved classification margin stability through adaptive hyperparameter tuning using the Tree Structured Parzen Estimator within Optuna. The novelty of this study lies in combining MobileNetV2 based feature extraction with SMOTE and Optuna-SVM for small agricultural datasets. The proposed approach offers an efficient, accurate, and practical solution for automated nutrient deficiency diagnosis and contributes to the development of AI-driven smart agriculture systems.
Downloads
References
S. Eshkabilov, J. Stenger, E. N. Knutson, E. Kktopcu, H. Simsek, and C. W. Lee, Hyperspectral Image Data and Waveband Indexing Methods to Estimate Nutrient Concentration on Lettuce (Lactuca sativa L.) Cultivars, Sensors, vol. 22, no. 21, 2022, doi: 10.3390/s22218158.
A. A. Saleema, P. Raajan, and K. S. Priya, Intelligent Systems And Application In Adaptive SVM with Bio-inspired Optimization Tuning for Guava Leaf Disease Prediction, IJISAE, vol. 12, no. 4, pp. 58135819, 2024.
A. Adianggiali, I. D. Irawati, S. Hadiyoso, and R. Latip, Classification of Nutrient Deficiencies Based on Leaf Image in Hydroponic Lettuce using MobileNet Architecture, ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 11, no. 4, p. 958, 2023, doi: 10.26760/elkomika.v11i4.958.
J. Sikati and J. C. Nouaze, YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano , Engineering Proceedings, vol. 58, no. 1, 2023, doi: 10.3390/ecsa-10-16256.
X. Zhu, N. Li, and Y. Pan, Optimization performance comparison of three different group intelligence algorithms on a SVM for hyperspectral imagery classification, Remote Sensing, vol. 11, no. 6, 2019, doi: 10.3390/RS11060734.
P. Thanh Noi and M. Kappas, Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery, Sensors (Basel, Switzerland), vol. 18, no. 1, 2017, doi: 10.3390/s18010018.
M. Sheykhmousa, M. Mahdianpari, and H. Ghanbari, Support Vector Machine vs . Random Forest for Remote Sensing Image Classification: A Meta-analysis and systematic review, IEEE Explore, 2021.
A. E. Maxwell, T. A. Warner, and F. Fang, Implementation of machine-learning classification in remote sensing: An applied review, International Journal of Remote Sensing, vol. 39, no. 9, pp. 27842817, 2018, doi: 10.1080/01431161.2018.1433343.
S. Jayanthi, M. A. J. Sathya, B. Nathan, and K. Karmokanda, Ensemble Learning Framework for Crop Yield Prediction with Optuna Hyperparameter Tuning, Journal of Information Systems Engineering and Management, vol. 10, no. 27s, pp. 783795, 2025, doi: 10.52783/jisem.v10i27s.4553.
Y. Wang, Q. Wang, Y. Su, B. Jing, and M. Feng, Detection of kidney bean leaf spot disease based on a hybrid deep learning model, Scientific Reports, vol. 15, no. 1, pp. 122, 2025, doi: 10.1038/s41598-025-93742-7.
Y. Efendi, Machine Learning-Based Classification of Student Adaptability in Online Learning with Feature Engineering, Journal TIERS, vol. 6, no. 1, pp. 129143, 2025.
T. Miftahushudur, H. M. Sahin, B. Grieve, and H. Yin, A Survey of Methods for Addressing Imbalance Data Problems in Agriculture Applications, Remote Sensing, vol. 17, no. 3, pp. 131, 2025, doi: 10.3390/rs17030454.
C. Cuenca-Romero, O. E. Apolo-Apolo, J. N. Rodrguez Vzquez, G. Egea, and M. Prez-Ruiz, Tackling unbalanced datasets for yellow and brown rust detection in wheat, Frontiers in Plant Science, vol. 15, no. May, pp. 111, 2024, doi: 10.3389/fpls.2024.1392409.
D. L. Weller, T. M. T. Love, and M. Wiedmann, Comparison of Resampling Algorithms to Address Class Imbalance when Developing Machine Learning Models to Predict Foodborne Pathogen Presence in Agricultural Water, Frontiers in Environmental Science, vol. 9, no. June, pp. 115, 2021, doi: 10.3389/fenvs.2021.701288.
F. Bal and F. Kayaalp, Performance Comparison of Smote-Based Machine Learning Models on Unbalanced Datasets: a Study on Date and Pistachio Fruits, stanbul Ticaret niversitesi Fen Bilimleri Dergisi, vol. 24, no. 47, pp. 176200, 2025, doi: 10.55071/ticaretfbd.1597150.
E. F. Swana, W. Doorsamy, and P. Bokoro, Tomek Link and SMOTE Approaches for Machine Fault Classification with an Imbalanced Dataset, Sensors, vol. 22, no. 9, 2022, doi: 10.3390/s22093246.
D. Gyoten, M. Ohkubo, and Y. Nagata, Imbalanced data classification procedure based on SMOTE, Total Quality Science, vol. 5, no. 2, pp. 6471, 2020, doi: 10.17929/tqs.5.64.
S. F. Taskiran, B. Turkoglu, E. Kaya, and T. Asuroglu, A comprehensive evaluation of oversampling techniques for enhancing text classification performance, Scientific Reports, vol. 15, no. 1, pp. 120, 2025, doi: 10.1038/s41598-025-05791-7.
S. Ghazal, N. Kommineni, and A. Munir, Comparative Analysis of Machine Learning Techniques Using RGB Imaging for Nitrogen Stress Detection in Maize, MDPI, pp. 12861300, 2024.
A. Bera, D. Bhattacharjee, and O. Krejcar, OPEN PND Net: plant nutrition deficiency and disease classification using graph convolutional network, Scientific Reports, pp. 117, 2024, doi: 10.1038/s41598-024-66543-7.
Ramimalik782, Lettuce NPK dataset, 2022. [Online]. Available: https://www.kaggle.com/datasets/baronn/lettuce-npk-dataset
C. Shorten and T. M. Khoshgoftaar, A survey on Image Data Augmentation for Deep Learning, Journal of Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0197-0.
S. R. Yang, H. C. Yang, F. R. Shen, and J. Zhao, Image Data Augmentation for Deep Learning: A Survey, Ruan Jian Xue Bao/Journal of Software, vol. 36, no. 3, pp. 13901412, 2025, doi: 10.13328/j.cnki.jos.007263.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, MobileNetV2: Inverted Residuals and Linear Bottlenecks, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 45104520, 2018, doi: 10.1109/CVPR.2018.00474.
P. Yan et al., A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions, IEEE Access, vol. 12, pp. 37683789, 2024, doi: 10.1109/ACCESS.2023.3349132.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, SMOTE: Synthetic Minority Over-sampling Technique, Journal of Artificial Intelligence Research, vol. 16, pp. 321357, 2002, doi: 10.1613/jair.953.
C. Miller, T. Portlock, D. M. Nyaga, and J. M. OSullivan, A review of model evaluation metrics for machine learning in genetics and genomics, Frontiers in Bioinformatics, vol. 4, no. 9, pp. 113, 2024, doi: 10.3389/fbinf.2024.1457619.
F. S. Nahm, ROC Curve: overview and practical use for clinicians, Korean Journal of Anesthesiology, vol. 75, no. 1, pp. 2536, 2022, doi: doi: 10.4097/kja.21209.
J. T. Hancock, T. M. Khoshgoftaar, and J. M. Johnson, Evaluating classifier performance with highly imbalanced Big Data, Journal of Big Data, vol. 10, no. 1, 2023, doi: 10.1186/s40537-023-00724-5.
A. C. J. W. Janssens and F. K. Martens, Reflection on modern methods: Revisiting the area under the ROC Curve, International Journal of Epidemiology, vol. 49, no. 4, pp. 13971403, 2020, doi: 10.1093/ije/dyz274.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Zuriati, Dewi Kania Widyawati, Oki Arifin, Kurniawan Saputra, Sriyanto Sriyanto, Asmala Ahmad
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
