UAV Image Classification of Oil Palm Plants Using CNN Ensemble Model
DOI:
https://doi.org/10.30871/jaic.v9i4.9437Keywords:
Oil Palm, UAV, Basal Stem Rot, CNN, Ensemble LearningAbstract
Basal Stem Rot (BSR), caused by Ganoderma boninense, is one of the most destructive diseases affecting oil palm plantations in Southeast Asia. Early detection of this disease is crucial to prevent its widespread transmission and to maintain plantation productivity. This study proposes an image classification approach using ensemble learning with three Convolutional Neural Network (CNN) architectures: DenseNet161, ResNet152, and VGG19, to detect BSR-infected oil palm trees through aerial imagery captured by Unmanned Aerial Vehicles (UAVs). The dataset used consists of 7,348 annotated images classified into two categories: healthy and unhealthy. Experimental results show that the DenseNet161 model outperformed the others, achieving a validation accuracy of 91.75% and a validation loss of 0.0307. The ensemble CNN approach demonstrated improved classification accuracy and holds significant potential for implementation in automated and precise plant health monitoring systems. This research provides a valuable contribution to AI-based agricultural technology, particularly in disease management for oil palm plantations.
Downloads
References
[1] R. H. V Corley and P. B. Tinker, “The Oil Palm, Fourth Edition,” 2003.
[2] Y. Siddiqui, A. Surendran, R. R. M. Paterson, A. Ali, and K. Ahmad, “Current strategies and perspectives in detection and control of basal stem rot of oil palm,” May 01, 2021, Elsevier B.V. doi: 10.1016/j.sjbs.2021.02.016.
[3] Y. Xu et al., “Author Correction: Recent expansion of oil palm plantations into carbon-rich forests (Nature Sustainability, (2022), 10.1038/s41893-022- 00872-1),” May 01, 2022, Nature Research. doi: 10.1038/s41893-022-00897-6.
[4] N. A. Jazuli et al., “A Review of Factors Affecting Ganoderma Basal Stem Rot Disease Progress in Oil Palm,” Oct. 01, 2022, MDPI. doi: 10.3390/plants11192462.
[5] O. Win Kent, T. Weng Chun, T. Lee Choo, and L. Weng Kin, “Early symptom detection of basal stem rot disease in oil palm trees using a deep learning approach on UAV images,” Comput Electron Agric, vol. 213, Oct. 2023, doi:10.1016/j.compag.2023.108192.
[6] M. L. Lo et al., “Comparison of Ganoderma boninense Isolate’s Aggressiveness Using Infected Oil Palm Seedlings,” Journal of Microbiology, vol. 61, no. 4, pp. 449–459, Apr. 2023, doi:10.1007/s12275-023-00040-w.
[7] N. H. Darlan, H. Hasan Siregar, E. Listia, and E. S. Sutarta, “Recent Evaluation of Rising Temperature and Oil Palm Extension to Higher Elevation in North Sumatra Evaluasi Terkini Kenaikan Suhu dan Perluasan Tanaman Kelapa Sawit ke Dataran Tinggi di Sumatera Utara,” 2009.
[8] J. Zheng, W. Li, M. Xia, R. Dong, H. Fu, and S. Yuan, Large-Scale Oil Palm Tree Detection From High-Resolution Remote Sensing Images Using Faster-RCNN. 2019 IEEE International Geoscience & Remote Sensing Symposium : proceedings : July 28-August 2, 2019, Yokohama, Japan, 2019.
[9] I. Bonet, F. Caraffini, A. Pena, A. Puerta, and M. Gongora, Oil Palm Detection via Deep Transfer Learning. 2020 IEEE Congress on Evolutionary Computation (CEC), 2020.
[10] J. Zheng et al., “Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network,” 2020.
[11] R. Malinee, D. Stratoulias, and N. Nuthammachot, “Detection of oil palm disease in plantations in krabi province, thailand with high spatial resolution satellite imagery,” Agriculture (Switzerland), vol. 11, no. 3, Mar. 2021, doi: 10.3390/agriculture11030251.
[12] L. I. Kuncheva and J. J. Rodríguez, “A weighted voting framework for classifiers ensembles,” Knowl Inf Syst, vol. 38, no. 2, pp. 259–275, Feb. 2014, doi: 10.1007/s10115-012-0586-6.
[13] M. Lestandy, A. Abdurrahim, A. Faruq, M. Irfan, and N. Setyawan, “Ensembled Machine Learning Methods and Feature Extraction Approaches for Suicide-Related Social Media,” Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), vol. 13, no. 2, pp. 192–203, Jul. 2024, doi: 10.23887/janapati.v13i2.70016.
[14] A. Faruq, S. S. Abdullah, A. Marto, C. M. Che Razali, and S. F. Mohd Hussein, “Flood Forecasting using Committee Machine with Intelligent Systems: A Framework for Advanced Machine Learning Approach,” in IOP Conference Series: Earth and Environmental Science, Institute of Physics Publishing, Jul. 2020. doi: 10.1088/1755- 1315/479/1/012039.
[15] B. Fu et al., “Comparison of RFE-DL and stacking ensemble learning algorithms for classifying mangrove species on UAV multispectral images,” International Journal of Applied Earth Observation and Geoinformation, vol. 112, Aug. 2022, doi: 10.1016/j.jag.2022.102890.
[16] I. Lizarazo, J. L. Rodriguez, O. Cristancho, F. Olaya,
M. Duarte, and F. Prieto, “Identification of symptoms related to potato Verticillium wilt from UAV-based multispectral imagery using an ensemble of gradient boosting machines,” Smart Agricultural Technology, vol. 3, Feb. 2023, doi: 10.1016/j.atech.2022.100138.
[17] A. M．P． and P. Reddy, “Ensemble of CNN models
for classification of groundnut plant leaf disease
detection,” Smart Agricultural Technology, vol. 6, Dec. 2023, doi: 10.1016/j.atech.2023.100362
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Merinda Lestandy, Adhi Nugraha
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
