Comparative Analysis of UAV and TLS-Derived Crown and Frond Data for Detecting Basal Stem Rot in Oil Palms
DOI:
https://doi.org/10.36877/aafrj.a0000628Abstract
Basal Stem Rot (BSR) disease, caused by Ganoderma boninense, is one of the most destructive diseases affecting oil palm plantations in Southeast Asia. Traditional detection methods are invasive, time-consuming, and often ineffective during the early stages of infection. This study evaluates the effectiveness of Unmanned Aerial Vehicle (UAV) imagery compared with Terrestrial Laser Scanning (TLS) for detecting BSR disease through structural canopy features. Three canopy features: crown area, frond number, and frond angle were extracted from UAV top-view imagery and TLS point-cloud data. Forty oil palm trees were assessed, with ten trees representing each of four disease severity levels: healthy (T0), early infection (T1), moderate infection (T2), and severe infection (T3). Data from both platforms (UAV and TLS) were processed using image segmentation and evaluated using descriptive statistics, correlation analysis (r and R²), Root Mean Square Error (RMSE) and inferential statistics. UAV and TLS measurements showed strong correlations, particularly for frond number (r = 0.993, R² = 0.98) and frond angle (r = 0.999, R² = 0.99 in moderate infection). ANOVA confirmed significant differences among disease severity levels for all canopy features (p < 0.0001). Paired t-tests indicated no significant differences between UAV and TLS for frond number and frond angle in moderate and severe infections, while significant differences occurred in healthy and early-stage palms due to canopy density and occlusion. Crown area remained significantly different across most severity levels, reflecting segmentation limitations in UAV imagery. Overall, the findings demonstrate that UAV imaging is a scalable and cost-effective tool for plantation-wide BSR monitoring, while TLS remains valuable as a high-resolution reference method.
References
Azuan, N. H., Khairunniza-Bejo, S., Abdullah, A. F., et al. (2019). Analysis of changes in oil palm canopy architecture from basal stem rot using terrestrial laser scanner. Plant disease, 103(12), 3218–3225. https://doi.org/10.1094/PDIS-10-18-1721-RE
Haw, Y. H., Lai, K. W., Chuah, J. H., et al. (2023). Classification of basal stem rot using deep learning: a review of digital data collection and palm disease classification methods. PeerJ Computer Science, 9, e1325. https://doi.org/10.7717/peerj-cs.1325
Husin, N. A., Bejo, S. K., Abdullah, A. F., et al. (2021). Relationship of oil palm crown features extracted using terrestrial laser scanning for basal stem rot disease classification. Basrah Journal of Agricultural Sciences, 34, 1–10. https://doi.org/10.37077/25200860.2021.34.sp1.1
Husin, N. A., Khairunniza-Bejo, S., Abdullah, A. F., et al. (2020a). Classification of basal stem rot disease in oil palm plantations using terrestrial laser scanning data and machine learning. Agronomy, 10(11), 1624. https://doi.org/10.3390/agronomy10111624
Husin, N. A., Khairunniza-Bejo, S., Abdullah, A. F., et al. (2020b). Application of ground-based LiDAR for analysing oil palm canopy properties on the occurrence of basal stem rot (BSR) disease. Scientific reports, 10(1), 6464. https://doi.org/s41598-020-62275-6
Husin, N. A., Khairunniza-Bejo, S., Abdullah, A. F., et al. (2022). Multi-temporal analysis of terrestrial laser scanning data to detect basal stem rot in oil palm trees. Precision Agriculture, 23(1), 101–126. https://doi.org/10.1007/s11119-021-09829-4
Husin, N. A., Khairunniza–Bejo, S., Abdullah, A. F., Kassim, M. S. M., & Ahmad, D. (2020c). Study of the oil palm crown characteristics associated with Basal Stem Rot (BSR) disease using stratification method of point cloud data. Computers and Electronics in Agriculture, 178, 105810. https://doi.org/10.1016/j. compag. 2020. 105810
Karunarathna, S. C., Patabendige, N. M., Lu, W., et al. (2024). An in-depth study of phytopathogenic Ganoderma: Pathogenicity, advanced detection techniques, control strategies, and sustainable management. Journal of Fungi, 10(6), 414. https://doi.org/10.3390/jof10060414
Kent, O. W., Chun, T. W., Choo, T. L., et al. (2023). Early symptom detection of basal stem rot disease in oil palm trees using a deep learning approach on UAV images. Computers and Electronics in Agriculture, 213, 108192. https://doi.org/10.1016/j.compag.2023.108192
Kurihara, J., Koo, V. C., Guey, C. W., et al. (2022). Early detection of basal stem rot disease in oil palm tree using unmanned aerial vehicle-based hyperspectral imaging. Remote Sensing, 14(3), 799. https://doi.org/10.3390/rs14030799
Liu, X., Ghazali, K. H., Han, F., et al. (2021). Automatic detection of oil palm tree from UAV images based on the deep learning method. Applied Artificial Intelligence, 35(1), 13–24. https://doi.org/10.1080/08839514.2020.1831226
Moura, A. B., Backhouse, D., de Souza Júnior, I. T., et al. (2022). Soilborne pathogens. In Subsoil constraints for crop production (pp. 199–224). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-031-00317-2_9
Siddiqui, Y., Surendran, A., Paterson, R.R.M., et al. (2021). Current strategies and perspectives in detection and control of basal stem rot of oil palm. Saudi Journal of Biological Sciences. 28, 2840–2849. https://doi.org/10.1016/j.sjbs.2021.02.016
Yarak, K., Witayangkurn, A., Kritiyutanont, K., et al. (2021). Oil palm tree detection and health classification on high-resolution imagery using deep learning. Agriculture, 11(2), 183. https://doi.org/10.3390/agriculture11020183
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nur Azuan Husin, Nurul Izzah Zainal Abidin, Siti Khairunniza-Bejo
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Author(s) shall retain the copyright of their work and grant the Journal/Publisher right for the first publication with the work simultaneously licensed under:
Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This license allows for the copying, distribution and transmission of the work, provided the correct attribution of the original creator is stated. Adaptation and remixing are also permitted.
This broad license intends to facilitate free access to, as well as the unrestricted reuse of, original works of all types for non-commercial purposes.
The author(s) permits HH Publisher to publish this article that has not been submitted elsewhere.
.png){kind=logo}
.jpg)
