Using Machine Learning in Detecting Ganoderma Disease in Oil Palm Plants


  • Mardiana Wahyuni Doctoral Program in Agricultural Sciences, Faculty of Agriculture, Universitas Sumatera Utara, Medan 20155 Indonesia
  • T. Sabrina Agrotechnology Study Program, Faculty of Agriculture, Universitas Sumatera Utara, Medan 20155 Indonesia
  • Mukhlis Agrotechnology Study Program, Faculty of Agriculture, Universitas Sumatera Utara, Medan 20155 Indonesia
  • Heri Santoso Indonesia Oil Palm Research Institute, Medan 20178 Indonesia


Ganoderma, UAV, reflectance, vegetation indices, Random Forest algorithm, Support Vector Machine algorithm


Ganoderma disease is asymptomatic, posing challenges in detection and identification. The utilization of Remote Sensing techniques is expected to provide rapid, accurate, and large-scale detection information. This study aims to identify and classify oil palm plant images recorded by a UAV, analyze digital vegetation indices, and apply RF and SVM algorithms. The UAV equipped with sensors capturing three bands: R, G, NIR. Data processing was conducted using software such as Mission Planner, Agisoft MetaShape, Mapir Camera Control, ArcGIS 10.5, Envi 5.3, and R Studio. The study locations were at Pabatu. Image recording took place on July 3, 2021. The observed parameters included disease incidence, reflectance values, vegetation indices (NDVI, GNDVI, SAVI, SR, CIgreen), with plant classes categorized as Healthy (H) and Infected (I). Infected plants exhibited lower reflectance compared to healthy plants. All vegetation indices, including NDVI, GNDVI, SAVi, SR, and CIgreen, were lower in infected plants compared to healthy plants. The SVM algorithm demonstrated the highest accuracy of 93.55% compared to RF only 84.42%. With Machine Learning algorithm, disease occurrences where imagery has been recorded can be predicted. This map can serve as fundamental information for control strategies, production calculations, and other cultivation activities.


Download data is not yet available.


Direktorat Jendral Perkebunan. 2020. Statistik Perkebunan Kelapa Sawit Indonesia. Direktorat Jendral Perkebunan Jakarta.

J. Flood, L. Keenan, S. Wayne, and Y. Hasan, “Studies on oil palm trunks as sources of infection in the field,” Mycopathologia, vol. 159, no. 1, pp. 101–107, 2005, doi: 10.1007/s11046-004-4430-8.

M. S. Arif, A. Roslan, A. S. Idris, and M. Ramle, “Economics of oil palm pests and Ganoderma disease and yield losses,” in Proceedings of the Third MPOB-IOPRI International Seminar: Integrated Oil Palm Pests and Diseases Management, Kuala Lumpur Convention Centre Kuala Lumpur, 2011.

R. Hushiarian, N. A. Yusof, and S. W. Dutse, “Detection and control of Ganoderma boninense: Strategies and perspectives,” Springerplus, vol. 2, no. 1, pp. 1–12, 2013, doi: 10.1186/2193-1801-2-555.

R. R. M. Paterson, “Ganoderma disease of oil palm—A white rot perspective necessary for integrated control,” Crop Protection, vol. 26, no. 9, pp. 1369–1376, Sep. 2007, doi: 10.1016/j.cropro.2006.11.009.

R. H. V Corley and P. B. H. Tinker, The oil palm. John Wiley & Sons, 2008.

C. C. Lelong et al., “Evaluation of Oil-Palm Fungal Disease Infestation with Canopy Hyperspectral Reflectance Data,” Sensors, vol. 10, no. 1, pp. 734–747, Jan. 2010, doi: 10.3390/s100100734.

T. M. Azahar, P. Boursier, and I. A. Seman, “Spatial analysis of basal stem rot disease using geographical information system,” Map Asia, vol. 1820, 2008.

L. Breiman, “Random forests,” Mach Learn, vol. 45, pp. 5–32, 2001.

T. O. Ayodele, “Types of Machine Learning Algorithms,” New Advances in Machine Learning, 2010.

S. Liaghat et al., “Early detection of basal stem rot disease (Ganoderma) in oil palms based on hyperspectral reflectance data using pattern recognition algorithms,” Int J Remote Sens, vol. 35, no. 10, pp. 3427–3439, 2014.

H. Santoso, H. Tani, X. Wang, A. E. Prasetyo, and R. Sonobe, “Classifying the severity of basal stem rot disease in oil palm plantations using WorldView-3 imagery and machine learning algorithms,” Int J Remote Sens, vol. 40, no. 19, pp. 7624–7646, 2019.

H. Santoso, “Pengamatan dan Pemetaan Penyakit Busuk Pangkal Batang di Perkebunan Kelapa Sawit Menggunakan Unmanned Aerial Vehicle (UAV) dan Kamera Multispektral,” Jurnal Fitopatologi Indonesia, vol. 16, no. 2, pp. 69–80, Dec. 2020, doi: 10.14692/jfi.16.2.69-80.

PPKS, “Laporan Rekomendasi Pemupukan Tanaman Kelapa Sawit Kebun Tinjowan PT. Perkebunan Nusantara IV pada tahun 2018,” 2018.

K. Utami, S. Supriadi, and K. S. Lubis, “Evaluasi Sifat Fisik Tanah Terhadap Laju Infeksi Ganoderma di Perkebunan Kelapa Sawit (Studi Kasus: PT. PD. PATI),” Jurnal Agroekoteknologi Universitas Sumatera Utara, vol. 4, no. 3, p. 108266, 2016.

J. L. Hatfield, A. A. Gitelson, J. S. Schepers, and C. L. Walthall, “Application of Spectral Remote Sensing for Agronomic Decisions,” Agron J, vol. 100, no. S3, May 2008, doi: 10.2134/agronj2006.0370c.

A. Susanto, P. S. Sudharto, and R. Y. Purba, “Enhancing biological control of basal stem rot disease (Ganoderma boninense) in oil palm plantations,” Mycopathologia, vol. 159, no. 1, pp. 153–157, Jan. 2005, doi: 10.1007/s11046-004-4438-0.

B. H. Prasetyo and danD A. Suriadikarta, “Karakteristik, potensi, dan teknologi pengelolaan tanah ultisol untuk pengembangan pertanian lahan kering di Indonesia,” Jurnal Litbang Pertanian, vol. 25, no. 2, pp. 39–46, 2006.

H. Z. M. Shafri and N. Hamdan, “Hyperspectral imagery for mapping disease infection in oil palm plantation using vegetation indices and red edge techniques,” Am J Appl Sci, vol. 6, no. 6, 2009, doi: 10.3844/ajassp.2009.1031.1035.

H. Santoso, H. Tani, and X. Wang, “Random Forest classification model of basal stem rot disease caused by Ganoderma boninense in oil palm plantations,” Int J Remote Sens, vol. 38, no. 16, pp. 4683–4699, Aug. 2017, doi: 10.1080/01431161.2017.1331474.

V. Martínez-Martínez, J. Gomez-Gil, M. L. Machado, and F. A. C. Pinto, “Leaf and canopy reflectance spectrometry applied to the estimation of angular leaf spot disease severity of common bean crops,” PLoS One, vol. 13, no. 4, p. e0196072, 2018.

N. S. Lang, L. Mills, R. L. Wample, J. Silbernagel, E. M. Perry, and R. Smithyman, “Remote image and leaf reflectance analysis to evaluate the impact of environmental stress on grape canopy metabolism,” Horttechnology, vol. 10, no. 3, pp. 468–474, 2000.

R. SHOFIYATI1, K. HONDA, N. T. S. WIJESEKERA, and WIDAGDO, “Pemantauan Kekeringan Lahan Pertanian Menggunakan Teknologi Remote Sensing dan SIG di DAS Brantas Hulu,” Jurnal Tanah dan Iklim, no. 20, pp. 24–34, 2002.

W. Li et al., “Outlier detection and removal improves accuracy of machine learning approach to multispectral burn diagnostic imaging,” J Biomed Opt, vol. 20, no. 12, p. 121305, 2015.

Y. L. Pavlov, “Random forests,” Random Forests, pp. 1–122, 2019, doi: 10.1201/9780367816377-11.

A. Susanto, A. Prasetyo, and S. Wening, “Laju Infeksi Ganoderma pada Empat Kelas Tekstur Tanah,” Jurnal Fitopatologi Indonesia, vol. 9, no. 2, pp. 39–46, Apr. 2013, doi: 10.14692/jfi.9.2.39.

A. E. Prasetyo, A. Susanto, and C. Utomo, “Metode penghindaran penyakit busuk pangkal batang kelapa sawit (Ganoderma boninense) dengan sistem lubang tanam besar,” Jurnal Penelitian Kelapa Sawit16, vol. 2, pp. 77–86, 2008.




How to Cite

Wahyuni, M. ., Sabrina, T. ., Mukhlis, M., & Santoso, H. . (2024). Using Machine Learning in Detecting Ganoderma Disease in Oil Palm Plants. International Journal of Intelligent Systems and Applications in Engineering, 12(16s), 145–155. Retrieved from



Research Article