Main Article Content

Abstract

Basal Stem Rot (BSR) is a fatal disease caused by the fungus Ganoderma boninense. Currently in Indonesia the identification of oil palm plants suffering from BSR is done by directly observing oil palm plants one by one and pressing the palm tree trunks. However the direct checking method is felt to be less effective and efficient, its need another better method for detecting BSR. This study aims to evaluate the Ganoderma attack by using a multispectral camera, applying a neural network method to analyze NDVI images, and analyzing the effect of altitude on the accuracy of multispectral camera performance. In this study, spectral data of oil palm plants were taken through the air at an altitude of 50 m, 60 m, and 70 m with a multispectral camera mounted on a UAV, then the spectral data were analyzed using artificial neural networks to identify oil palm plants that were attacked by Ganoderma and healthy plants. The results of this study conclude that multispectral cameras can identify oil palm plants that have been attacked by Ganoderma at an altitude of 50 m and 60 m with utilization of artificial neural networks.

Keywords

Ganoderma basal stem rot multispectral camera UAV oil palm plantations

Article Details

References

  1. Arifin D, Idris A S, Singh G. 2000. Status of Ganoderma in oil palm. Di dalam: Flood J,Bridge PD, Holderners M. (Editor), Ganoderma Disease ofPerenial Crops. CABI Publishing, Wallingford, UK. hlm 49-68.
  2. [BPS] Badan Pusat Statistik Indonesia. 2018. Analisa Komoditi Ekspor. Jakarta (ID) : BPS Indonesia.
  3. Chipman JW, Kiefer RW, Lillesand TM. 2011. Remote Sensing and ImageInterpretation 6th ed. New York (USA) : Willey.
  4. Kasih LSB. 2012. Penentuan iluminansi dan ketinggian terbang pesawat yang optimum untuk pemetaan tingkat warna daun padi [skripsi]. Bogor (ID) :Institut Pertanian Bogor
  5. Liaghat S, Ehsani R, Mansor S, Shafri H. 2014. Early detection of basal stem rotdisease (Ganoderma) in oil palms based on hyperspectral reflectance data using pattern recognition algorithms. International Journal of Remote Sensing, 35:10, 3427-3439.
  6. Martawijaya A, Kartasujana I, Kadir K, Mandang Y, Prawira S. 2005. Atlas KayuIndonesia Jilid I. Bogor. Badan Penelitian dan Pengembangan Kehutanan.Paterson RRM .2007. Ganoderma disease of oil palm: A white rot perspective necessary for integrated control. Crop Protect 26: 1369-1376
  7. Semangun H. 2000. Penyakit-Penyakit Tanaman Perkebunan di Indonesia. Gadjah Mada University Press. Yogyakarta. 150-161.
  8. Shafri H, Anuar M, Seman I, Noor N. 2011. Spectral discrimination of healthy andGanoderma infected oil palms from hyperspectral data. International Journal of Remote Sensing, 32:22, 7111-7129
  9. Susanto A. 2013. Laju Infeksi Ganoderma pada Empat Kelas Struktur Tanah. J Fitopanol Indonesia. 9(2):39-46.
  10. Thomson S J, Brand H J, Reddy K N. 2016. Development of low altitude Remote sensing systems for crop production management. Int J Agric & Biol Eng; 9(4): 1-11.