Investigation of Classification Algorithm for Land Cover Mapping in Oil Palm Area Using Optical Remote Sensing
Keywords:
Support Vector Machine, Kappa Coefficient, Supervised Classification, NDVI, Landsat 8 OLIAbstract
Technological development on globalization era enable the application of remote sensing technology in access speed and accuracy for mapping land cover based on image classification. The objective on this study is to investigate the utilization of remote sensing imagery of Landsat 8 Operational Land Imager (OLI) for the classification of land cover in oil palm area. Methodology consists of collecting of Landsat 8 OLI, radiometric and geometric correction, making the Region of Interest (ROI) based on class are used in the multispectral classification process to know the land cover in the form of oil palm area, accuracy analysis, and mapping land cover classification with the highest accuracy and kappa coefficient. The algorithm used for classification of land cover types to make class are Maximum Likelihood, Minimum Distance, and Support Vector Machine (SVM) by using various bands on Landsat image and added Normalized Difference Vegetation Index (NDVI). The results in this study show that Support Vector Machine is the best Algorithm of three classification algorithms using all bands on Landsat 8 OLI image with overall accuracy of 96,21% (kappa coefficient 0,9041), Maximum Likelihood Algorithm with overall accuracy of 89,53% (kappa coefficient 0,7713), and Minimum Distance Algorithm with overall accuracy of 84,83% (kappa coefficient 0,6799).
References
Ahmad A, Quegan S. 2012. Analysis of Maximum Likelihood Classification on Multispectral Data. Applied Mathematical Sciences. 129 (64):25–36.
Anderson, J. H., E., Roach J.T., & R. Wittmer. (1976). A Land Use and Land Cover Classification System for Use with Remote Sensor Data.Geological Survey Professional Paper 964. Washington: United States Government Printing Office.
Butler, R. A., L. P. Koh, and J. Ghazoul. (2009). “REDD in the Red: Palm Oil Could Undermine Carbon Payment Schemes.” Conservation Letters 2 (2): 67–73. doi:10.1111/j.1755263X.2009.00047.x.
Danoedoro, Projo. (2012). Pengantar Penginderaan Jauh Digital. Yogyakarta: ANDI Yogyakarta.
Duda, R.O., P.E. Hart. (1973). Pattern Classification and Scene Analysis, New York: Wiley
Eko, Rudi. (2012). Klasifikasi Penutupan Lahan Hutan Mangrove Di Kecamatan Buduran, Kabupaten Sidoarjo, Provinsi Jawa Timur, Dengan Citra Satelit Terrasar-X High Resolution. Skripsi Program Sarjana pada Fakultas Pertanian IPB. Bogor.
Hamdir, Ardian. (2014). Studi Perbandingan Klasifikasi Multispektral Maximum Likelihood Dan Support Vector Machine Untuk Pemetaan Penutup Lahan. Kartografi dan Pengindraan Jauh. Universitas Gajah Mada.
Hudson, William D. (1987), Digital Classification of Landsat Multispectral Scanner data – An Introduction, Research Report Natural Resources From The Michigan State University Agricultural Experiment Station East Lansing, No 483.
I.K. Nooni, A.A. Duker, I. Van Duren, L. Addae-Wireko & E.M. Osei Jnr. (2014). Support vector machine to map oil palm in a heterogeneous environment. International Journal of Remote Sensing Vol. 35, No. 13, 4778–4794.
Kementrian Pertanian. (2010). Outlook Komiditi Kelapa Sawit. Pusat dan Sistem Informasi Pertanian.
Mathur A. (2004). A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing.
Muhammad, Teguh. (2014). Kajian Beberapa Metode Klasifikasi Citra Digital Terhadap Data Penginderaan Jauh. Fakultas Matematika Dan Ilmu Pengetahuan Alam. Institut Pertanian Bogor.
Narumalani, D.C. Rundquist, R.L. Perk, J. Schalles, K. Hutchins, dan J. Keck. (2002). Classifying and Mapping General Coral-Reef Structure Using Ikonos Data. Photogrammetric Engineering & Remote Sensing. Vol. 68, No. 12, hal: 1297-1305
Sampurno, Rizky. (2016). Klasifikasi Tutupan Lahan Menggunakan Citra Landsat 8 Operational Land Imager (Oli) Di Kabupaten Sumedang. Fakultas Teknologi Industri Pertanian, Universitas Padjadjaran
Setyowati, Heratania. (2015). Aplikasi Citra Spot-6 Berbasis Transformasi spektral Untuk Estimasi Produksi Kelapa Sawit. Kartografi dan Pengindraan Jauh Universitas Gajah Mada.
Wielicki, Bruce. (1985). Cumulus Cloud Properties Derived Using Landsat Satellite Data: Journal of Climate and Applied Meteorology vol 25 no 3.
Yohannes. (2012). Sistem Pengindraan Jauh Teknik Survey dan Pemetaan. Diktat Kuliah. Lampung: Universitas Lampung.
