KLASIFIKASI PENUTUP/PENGGUNAAN LAHAN DENGAN DATA SATELIT PENGINDERAAN JAUH HIPERSPEKTRAL (HYPERION) MENGGUNAKAN METODE NEURAL NETWORK TIRUAN
Abstract
Hyperspectral remote sensing data has numerous spectral information for the land-use/land-cover (LULC) classification, but a large number of hyperspectral band data is becoming a problem in the LULC classification. This research proposes the use of the back propagation neural network for LULC classification with hyperspectral remote sensing data. Neural network used in this study is three layers, in which to test input layer has a number of neurons as many as 242 to process all band data, 163 neurons, and 50 neurons to process the data band has a high average digital number, and data bands at wavelengths of visible to near infrared. The results showed the use of all the data band hyperspectral on classification with the neural network has the highest classification accuracy of up to 98% for 18 LULC class, but it takes a very long time. Selecting a number of bands of precise data for classification with a neural network, in addition to speeding up data processing time, can also provide sufficient accuracy classification results.
ABSTRAK
Data penginderaan jauh hiperspektral memiliki informasi spektral yang sangat banyak untuk klasifikasi penutup/penggunaan lahan (LULC), akan tetapi banyaknya jumlah band data hiperspektral menjadi masalah dalam klasifikasi LULC. Penelitian ini mengusulkan penggunaan back propagation neural network untuk klasifikasi LULC dengan data penginderaan jauh hiperspektral. Neural network yang dipergunakan 3 lapis, dimana untuk uji coba lapis masukan memiliki jumlah neuron sebanyak 242 untuk mengolah seluruh band, 163 neuron, dan 50 neuron untuk mengolah data band yang memiliki nilai digital rataan yang tinggi, dan data band pada panjang gelombang cahaya tampak hingga infra merah dekat. Hasil penelitian menunjukkan penggunaan seluruh band data hiperspektral pada klasifikasi dengan neural network memiliki akurasi hasil klasifikasi tertinggi hingga 98% untuk 18 kelas LULC, akan tetapi waktu yang diperlukan sangat lama. Pemilihan sejumlah band data yang tepat untuk klasifikasi dengan neural network, selain mempercepat waktu pengolahan data, juga bisa memberikan akurasi hasil klasifikasi yang mencukupi.
Keywords
Full Text:
PDFReferences
Ablin R. And C.H. Sulochana, 2013. A Survey of Hyperspectral Image Classification in Remote Sensing, Inter. J. of Advanced Research in Computer and Communication Engineering, Vol. 2, Issue 8, pp.2986-3000.
Beck R. (ed), 2003. EO-1 users Guide v.2.3, Cincinnati Univ., Ohio, Amerika, http:// eo1.usgs.gov/ (diunduh Januari 2016).
Craig R., and J. Shan, 2002. Principal Component Analysis for Hyperspectral Image Classification, Surveying and Land Information Systems, Vol. 62, No. 2, pp.115-123.
Deilmai B.R., K.D. Kanniah, A.W. Rasib and A. Ariffin, 2014. Comparison of Pixel -Based and Artificial Neural Networks Classification Methods for Detecting Forest Cover Changes in Malaysia, IOP Conf. Ser.: Earth Environ, Sci. 18 012069.
Du Q., I. Kopriva, and H. Szu, 2006. Independent-Component Analysis for Hyperspectral Remote Sensing Imagery Classiï¬cation, Optical Engineering, Vol. 45, No. 1, 1-13.
Kitti K., C. Jaruskulchai, and A. Eiumnoh, 2012. Band Selection for Dimension Reduction in Hyper Spectral Image Using Integrated Information Gain and Principal Components Analysis Technique, Inter. J. of Machine Learning and Computing, Vol. 2, No. 3, 248-251.
Kushardono D., 1997a. Model Klasifikasi Penutup Lahan Data Multisensor Radar Optik, Majalah LAPAN, No.83, 31-41.
Kushardono D., 1997b. Metode Fuzzy Neural Network untuk Klasifikasi Penutup Lahan dari Data Penginderaan Jauh serta Perbandingannya dengan Back Propagation Neural Network dan Maximum Likelihood, Majalah LAPAN, No.80, 31-45.
Kushardono D., K. Fukue, H. Shimoda and T. Sakata, 1995a. Optimized Neural Network for Spatial Landcover Classification with the Aid of Co-occurence Matrix, J.of the Japan Soc. Of Photogrammetry and Remote Sensing, vol.34, no.4, 22-35.
Kushardono D., K. Fukue, H. Shimoda and T. Sakata, 1995b. Comparison of Multitemporal Image Classification Methods, IEEE Proc. of IGARSS, vol.II, 1282-1284.
Mader S, M. Vohland, T. Jarmer, and M. Casper, 2006. Crop Classification with Hyperspectral Data of the Hymap Sensor using Different Feature Extraction Techniques, Proc. of the 2nd Workshop of the EARSeL SIG on Land Use and Land Cover, Center for Remote Sensing of Land Surfaces, Bonn, 28-30 September 2006, 96-101.
Muhammad K., dan S. Arjasakusuma, 2010. Ekstraksi Informasi Penutup Lahan Menggunakan Spektrometer Lapangan Sebagai Masukan Endmember pada Data Hiperspektral Resolusi Sedang, J. Ilmiah Geomatika, Vol. 16, No. 2, 10-22.
Muller S., G.L.A. Mota, and C.E. Liedtke, 2004. Multitemporal Interpretation of Remote Sensing Data, Proc. of XXth ISPRS Congress Technical Commission IV, July 12-23, 2004, Istanbul, Turkey, 1244-1248.
Sari, N.N. dan D. Kushardono, 2014. Klasifikasi Penutup Lahan Berbasis Obyek pada Data Foto Udara untuk Mendukung Penyediaan Informasi Penginderaan Jauh Skala Rinci, J. Penginderaan Jauh, Vol. 11, No.2, 114-127.
Sun X., J. Zhang, and Z. Liu, 2005. A Comparison of Object-Oriented and Pixel-Based Classification Approachs using Quickbird, Proc. of Int. Symposium on Spatio-temporal Modeling, Spatial Reasoning, Analysis, Data Mining and Data Fusion, 27-29 Aug, Beijing, China.
Whiteside T. and W. Ahmad, 2005. A Comparison of Object-Oriented and Pixel-Based Classification Methods for Mapping Land Cover in Northern, Proc. of Spatial Intelligence, Innovation and Praxis: The national biennial Conf. of the Spatial Sciences Institute, September 2005. Melbourne, Australia.
Refbacks
- There are currently no refbacks.
