LAND COVER SPECTRAL DATA CLASSIFICATION USING ARTIFICIAL NEURAL NETWORK (ANN)
(1) Informatics Engineering, Faculty of Engineering, Pancasila University
(2) Informatics Engineering, Faculty of Engineering, Pancasila University
(3) Informatics Engineering, Faculty of Engineering, Pancasila University
(4) Informatics Engineering, Faculty of Engineering, Pancasila University
(5) Information Systems, Kalbis Institute
Corresponding Author
Abstract
Bamboo is one of the plants in the tropics which is also a lignocellulosic natural material which can be used as a substitute for wood. There are hundreds of types of bamboo in Indonesia, where each type has its own characteristics in its use so that bamboo has potential in the industrial sector where when combined with innovation and creativity it has high economic value and is in demand by domestic and foreign consumers. The use of "Remote Sensing" technology, especially in terms of identifying bamboo and vegetation and other objects, has been proven through research related to land cover classification. This study aims to classify land cover spectrum data using an Artificial Neural Network algorithm.Classification of 36 data consisting of light bamboo, dark bamboo, dry soil, wet soil, bricks, concrete, grass, and taro leaves was evaluated using accuracy techniques. The resulting accuracy is 94.45%.
Keywords
References
Ahmad, S., Pandey, A.C., Kumar, A. dkk. (2021). Potential of hyperspectral AVIRIS-NG data for vegetation characterization, species spectral separability, and mapping. Appl Geomat 13, 361–372. https://doi.org/10.1007/s12518-021-00355-
Dong, L., dkk. (2020). Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2. Remote Sens. 12, 958. https://doi.org/10.3390/rs12060958.
Kementerian Lingkungan Hidup dan Kehutanan. Bambu Penggerak Ekonomi dan Kualitas Lingkungan Hidup. (2021). Tersedia: http://pojokiklim.menlhk.go.id/read/bambu-penggerak-ekonomi-dan-peningkatan-kualitas-lingkungan-hidup [Diakses 11 Agustus 2021].
S.R. Sutardi, dkk, (2015). Informasi Sifat Dasar dan Kemungkinan Penggunaan 10 Jenis Bambu”, Pusat Penelitian dan Pengembangan Hasil Hutan Badan Penelitian, Pengembangan dan Inovasi Kementerian Lingkungan Hidup dan Kehutanan, 2015. Tersedia: http://www.forda-mof.org/files/Informasi_sifat_dasar_dan_kemungkinan_penggunaan_10_jenis_bambu.pdf [Diakses 11 Agustus 2021].
R. N. Febriani. (2016). Ada 420 Jenis Bambu di Indonesia yang Belum Termanfaatkan Secara Optimal. Tersedia: https://www.pikiran-rakyat.com. [Diakses 13 Agustus 2021].
B. T. Hartono. (2016). Tantangan dalam Penyediaan Bahan Baku Industri Berbasis Bambu di Indonesia. Tersedia: https://docplayer.info/47881661-Tantangan-dalam-penyeiaan-bahan-baku-industri-berbasis-bambu-di-indonesia.html. [Diakses 11 Agustus 2021]
Tim Penulis. (2015). Pengembangan Industri Berbasis Bambu, Badan Penelitian dan Pengembangan Kehutanan. Tersedia: www.forda-mof.org/index.php/berita/post/1983. [Diakses 11 Agustus 2021].
P. S. Roy, S. Saran dan S. Ghosh. (2014). Development of Biodiversity Information System for Northeast India Using Internet GIS. Symposium on Geospatial Theory Processing and Applications.
M. Törmä, M. Kervinen, and S. Anttila, (2015). Estimating vegetation phenological trends using MODIS NDVI time serie. Tersedia: doi: 10.1117/12.898062.
Ghayour L, dkk. (2021). Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms. Remote Sensing. 13(7):1349. https://doi.org/10.3390/rs13071349
H. Du., dkk. (2018). "Mapping Global Bamboo Forest Distribution Using Multisource Remote Sensing Data," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 11, no. 5, pp. 1458-1471, May 2018, doi: 10.1109/JSTARS.2018.2800127.
Liu, G.; Li, L.; Gong, H.; Jin, Q.; Li, X.; Song, R.; Chen, Y.; Chen, Y.; He, C.; Huang, Y.; Yao, Y. (2017). Multisource Remote Sensing Imagery Fusion Scheme Based on Bidimensional Empirical Mode Decomposition (BEMD) and Its Application to the Extraction of Bamboo Forest. Remote Sens. 2017, 9, 19. https://doi.org/10.3390/rs9010019.
Li, Y.; Han, N.; Li, X.; Du, H.; Mao, F.; Cui, L.; Liu, T.; Xing, L. (2018). Spatiotemporal Estimation of Bamboo Forest Aboveground Carbon Storage Based on Landsat Data in Zhejiang, China. Remote Sens. 2018, 10, 898. https://doi.org/10.3390/rs10060898
Bharadwaj, S.P; Subramanian, s.; Manda, S.; RAY, T.; Mukherjee, P.; RAO, R. (2003). Bamboo livelihood development planning, monitoring and analysis through GIS and remote sensing, J. Bamboo and Rattan, Vol. 2, No. 4, pp. 453–461.
Nfornkah, B. N., Rene, K., Martin, T., Louis, Z., Cedric, C., & Armand, T. (2020). Assessing the spatial distribution of bamboo species using remote sensing in Cameroon. Journal of Ecology and the Natural Environment, 12(4), 172-183. https://doi.org/10.5897/JENE2020.0839
Cat, Tuong & Tani, Hiroshi & Wang, Xiufeng & Pham, Van-Manh. (2019). Estimating Aboveground Biomass Of Bamboo And Mixed Bamboo Forest In Thua Thien-Hue Province, Viet Nam Using Palsar-2 And Landsat Oli Data. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLII-4/W20. 11-19. 10.5194/isprs-archives-XLII-4-W20-11-2019.
USGS. Remote Sensing. Tersedia: https://www.usgs.gov/faqs/what-remote-sensing-and-what-it-used [Diakses 11 Agustus 2021]
Article Metrics
Abstract View
: 102 times
Download : 33 times
DOI: 10.56327/jurnaltam.v13i2.1311
Refbacks
- There are currently no refbacks.
