Pemanfaatan Citra Sentinel-2 untuk Identifikasi Vegetasi dengan Metode OBIA (Studi Kasus : Kecamatan Semanding, Kabupaten Tuban)

Zain, Achmad Fikri Althaf (2023) Pemanfaatan Citra Sentinel-2 untuk Identifikasi Vegetasi dengan Metode OBIA (Studi Kasus : Kecamatan Semanding, Kabupaten Tuban). Other thesis, Insittitut Teknologi Sepuluh Nopember.

Text 03311940000080-Non-Degree.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (4MB) | Request a copy

Abstract

Perkembangan teknologi penginderaan jauh semakin pesat, ditandai dengan mudahnya dalam mendapatkan data penginderaan jauh dan perangkat lunak pengolahnya. Penggunaan teknologi penginderaan jauh telah berkembang di berbagai bidang, salah satunya dalam mengidentifikasi jenis vegetasi yang menutupi suatu wilayah menggunakan metode Object Based Image Analysis (OBIA). Penelitian ini mengkaji pemanfaatan metode OBIA pada citra satelit sentinel-2 yang merupakan citra satelit dengan resolusi spasial kelas menengah untuk mengidentifikasi penutup lahan berupa jenis vegetasi pada wilayah tertentu, dalam hal ini adalah Kecamatan Semanding, Kabupaten Tuban. Digunakan dua masukan data citra sentinel-2 dengan proses pengolahan yang berbeda. Masukan data pertama mengeliminasi area non-vegetasinya menggunakan data vektor tutupan lahan sedangkan masukan data kedua mengeliminasi area non-vegetasinya menggunakan indeks spektral NDVI (Normalized Difference Vegetation Index). Jenis vegetasi dapat dikasifikasilan menjadi 4 kelas, yaitu pepohonan/hutan, perkebunan, sawah, dan semak/ilalang. Uji validasi dilakukan menggunakan data lapangan dan metode Confusion Matrix. Berdasarkan Confusion Matrix didapatkan overall Accuracy sebesar 86,02% dan kappa accuracy sebesar 74,40% dari hasil masukan data pertama serta overall accuracy sebesar 88,17% dan kappa accuracy sebesar 76,45% dari hasil masukan data kedua.
=================================================================================================================================
The development of remote sensing technology is progressing rapidly, marked by the ease of obtaining remote sensing data and processing software. The utilization of remote sensing technology has grown in various fields, one of which is the identification of vegetation types covering a specific area using the Object-Based Image Analysis (OBIA) method. This research examines the implementation of the OBIA method on Sentinel-2 satellite imagery, which provides medium spatial resolution, to identify land cover in the form of vegetation types in a particular region, in this case, Semanding District, Tuban Regency. Two sets of Sentinel-2 data were used with different processing approaches. The first data set eliminated non-vegetated areas using land cover vector data, while the second data set eliminated nonvegetated areas using the Normalized Difference Vegetation Index (NDVI) spectral index. The vegetation types were classified into four classes: trees/forests, plantations, rice fields, and shrubs/weeds. Validation tests were conducted using field data and Confusion Matrix method. Based on the Confusion Matrix, the overall accuracy was found to be 86.02% with a kappa accuracy of 74.40% for the first data set, and an overall accuracy of 88.17% with a kappa accuracy of 76.45% for the second data set.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Object-Based Image Analysis (OBIA), Sentinel-2, Vegetasi, Vegetation
Subjects:	G Geography. Anthropology. Recreation > G Geography (General) > G70.5.I4 Remote sensing
Divisions:	Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis
Depositing User:	Zain Achmad Fikri Althaf
Date Deposited:	07 Dec 2023 02:42
Last Modified:	07 Dec 2023 02:42
URI:	http://repository.its.ac.id/id/eprint/104721

Actions (login required)

View Item