Pemetaan Habitat Bentik Perairan Dangkal Di Pesisir Pulau Tiga (Selat Tiworo) Menggunakan Citra Satelit Sentinel-2a

Abstract

Penelitian pemetaan habitat bentik di Pulau Tiga masih sangat kurang dilakukan, sehingga ketersediaan data spasial habitat bentik di daerah ini sangat terbatas. Penelitian ini bertujuan untuk; memberikan informasi kelas tutupan habitat bentik perairan laut dangkal di Pulau Tiga dalam pendekatan OBIA dan menghitung tingkat akurasi citra satelit terhadap habitat bentik perairan laut dangkal di Pulau Tiga dalam pendekatan OBIA. Penelitian ini dilaksanakan di perairan Selat Tiworo khususnya perairan Pulau Tiga. Penelitian ini menggunakan data satelit Sentinel-2A dengan resolusi 10x10 m2 dan pengambilan data lapangan dilakukan pada bulan juni 2020. Klasifikasi citra dengan metode OBIA dengan klasifikasi terbimbing menggunakan algoritma klasifikasi yaitu support vector machine (SVM) dengan imput data lapangan diperoleh hasil klasifikasi habitat bentik sebanyak 6 kelas yaitu karang hidup, karang mati, rubble, lamun, makro alga dan pasir, dengan penerapan optimasi skala segmentasi yaitu scala 10, shape 0.5 dan compactness 0,5. Berdasarkan metode OBIA, habitat bentik dapat dipetakan dengan tingkat akurasi sebesar 88% pada citra klasifikasi dengan algoritma SVM.Kata Kunci: Habitat Bentik, Tutupan Habitat Bentik, OBIA

Benthic Habitat Mapping Using Sentinel-2A Imagery in the Waters of Pengudang Village, Bintan Regency

“…The results of research using the SVM algorithm are also evidenced by previous research conducted by (Rahmani, 2022), using object-based classification methods using Sentinel-2A imagery and UAV imagery, and resulted in accuracy of 73.95% and 81.51%. Mukrimin et al, (2021), also conducted research on object-based benthic habitat mapping using Sentinel-2A imagery with the application of SVM algorithm which resulted in an accuracy of 88%. In addition, other studies were also conducted using Sentinel-2A images with the application of MLC, MDC and MaDC algorithms which resulted in accuracy rates of 74.33%, 73.45%, and 78.35% respectively (La Ode Alifatri, 2022).…”

“…Various studies on mapping benthic habitats in shallow waters have been carried out using this image with several algorithm models used. Mukrimin et al, (2021) have mapped benthic habitats using Sentinel-2A imagery in 2020 and 2016 by applying the SVM algorithm, on the Coast of Pulau Tiga (Tiworo Strait) which resulted in accuracy rates of 88% and 30% respectively from 6 classes. Another study was also conducted in the Kei Islands, North Maluku using the same image by applying the Maximum Likelihood Classification (MLC), Minimum Distance Classification (MDC), and Mahalanobis Distance Classification (MaDC) algorithms which resulted in accuracy rates of 74.33%, 73.45%, and 78.35% respectively (La Ode Aliftari, 2022).…”