THE ACCURACY OF OBIA METHOD TO DETERMINE LANDSLIDE CANDIDATES IN SIRIMAU AND NUSANIWE DISTRICT, AMBON CITY Ferad Puturuhu (a*)
a) Pattimura University. *feradputuruhu[at]gmail.com
Abstract
The purpose of this study is to test the accuracy of the OBIA (Object Based Image Analysis) method in identifying landslide candidates in Sirimau and Nusanive Districts, Ambon City. This study was conducted using the OBIA digital interpretation method, which was carried out on Landsat 8 images with a 653 composite, using Idrisi Selva software. With two major stages in this process, namely: segmentation and classification. In the segmentation process there are several stages, namely: a) segmentation by determining how large the segmentation vector is used, b) segmentation training to create land cover training areas, c) classification is carried out using the maximum likelihood algorithm, and d) land cover segmentation classification is carried out. From this segmentation classification, a land cover classification is produced, with open land as a candidate for landslides. The results obtained from this study were that the results of digital interpretation with OBIA found 7 candidate landslides with a Similarity Tolerance of 50, while 9 existing landslides were found with an accuracy of 43.8%.
