SEAGRASS ECOSYSTEM MAPPING WITH AND WITHOUT WATER COLUMN CORRECTION IN PAJENEKANG ISLAND WATERS, SOUTH SULAWESI
Previous studies showed that water column correction in habitat benthic mapping using remote sensing data can increase the accuracy of the information produced. This study aims to look at the distribution of seagrasses with and without water column correction using object-based classification (OBIA) on the Pajanekang Island. Field data on the distribution of seagrass and non-seagrass of a total of 347 points were taken in July-August 2018 with a transect 1x1 m2. The satellite data used was SPOT-7 imagery acquired on March 27, 2017, with a spatial resolution of 6×6 m2. Within the OBIA classification method, we used several algorithms such as Support Vector Machine (SVM), Bayes, K-Nearest Neighbor (KNN), and Decision Tree (DT) to map benthic and seagrass habitats. The results showed that the treatment of with and without water column correction in mapping benthic and seagrass ecosystem habitats using several classification algorithms produced no significant difference in the accuracy of classification image product. However, from the four algorithms used, the Bayes algorithm without water column correction produced the highest accuracy value for benthic habitat mapping of 70.36% and seagrass habitat of 66.47%. The results showed that water column correction did not provide better results in the classification of benthic and seagrass habitats of digital satellite imagery than that of without water column correction.
Copyright (c) 2020 Jurnal Ilmu dan Teknologi Kelautan Tropis
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors submitting manuscripts should understand and agree that copyright of manuscripts published are held by Tropical Animal Science Journal. This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-NC-SA) where Authors and Readers can copy and redistribute the material in any medium or format, as well as remix, transform, and build upon the material for any purpose, but they must give appropriate credit (cite to the article or content), provide a link to the license, and indicate if changes were made. If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.