Syamsul Bahri Agus

Klasifikasi Habitat Bentik Berbasis Objek dengan Algoritma Support Vector Machines dan Decision Tree Menggunakan Citra Multispektral SPOT-7 di Pulau Harapan dan Pulau Kelapa.

The research of object based image classification (OBIA) with machine learning algorithm for high resolution image in Indonesia is still limited especially for coral reef mapping, therefore further research needed for comparison in method and application of algorithms as alternative of classification. This research aims to map benthic habitat based on multiscale classification using OBIA method with support vector machine and decision tree algorithm in Harapan Island and Kelapa Island, Kepulauan Seribu. Segmentation was performed using a multiresolution segmentation algorithm with a scale factor of 15. The OBIA method is applied to atmospheric corrected images with a predefined benthic habitat classification scheme. The overall accuracy of SVM and DT algorithm implementations are 76.68% and 60.62%, respectively. The Z statistic value analysis obtained from the application of two algorithms used is 2.23, where this value indicates that the classification with SVM algorithm is significantly different from the DT algorithm. This research suggest that the OBIA technique could be a promise approach for mapping benthic habitats.

PEMANFAATAN CITRA SPOT-7 UNTUK PEMETAAN DISTRIBUSI LAMUN PADA ZONA INTERTIDAL DAN PENDUGAAN KEDALAMAN PERAIRAN PULAU WAWONII

One of the important roles of seagrass habitat in the marine environment is as habitat for various types of marine biota. In Indonesia, the availability of spatial information of seagrass beds still leave a large gap, so it is necessary to keep on developing methods and mapping the seagrass ecosystems. This research utilized SPOT-7 imagery as the input to obtain spatial information of seagrass distribution in the coastal area of Wawonii Island, Southeast Sulawesi. The imagery also used to obtain water depth, especially the location where seagrass beds were found. Image transformation into depth was done using band ratio algorithm, while for seagrass distribution was obtained by supervised classification using MLH algorithm on pixel-based method. Both methods were applied using field information and secondary data obtained from several sources as references in performing digital image processing. The study focused on the western and northern sides of Wawonii Island, particularly in the shallow waters of Wawonii Barat, Wawonii Utara, and Wawonii Timur Laut Subdistrict. The result of satellite image classification shows the distribution of seagrass alongside the focused study of the Island with different thickness. The seagrass distribution zone is mainly determined by depth, where the distribution in this location is commonly less than 2m of water depth.

Formulating marine sanctuary designation for sustainable management of blue swimming crab in Lancang Island, Kepulauan Seribu

Lancang Island is the center of fisheries of blue swimming crab in Kepulauan Seribu, Jakarta. Most of the inhabitants in this island are fishermen, and blue swimming crab is the main target without considering the stocks. One of the management effort of blue swimming crab by the government is the restriction of catchment size. To support the government policy and to maintain the population stocks and the sustainability of blue swimming crab around Lancang Island, we need another effort such us proposing area of Marine Sanctuary. The analysis of possibility area of the marine sanctuary was performed with simulated annealing using Marxan. The datasets were used in analysis included geomorphic model of habitat (sea floor), coastal ecosystems, blue swimming crab catches (sample size, location, and fishing pressure). The results obtained three possibility locations of the marine sanctuary, which is around of Laki Island, Southern, and Southeastern of Lancang Island. From the possibility locations, we recommend the first location as the Marine Sanctuary with considering the more diverse of features represented.

The utilization of Depth Invariant Index and Principle Component Analysis for mapping seagrass ecosystem of Kotok Island and Karang Bongkok, Indonesia

Seagrass perform a variety of functions within ecosystems, and have both economic and ecological values, therefore it has to be kept sustainable. One of the stages to preserve seagrass ecosystems is monitoring by utilizing thespatial data accurately. The purpose of the study was to assess and compare the accuracy of DII and PCA transformationsfor mapping of seagrass ecosystems. Fieldstudy was carried out in Karang Bongkok and Kotok Island waters, in Agustus 2014 and in March 2015. A WorldView-2 image acquisition date of 5 October 2013 was used in the study. The transformations for image processing data were Depth Invariant Index (DII) and Principle Component Analysis (PCA) using Support Vector Machine (SVM) classification. The result shows that benthic habitat mapping of Karang Bongkok using DII and PCA transformations were 72%and 81% overalls accuracy respectively, whereas of Kotok Island were 83% and 84% overalls accuracy respectively. There were seven benthic habitat types found in karang Bongkok waters and in Kotok Island namely seagrass, sand, rubble, coral, logoon, sand mix seagrass, and sand mix rubble. PCA transformation was effectively to improve mapping accuracy of sea grass mapping in Kotok Island and Karang Bongkok.

Spatial distribution and biophysics chemistry characterization of Pearl Oyster farming in Semau Strait, East Nusa Tenggara

Pearl oyster is one of marine organisms which has high of economic value. One of Indonesia region that potential for pearl oyster farming activity is Semau Strait-East Nusa Tenggara. The purpose of this study is mapping and characterize spatial distribution based on biophysics chemistry condition of pearl oyster farming. Mapping using Geographic Information System (GIS) tools, while grouping and characterize using hierarchical clustering and Mann-Whitney method. Grouping based on character similarity of biophysics chemistry divided the stations distribution into three groups: Group I is excellent group, Group II is good group and Group III is bad group for pearl oyster farming. Group I is excellent area because it has the highest values of dissolved oxygen, chlorophyll-a, and phytoplankton abundance. Group III is bad area because it temperature is high relatively.

Distribusi Spasial Rajungan (Portunus pelagicus) pada Musim Timur di Perairan Pulau Lancang, Kepulauan Seribu

A study was carried out to assess the present status of blue swimmer crab (Portunus pelagicus) in Lancang Island, incorporating identification of fishing ground, also measurement of environmental condition and crab biometry. Monthly catch assessment was performed on JuneSeptember 2015 at three landing bases using structured questionnaire and morphometric sampling of minimum randomly selected 30 crabs. Bathymetric survey was conducted to produce depth-contoured maps combined with certain oceanographic parameters (sea surface temperature, salinity, water clarity, total suspended solids, dissolved oxygen, and nitrate-NO3) measured at 15 sampling sites. A grid map was produced to identify key areas of crab fishing grounds, recruitment habitat, and spawning habitats. During southeast monsoon, main fishing ground was distributed in the western and southern part of Lancang Island (grid C3, C4, and D5). In general, crab yields were dominated by female (66.9%) and 43.8% of them were bearing eggs. Four size classes were determined from frequency distribution of carapace width (Class 1 = 7.010.6 cm; Class 2 = 10.714.2 cm; Class 3 = 14.317.8 cm; and Class 4 = 17.921.5 cm), with Class 2 as the most prominent catch. Referring to ontogenetic migration trait of the species, presumed recruitment habitat for blue swimmer crab in Lancang Island is located at A6, where abundant juveniles were harvested in the area with strong oceanic influence and depth range of 2430 m. Spatial coherence on the distribution of bearing egg female with several environmental parameters (sea surface temperature, salinity, and dissolved oxygen) indicates strong estuarine influence is required for crab spawning habitat at C3 and D5.