Remote sensing technology is reliable in identifying the distribution of seabed cover yet there are still challenges in retrieving the data collection of shallow water habitats than with other objects on land. Classification algorithms based on remote sensing technology have been developed for application to map benthic habitats, such as Maximum Likelihood, Minimum Distance, and Support Vector Machine. This study focuses on examining those three classification algorithms to retrieve information on the benthic habitat in Pari Island, Jakarta using visual interpretation data for classification, and data field measurements for accuracy testing. This study used five classes of benthic objects, namely sand, sand-seagrass, rubble, seagrass, and coral. The results show how the proposed approach in this study provides an overall good classification of marine habitat with an accuracy produced 63.89–81.95%. The Support Vector Machine algorithm produced the highest accuracy rate of about 81.95%. The Support Vector Machine algorithm at a very high spatial resolution is considered to be capable of identifying, monitoring, and performing the rapid assessment of benthic habitat objects.

The impact of climate and human interaction has resulted in environmental degradation. Consistent observations of lakes in Indonesia are quite limited, especially for flood-exposure lake types. Satellite imagery data improves the ability to monitor water bodies of different scales and the efficiency of generating lake boundary information. This research aims to detect the boundaries of flood-exposure type lake water bodies from the detection model and calculate its accuracy in Semayang Melintang Lake using Sentinel-2 imagery data. The characteristics of water, soil, and vegetation objects were investigated based on the spectral values of the composite image bands from the Optimum Index Factor (OIF) calculation, to support the lake water body boundary detection model. The Object-Based Image Analysis (OBIA) method is used for water and non-water classification, by applying the machine learning algorithms random forest (RF), support vector machine (SVM), and decision tree (DT). Model validation was conducted by comparing spectral graphs and lake water body boundary model results. The accuracy test used the confusion matrix method and resulted in the highest accuracy value in the SVM algorithm with an Overall Accuracy of 95% and a kappa coefficient of 0.9. Based on the detection model, the area of Lake Semayang Melintang in 2021 is 23392.30 ha. This model can be used to estimate changes in the area of the flood-exposure lake consistently. Information on the boundaries of lake water bodies is needed to control the decline in the capacity and inundation area of flood-exposure lakes for management and monitoring plans.