Dynamics of Seagrass Expansion During Dry and Rainy Seasons Using Planetscope Imagery and Machine Learning Agus Aris (a,b*), Nurjannah Nurdin (c,d), Supriadi Mashoreng (c), Eymal Bahsar Demmalino (e), Chair Rani (c), S H Aly (f)
a) The Environmental Science Study Program Doctoral Program, Hasanuddin University Graduate School
b) Department of Remote Sensing and Geographic Information Systems, Vocational Faculty, Hasanuddin University, Jl. Perintis Kemerdekaan km.10, Makassar 90245, Indonesia
*agus.aris[at]unhas.ac.id
c) Departement of Marine Science Faculty of Marine Science & Fisheries, Hasanuddin University, Makassar, 90245. Indonesia
d) Research and Development Center for Marine, Coast and Small Islands, Hasanuddin University, Makassar 90245. Indonesia
e) Environmental Science study program, Hasanuddin University Graduate School
f) Department of Environmental Engineering, Engineering Faculty, Hasanuddin University, Makassar, Indonesia
Abstract
This preliminary study aims to estimate the carbon produced by seagrass meadows and develop a model to assess the relationship between organic carbon and bulk density in seagrass meadows and sediments, along with various environmental parameters (temperature, salinity, total suspended solids (TSS), NO2, CO, rainfall, and wind). The research focuses on seagrass meadows as critical carbon-sequestering ecosystems. The objective is to map the dynamics of seagrass meadows across different seasons using SuperDove imagery from PlanetScope, which offers a spatial resolution of 3 meters. The data utilized in this study encompass seagrass conditions and SuperDove imagery from 2020 to 2025. The methods employed in this research involve a machine learning approach, incorporating processes such as sun glint correction, segmentation, seagrass masking, and pixel-based classification using the random forest method. The results indicate significant spatial and temporal variations in seagrass coverage, particularly in the northern, western, and southern parts of the island, with accuracy levels between 70% and 75%. The high temporal resolution of SuperDove imagery demonstrates its effectiveness in tracking seagrass dynamics. Following laboratory analysis, this data will be utilized to estimate carbon based on varying seagrass density levels.
Keywords: Seagrass- Dry and Rainy Seasons- SuperDove- Machine Learning- Blue Carbon
