Mangrove monitoring revealed by MDPrePost-Net using archived Landsat imageries

Dimyati, Muhammad and Umarhadi, Deha Agus and Jamaluddin, Ilham and Awanda, Disyacitta and Widyatmanti, Wirastuti (2023) Mangrove monitoring revealed by MDPrePost-Net using archived Landsat imageries. Remote Sensing Applications: Society and Environment, 32. ISSN 23529385

[thumbnail of 1-s2.0-S2352938523001234-main.pdf] Text
1-s2.0-S2352938523001234-main.pdf - Published Version
Restricted to Registered users only

Download (15MB) | Request a copy

Abstract

Acting as a global vital entity in the coastal ecosystem, mangroves are currently facing major threats to destruction due to anthropogenic activities. Restoration and rehabilitation measures of mangroves are being carried out, including in Indonesia. To support conservation actions in many islands in Indonesia, spatio-temporal information on mangroves is required. Remote sensing with advanced techniques such as machine learning and deep learning has proven the capability to spatially observe mangroves. This study aims to monitor mangrove change in three study areas, i.e., South Sumatra, North Kalimantan, and Southeast Sulawesi, using a fully convolutional network (FCN)-based MDPrePost-Net. This method was developed originally to assess the mangrove degradation due to a major event (i.e., Hurricane irma 2017 in southwest Florida), whereas this study adopts it for an extended observation period (1989–2022 for South Sumatra, 1991–2021 for North Kalimantan, and 1990–2021 for Southeast Sulawesi) using medium-resolution Landsat imageries. We observed that the mangroves remain stable within the national parks designated by the government. Outside the national parks, mangrove conversion massively occurred even though the areas are assigned as protection forests. The classification results showed satisfactory accuracy values of more than 84. The maps produced have an advantage in the spatial change analysis compared to the global datasets such as Global Mangrove Watch version 3.0. Our method has a limitation when cloudless images are not available. The integration with Synthetic Aperture Radar (SAR) images and a rigorous cloud removal method for the optical images may improve the results of mangrove monitoring. © 2023

Item Type: Article
Additional Information: Cited by: 2
Uncontrolled Keywords: Deep learning; Fully convolutional network; Remote sensing; Classification algorithm; Wetland
Subjects: S Agriculture > SD Forestry
S Agriculture > SH Aquaculture. Fisheries. Angling
Divisions: Faculty of Geography > Departemen Sains Informasi Geografi
Depositing User: Sri Purwaningsih Purwaningsih
Date Deposited: 03 Sep 2024 01:56
Last Modified: 03 Sep 2024 01:56
URI: https://ir.lib.ugm.ac.id/id/eprint/6124

Actions (login required)

View Item
View Item