COMPARISON OF THE MANGROVE FOREST MAPPING ALGORITHMS IN KELABAT BAY USING RANDOM FOREST AND SUPPORT VECTOR MACHINES
DOI:
https://doi.org/10.30536/j.ijreses.2023.v20.a3885Keywords:
mangrove, mapping, remote sensing, machine learning, random forest, support vector machine, kelabat bayAbstract
One of the tropical ecosystems is the mangrove forest, which thrives on protected coastlines such as bays, estuaries, lagoons, and rivers. These are usually found in the intertidal zone. Mangroves are a valuable natural resource because they stabilize coastlines, prevent erosion, retain sediment and nutrients, protect against storms, regulate floods and currents, sequester carbon, maintain water quality, serve as spawning grounds for fish and other marine life, and provide food For plankton. With over 59.8% of the total area of mangroves on the planet, Indonesia has some of the largest mangrove forests in the world. With the case study of Kelabat Bay in Bangka Regency and the Bangka Belitung Islands, this study compares the use of random forest (RF) techniques and support vector machines (SVM) for mapping mangrove forests. Landsat-9 imagery from 2022, taken via the Google Earth Engine (GEE), is the data source used in this study. This study utilizes computer programming and accuracy testing. As a result, RF detected mangrove forests covering an area of approximately 67 ha (OA: 0.932), while SVM detected mangrove forests covering an area of approximately 62 ha (OA: 0.912).
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Author (S)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright Notice for the International Journal of Remote Sensing and Earth Sciences (IJReSES)
Copyright Holder: Author(s).
By submitting an article to IJReSES, author(s) agree to the following terms:
1. Grant of Publishing Rights: Authors grant IJReSES the license to publish the article and to identify itself as the original publisher. This includes the right to make the article available in all forms and media.
2. Commercial Rights: Authors grant IJReSES the rights to produce and sell hardcopy volumes of the journal. These volumes may be purchased by libraries, individuals, or other entities.
3. Third-Party Use: Authors agree to allow any third party to freely use the article, provided that the original authors are credited and the article is cited appropriately. This facilitates the dissemination and impact of the work.
4. Creative Commons License: The article is distributed under the Creative Commons Attribution non Commercial Share Alike 4.0 License (CC BY-NC-SA 4.0). This license allows others to distribute, remix, adapt, and build upon the work, even commercially, as long as the original author is credited for the original creation.
5. Associated Published Material: Unless otherwise stated, any associated published material (such as supplementary data, graphics, and multimedia) is distributed under the same CC BY-NC-SA 4.0 License.
By adhering to these terms, authors ensure the wide dissemination and accessibility of their work, contributing to the advancement of knowledge in the fields of remote sensing and earth sciences.
