Email this article 
Coastal Ecosystem Classification Using Satellite-Based Machine Learning Approaches
Abstract
Sebagai negara kepulauan yang kaya akan sumber daya alam, Indonesia memiliki potensi ekonomi kelautan yang besar. Untuk mempertahankan potensi ekonomi ini dalam jangka panjang, ekonomi biru diperlukan sebagai konsep dalam menetapkan program pembangunan dan kebijakan publik. Salah satu cara untuk mengimplementasikan konsep tersebut adalah dengan menyusun neraca laut, yang kerangka kerjanya mengimplementasikan konsep ekonomi biru dalam bentuk neraca lingkungan. Neraca laut dapat dianggap mendukung pembentukan kebijakan dan program nasional suatu negara. Oleh karena itu, data spasial yang akurat yang mencerminkan kondisi terkini sangat penting untuk menyusun neraca ini. Namun, pengumpulan data tersebut dapat memakan biaya dan sumber daya yang besar, sehingga menjadi tantangan untuk memastikan ketersediaan informasi yang terkini dan akurat. Dalam konteks ini, sumber data alternatif dapat memberikan solusi yang layak. Penelitian sebelumnya telah berhasil membuktikan bahwa pemodelan pembelajaran mesin juga citra satelit Sentinel-1 dan Sentinel-2 mampu memetakan wilayah pesisir, seperti wilayah pasang surut dan bentik. Oleh karena itu, penelitian ini mencoba mengklasifikasikan ekosistem pesisir Taman Nasional Karimunjawa dengan memanfaatkan citra Sentinel-1 dan Sentinel-2 dan membandingkan hasil klasifikasi dari tiga metode pembelajaran mesin, yaitu Random Forest (RF), Support Vector Classification (SVC), dan Extreme Gradient Boosting (XGBoost), dan menganalisis perubahan ekosistem antara tahun 2020 dan 2023. Hasilnya menunjukkan bahwa RF memberikan hasil terbaik dalam melakukan klasifikasi untuk daerah bentik yang mencapai 0,77 dan 0,78 dalam skor F1 dan Koefisien Korelasi Matthew (MCC), sedangkan model SVC berhasil mencapai 0,83 dalam skor F1 dan MCC memberikan hasil terbaik untuk daerah pasang surut. Selanjutnya, luas terumbu karang dan padang lamun menurun masing-masing sebesar 6,524 km 2 dan 1,39 km 2 . Sedangkan, luas mangrove, kawasan terbangun, dan hutan menunjukkan sedikit perubahan.
Keywords
Full Text:
PDFReferences
U. Nations, “Blue economy definitions,” 2024, https://www.un.org/regularprocess/sites/www.un.org.regularprocess/files/, Accessed on 27 August 2024.
OECD, “Sustainable ocean economy country diagnostics of indonesia,” 2021, https://www.oecd.org/en/publications/sustainable- ocean-economy-country-diagnostics-of-indonesia_9bc36234-en.html, Accessed on 11 July 2024.
ERIA, “Asean blue economy framework,” 2023, https://asean.org/wp-content/uploads/2023/09/ASEAN-Blue-Economy- Framework.pdf, Accessed on 27 August 2024.
KKP, “Report of the ocean accounts development report in indonesia,” 2022, https://oceanaccounts.atlassian.net/wiki/spaces/WD/pages/939884628, Accessed on 6 June 2024.
S. Pramana et al., “Big data for government policy: Potential implementations of bigdata for official statistics in indonesia,” in 2017 International Workshop on Big Data and Information Security (IWBIS), pp. 17–21, 2017. DOI:10.1109/IWBIS.2017.8275097
K. Maurya, S. Mahajan, and N. Chaube, “Remote sensing techniques: mapping and monitoring of mangrove ecosystem—a review,” Complex and Intelligent Systems, vol. 7, no. 6, pp. 2797–2818, 2021. DOI:10.1007/s40747-021-00457-z
T. Nguyen et al., “Mapping of coral reefs with multispectral satellites: A review of recent papers,” Remote Sensing, vol. 13, no. 21, pp. 1–25, 2021. DOI:10.3390/rs13214470
NOAA, “What is a benthic habitat map?,” 2024, https://oceanservice.noaa.gov/facts/benthic.html, Accessed on 10 April 2024.
A. Anas, V. Siregar, and S. Wouthuyzen, “Performance of mlh and svm algorithms in mapping macroalga habitats using satellite data in pannikiang island, south sulawesi,” MAJALAH ILMIAH GLOBE, vol. 25, pp. 97–108, 11 2023.
P. Wicaksono, M. A. Fauzan, and S. G. W. Asta, “Assessment of sentinel-2a multispectral image for benthic habitat composition mapping,” IET Image Processing, vol. 14, no. 2, pp. 279–288, 2020. DOI:10.1049/iet-ipr.2018.8044
W. Lazuardi, P. Wicaksono, and M. A. Marfai, “Remote sensing for coral reef and seagrass cover mapping to support coastal management of small islands,” IOP Conference Series: Earth and Environmental Science, vol. 686, no. 1, p. 012031, 2021. DOI:10.1088/1755-1315/686/1/012031
A. Sharifi, S. Felegari, and A. Tariq, “Mangrove forests mapping using sentinel-1 and sentinel-2 satellite images,” Arabian Journal of Geosciences, vol. 15, no. 20, p. 1593, 2022. DOI:10.1007/s12517-022-10867-z
K. Upakankaew et al., “Discrimination of mangrove stages using multitemporal sentinel-1 c-band backscatter and sentinel-2 data—a case study in samut songkhram province, thailand,” Forests, vol. 13, no. 9, p. 1433, 2022. DOI:10.3390/f13091433
X. Liu et al., “Large-scale high-resolution coastal mangrove forests mapping across west africa with machine learning ensemble and satellite big data,” Frontiers in Earth Science, vol. 8, 2021. DOI:10.3389/feart.2020.560933
B. Misiuk and C. J. Brown, “Benthic habitat mapping: A review of three decades of mapping biological patterns on the seafloor,” Estuarine, Coastal and Shelf Science, vol. 296, p. 108599, 2024. DOI:10.1016/j.ecss.2023.108599
T. D. Pham et al., “Remote sensing approaches for monitoring mangrove species, structure, and biomass: Opportunities and challenges,” Remote Sensing, vol. 11, no. 3, p. 230, 2019. DOI:10.3390/rs11030230
S. Nemani et al., “A multi-scale feature selection approach for predicting benthic assemblages,” Estuarine, Coastal and Shelf Science, vol. 277, p. 108053, 2022. DOI:10.1016/j.ecss.2022.108053
BTNKJ, Panduan Pendidikan dan Penelitian di Taman Nasional Karimunjawa, Karimunjawa: Departemen Kehutanan Direktorat Jenderal Perlindungan Hutan Dan Konservasi Alam Balai Taman Nasional Karimunjawa, 2025, Accessed on 13 September 2024.
P. Wicaksono, P. A. Aryaguna, and W. Lazuardi, “Benthic habitat mapping model and cross validation using machine-learning classification algorithms,” Remote Sensing, vol. 11, no. 11, p. 1279, 2019. DOI:10.3390/rs11111279
W. Lazuardi et al., “Coastal reef and seagrass monitoring for coastal ecosystem management,” International Journal of Sustainable Development and Planning, vol. 16, no. 3, pp. 557–568, 2021. DOI:10.18280/ijsdp.160317
G. Varoquaux and O. Colliot, “Evaluating machine learning models and their diagnostic value,” New York: Machine Learning for Brain Disorders, pp. 601–630, 2023. DOI:10.1007/978-1-0716-3195-9_20
A. Umardiono, “Pengembangan Obyek Wisata Taman Nasional Laut Kepulauan Karimun Jawa,” J.FISIP, vol. 24, no. 4, pp. 192–201, 2013.
M. S. Daniar, “Potensi Alam Dan Kepariwisataan Kepulauan Karimunjawa Jepara Provinsi Jawa Tengah Sebagai Medan Pengembangan Olahraga Rekreasi,” vol. 53, no. 9, pp. 1689-1699, 2013.
BTNKJ, “Statistik balai taman nasional karimunjawa tahun 2022,” 2022, https://tnkarimunjawa.id/publikasi/dokumen, Accessed on 7 June 2024.
I. Fajarini, D. Suryandari, and M. Ihlashu’amal, “Peningkatan perekonomian penduduk melalui pembentukan kelompok sadar wisata (pokdarwis) di desa kemojan kepulauan karimunjawa kabupaten jepara,” in Prosiding Seminar Nasional Kolaborasi Pengabdian Masyarakat UNDIP-UNNES 2019, pp. 10–12, 2020.
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32. DOI:10.1023/A:1010933404324
H. I. Choi, “Lecture 10: Random forests,” 2017.
H. I. Choi, “Lecture 9: Classification and regression tree (cart),” 2017.
D. Traganos and P. Reinartz, “Mapping mediterranean seagrasses with sentinel-2 imagery,” Marine Pollution Bulletin, vol. 134, pp. 197–209, 2018. DOI:10.1016/j.marpolbul.2017.06.075
A. Ghorbanian et al., “Mangrove ecosystem mapping using sentinel-1 and sentinel-2 satellite images and random forest algorithm in google earth engine,” Remote Sensing, vol. 13, no. 13, p. 2565, 2021. DOI:10.3390/rs13132565
Asy’AriRahmat et al., “Mapping mangrove forest distribution on Banten, Jakarta, and West Java Ecotone Zone from Sentinel-2-derived indices using cloud computing based Random Forest,” Jurnal Pengelolaan Sumberdaya Alam dan Lingkungan (Journal of Natural Resources and Environmental Management), vol. 12, no. 1, pp. 97–111, 2022. DOI:10.29244/jpsl.12.1.97-111
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques (3rd ed.). Morgan Kaufmann Publishers, 2012, ISBN:9780123814791.
A. Ng and T. Ma, “Cs229 lecture notes,” 2023.
D. Wang et al., “Artificial mangrove species mapping using pléiades-1: An evaluation of pixel-based and object-based classifications with selected machine learning algorithms,” Remote Sensing, vol. 10, no. 2, p. 294, 2018. DOI:10.3390/rs10020294
Z. Zhao et al., “Comparison of three machine learning algorithms using google earth engine for land use land cover classification,” Rangeland Ecology and Management, vol. 92, pp. 129–137, 2024. DOI:10.1016/j.rama.2023.10.007
P. Wicaksono et al., “Sentinel-2 images deliver possibilities for accurate and consistent multi-temporal benthic habitat maps in optically shallow water,” Remote Sensing Applications: Society and Environment, vol. 23, p. 100572, 2021. DOI:10.1016/j.rsase.2021.100572
T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on
Knowledge Discovery and Data Mining, pp. 785–794, 2016. DOI:10.1145/2939672.2939785
J. Burger, H. J. Boonstra, and J. van den Brakel, “Effect of spatial scale, color infrared and sample size on learning poverty from aerial
images,” Remote Sensing Applications: Society and Environment, vol. 36, p. 101304, 2024. DOI:10.1016/j.rsase.2024.101304
D. Abriha, P. K. Srivastava, and S. Szabó, “Smaller is better? unduly nice accuracy assessments in roof detection using remote sensing
data with machine learning and k-fold cross-validation,” Heliyon, vol. 9, no. 3, p. e14045, 2023. DOI:10.1016/j.heliyon.2023.e14045
J. Goodman, S. Purkis, and S. Phinn, Coral Reef Remote Sensing: A Guide for Mapping, Monitoring and Management, 2013. ISBN 978-90-481-
-5
A. Purwanto and W. Asriningrum, “Identification of mangrove forests using multispectral satellite imageries,” International Journal of
Remote Sensing and Earth Sciences (IJReSES), vol. 16, no. 1, p. 63, 2019. DOI:10.30536/j.ijreses.2019.v16.a3097
A. S. A. Nugraha and I. P. A. Citra, “Perbandingan metode soil adjusted vegetation index (savi) dan forest canopy density (fcd) untuk
identifikasi tutupan vegetasi (kasus; area pembuatan jalan baru singaraja-mengwi),” Jurnal Geografi Media Informasi Pengembangan dan
Profesi Kegeografian, vol. 18, no. 1, pp. 1–8, 2021. DOI:10.15294/jg.v18i1.25367
A. A. Abubakar et al., Analysis of vegetation index (ndvi, savi, lai) on coffee productivity in bener meriah district, aceh province, in Proceedings of
the International Conference on Educational Technology and Social Science (ICoETS 2023), pp. 39–45, 2024. DOI:10.2991/978-2-38476-200-2_9.
J. Valdiviezo-N et al., “Built-up index methods and their applications for urban extraction from sentinel 2a satellite data: discussion,”
Journal of the Optical Society of America A, vol. 35, no. 1, pp. 35–44, 2018. DOI:10.1364/JOSAA.35.000035
XGB. Developerss, “Xgboost parameters," https://xgboost.readthedocs.io/en/stable/parameter.html, Accessed on 26 January 2025.
O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Scientific reports, vol. 14, no. 1,m p. 6086,
DOI:10.1038/s41598-024-56706-x
DOI: https://doi.org/10.37905/jjbm.v6i2.30466
Copyright (c) 2025 Giani Jovita Jane, La Ode Alifatri, Etjih Tasriah, Setia Pramana
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Jambura Journal of Biomathematics (JJBM) has been indexed by:
EDITORIAL OFFICE OF JAMBURA JOURNAL OF BIOMATHEMATICS |
 | Department of Mathematics, Faculty of Mathematics and Natural Science, Universitas Negeri Gorontalo Jl. Prof. Dr. Ing. B. J. Habibie, Moutong, Tilongkabila, Kabupaten Bone Bolango 96554, Gorontalo, Indonesia |
 | Email: [email protected] |
 | Jambura Journal of Biomathematics (JJBM) by Department of Mathematics Universitas Negeri Gorontalo is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Powered by Public Knowledge Project OJS. |