Algoritma Extreme Gradient Boosting dan Multilayer Perceptron Untuk Pemetaan Hutan Mangrove

Amati Eltriman Hulu; Bau Toknok; Sensi Bunga; Arman Maiwa; Rizky Purnama

doi:10.23960/jgrs.ft.unila.451

Amati Eltriman Hulu Departemen Manajemen Hutan, Fakultas Kehutanan dan Lingkungan, IPB University
Bau Toknok Fakultas Kehutanan, Universitas Tadulako
Sensi Bunga Fakultas Teknik, Universitas Tadulako
Arman Maiwa Fakultas Kehutanan, Universitas Tadulako
Rizky Purnama Fakultas Kehutanan, Universitas Tadulako

DOI: https://doi.org/10.23960/jgrs.ft.unila.451

Keywords: Mangrove, Machine Learning, Extreme Gradient Boosting, Multilayer Perceptron

Abstract

Lanskap ekosistem pesisir terdiri dari beragam ekosistem yang kompleks, di mana ekosistem mangrove menjadi salah satu komponen integral yang penting. Keberlanjutan ekosistem pesisir sangat bergantung pada keberadaan mangrove, sehingga pemetaan hutan mangrove merupakan langkah krusial untuk tujuan konservasi dan pengelolaan lingkungan. Penelitian ini bertujuan untuk memetakan distribusi hutan mangrove dan kelas non-mangrove menggunakan algoritma Extreme Gradient Boosting (XGBoost) dan Multilayer Perceptron (MLP) berbasis citra Sentinel-2. Variabel prediktor yang digunakan meliputi band spektral biru, hijau, merah, near-infrared (NIR), shortwave infrared 1 (SWIR 1), dan shortwave infrared 2 (SWIR 2). Selain itu, penelitian ini juga menggunakan lima indeks spektral, yaitu, Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Modified Normalized Difference Water Index (MNDWI), Normalized Difference Moisture Index (NDMI), dan Combined Mangrove Recognition Index (CMRI). Evaluasi akurasi dilakukan menggunakan confusion matrix, classification report, overall accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma XGBoost menghasilkan overall accuracy sebesar 95,50%, sedangkan MLP menghasilkan overall accuracy sebesar 93,89%. Nilai tersebut menunjukkan bahwa kedua algoritma mampu mengklasifikasikan hutan mangrove dan kelas non-mangrove dengan tingkat akurasi yang tinggi. Namun, XGBoost menunjukkan performa yang lebih unggul dibandingkan MLP berdasarkan nilai akurasi keseluruhan dan metrik evaluasi klasifikasi. Hasil klasifikasi juga menunjukkan bahwa XGBoost mendeteksi hutan mangrove seluas 429,35 ha, sedangkan MLP mendeteksi hutan mangrove seluas 407,10 ha. Dengan demikian, pendekatan machine learning berbasis citra Sentinel-2, khususnya algoritma XGBoost dan MLP, dapat digunakan sebagai metode yang efektif untuk pemetaan hutan mangrove dan mendukung pengelolaan ekosistem pesisir secara berkelanjutan.

References

Alongi, D. M. (2014). Carbon cycling and storage in mangrove forests. Annual Review of Marine Science, 6. https://doi.org/10.1146/annurev-marine-010213-135020

Ayodele, B. V., Mustapa, S. I., Kanthasamy, R., Zwawi, M., & Cheng, C. K. (2021). Modeling the prediction of hydrogen production by co-gasification of plastic and rubber wastes using machine learning algorithms. International Journal of Energy Research, 45(6). https://doi.org/10.1002/er.6483

Bimrah, K., Dasgupta, R., Hashimoto, S., Saizen, I., & Dhyani, S. (2022). Ecosystem Services of Mangroves: A Systematic Review and Synthesis of Contemporary Scientific Literature. Sustainability, 14(19), 12051. https://doi.org/10.3390/su141912051

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13-17-August-2016. https://doi.org/10.1145/2939672.2939785

Cheng, Z., Li, Y., Sun, X., Yuan, J., Liu, D., & Xiang, Q. (2026). Improved XGBoost with multi-source UAV data for high-accuracy fine-scale mangrove mapping. Journal of Oceanology and Limnology. https://doi.org/10.1007/s00343-025-5293-8

Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5). https://doi.org/10.1214/aos/1013203451

Gao, B. C. (1996). NDWI - A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment, 58(3). https://doi.org/10.1016/S0034-4257(96)00067-3

Gupta, K., Mukhopadhyay, A., Giri, S., Chanda, A., Datta Majumdar, S., Samanta, S., Mitra, D., Samal, R. N., Pattnaik, A. K., & Hazra, S. (2018). An index for discrimination of mangroves from non-mangroves using LANDSAT 8 OLI imagery. MethodsX, 5. https://doi.org/10.1016/j.mex.2018.09.011

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December. https://doi.org/10.1109/CVPR.2016.90

Heumann, B. W. (2011). Satellite remote sensing of mangrove forests: Recent advances and future opportunities. Progress in Physical Geography, 35(1). https://doi.org/10.1177/0309133310385371

Hicks, D., Kastner, R., Schurgers, C., Hsu, A., & Aburto, O. (2020). Mangrove Ecosystem Detection using Mixed-Resolution Imagery with a Hybrid-Convolutional Neural Network. Tackling Climate Change with Machine Learning workshop at NeurIPS.

Hulu, A. E., & Alexis, M. (2025). Model Deteksi Tutupan Lahan di Kecamatan Gunungsitoli Menggunakan Algoritma Decision Tree Berbasis Machine Learning. Techno.Com, 24(3), 658–668. https://doi.org/10.62411/tc.v24i3.12955

Jamali, A., Roy, S. K., Hong, D., Atkinson, P. M., & Ghamisi, P. (2024). Spatial-Gated Multilayer Perceptron for Land Use and Land Cover Mapping. IEEE Geoscience and Remote Sensing Letters, 21, 1–5. https://doi.org/10.1109/LGRS.2024.3354175

Jaya, I. N. S. (2021). Analisis Citra Digital Perspektif Penginderaan Jauh untuk Pengelolaan Sumber Daya Alam (Vol. 1). PT Penerbit IPB Press.

Jaya, I. N. S., Tiryana, T., Suwiji, N. S. Z., & Diefda, G. (2025). Machine Learning dalam Penginderaan Jauh Kehutanan Modern: Citra Sintetis, Analisis Citra Berbasis Objek (OBIA) & Change Vector Analysis (CVA). IPB Press.

Kusmana, C. (2014). Distribution and current status of mangrove forests in Indonesia. Dalam Mangrove Ecosystems of Asia: Status, Challenges and Management Strategies. https://doi.org/10.1007/978-1-4614-8582-7_3

Leal, M., & Spalding, M. D. (2024). The State of the World’s Mangroves 2024. https://doi.org/10.5479/10088/119867

Lee, D. H., Kim, Y. T., & Lee, S. R. (2020). Shallow landslide susceptibility models based on artificial neural networks considering the factor selection method and various non-linear activation functions. Remote Sensing, 12(7). https://doi.org/10.3390/rs12071194

Magalhães, I. A. L., de Carvalho Júnior, O. A., de Carvalho, O. L. F., de Albuquerque, A. O., Hermuche, P. M., Merino, É. R., Gomes, R. A. T., & Guimarães, R. F. (2022). Comparing Machine and Deep Learning Methods for the Phenology-Based Classification of Land Cover Types in the Amazon Biome Using Sentinel-1 Time Series. Remote Sensing, 14(19). https://doi.org/10.3390/rs14194858

Mahmoudi, J., Arjomand, M. A., Rezaei, M., & Mohammadi, M. H. (2016). Predicting the Earthquake Magnitude Using the Multilayer Perceptron Neural Network with Two Hidden Layers. Civil Engineering Journal, 2(1). https://doi.org/10.28991/cej-2016-00000008

Miao, J., Zhen, J., Wang, J., Zhao, D., Jiang, X., Shen, Z., Gao, C., & Wu, G. (2022). Mapping Seasonal Leaf Nutrients of Mangrove with Sentinel-2 Images and XGBoost Method. Remote Sensing, 14(15). https://doi.org/10.3390/rs14153679

Mienye, I. D., & Sun, Y. (2022). A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects. Dalam IEEE Access (Vol. 10). https://doi.org/10.1109/ACCESS.2022.3207287

Minati, M., Yanuarsyah, I., & Hudjimartsu, S. A. (2023). Machine Learning XGBoost Method for Detecting Mangrove Cover Using Unmanned Aerial Vehicle Imagery. Jambura Geoscience Review, 5(2). https://doi.org/10.34312/jgeosrev.v5i2.20782

Neapolitan, R. E., & Jiang, X. (2018). Neural Networks and Deep Learning. Dalam Artificial Intelligence. https://doi.org/10.1201/b22400-15

Powers, D. M. W. (2011). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. ArXiv, abs/2010.16061. https://api.semanticscholar.org/CorpusID:3770261

Purwanto, A. D., Wikantika, K., Deliar, A., & Darmawan, S. (2022). Decision Tree and Random Forest Classification Algorithms for Mangrove Forest Mapping in Sembilang National Park, Indonesia. Remote Sensing, 15(1), 16. https://doi.org/10.3390/rs15010016

Raharjo, P., Setiady, D., Zallesa, S., & Putri, E. (2016). Identifikasi kerusakan pesisir akibat konversi hutan bakau (mangrove) menjadi lahan tambak di kawasan pesisir Kabupaten Cirebon. Jurnal Geologi Kelautan, 13(1).

Raschka, S., Patterson, J., & Nolet, C. (2020). Machine learning in python: Main developments and technology trends in data science, machine learning, and artificial intelligence. Dalam Information (Switzerland) (Vol. 11, Nomor 4). https://doi.org/10.3390/info11040193

Reski, N., Toknok, B., Korja, I. N., Naharuddin, Rosyid, A., Purnama, R., Yani, R. A., & Hulu, A. E. (2024). Kondisi habitat mangrove di Kelurahan Mapane Kecamatan Poso Pesisir Kabupaten Poso. ULIN: Jurnal Hutan Tropis, 8(1), 141–148.

Rouse, J. W., Haas, R. H., Schell, J. A., & Deering, D. W. (1974). Monitoring vegetation systems in the Great Plains with ERTS. NASA special publication. NASA special publication, 24(1).

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088). https://doi.org/10.1038/323533a0

Salampessy, M. L., Nugroho, B., Kartodiharjo, H., & Kusmana, C. (2024). Species composition and mangrove forest structure in Buano Island, Moluccas. IOP Conference Series: Earth and Environmental Science, 1315(1), 012020. https://doi.org/10.1088/1755-1315/1315/1/012020

Sanderman, J., Hengl, T., Fiske, G., Solvik, K., Adame, M. F., Benson, L., Bukoski, J. J., Carnell, P., Cifuentes-Jara, M., Donato, D., Duncan, C., Eid, E. M., Ermgassen, P. Z., Lewis, C. J. E., Macreadie, P. I., Glass, L., Gress, S., Jardine, S. L., Jones, T. G., … Landis, E. (2018). A global map of mangrove forest soil carbon at 30 m spatial resolution. Environmental Research Letters, 13(5). https://doi.org/10.1088/1748-9326/aabe1c

Sasmito, S. D., Sillanpää, M., Hayes, M. A., Bachri, S., Saragi-Sasmito, M. F., Sidik, F., Hanggara, B. B., Mofu, W. Y., Rumbiak, V. I., Hendri, Taberima, S., Suhaemi, Nugroho, J. D., Pattiasina, T. F., Widagti, N., Barakalla, Rahajoe, J. S., Hartantri, H., Nikijuluw, V., … Murdiyarso, D. (2020). Mangrove blue carbon stocks and dynamics are controlled by hydrogeomorphic settings and land-use change. Global Change Biology, 26(5). https://doi.org/10.1111/gcb.15056

Seydi, S. T., Ahmadi, S. A., Ghorbanian, A., & Amani, M. (2024). Land Cover Mapping in a Mangrove Ecosystem Using Hybrid Selective Kernel-Based Convolutional Neural Networks and Multi-Temporal Sentinel-2 Imagery. Remote Sensing, 16(15). https://doi.org/10.3390/rs16152849

Sibindi, R., Mwangi, R. W., & Waititu, A. G. (2023). A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices. Engineering Reports, 5(4). https://doi.org/10.1002/eng2.12599

Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing and Management, 45(4). https://doi.org/10.1016/j.ipm.2009.03.002

Sun, J., Jiang, W., Ling, Z., Fu, B., Zhang, Z., Xiao, Z., & Mu, X. (2025). Synergistic construction of an annual 2 m mangrove species dataset from 2016 to 2023 using structural features and hybrid stacked deep learning models—Beibu Gulf, Guangxi, China. ISPRS Journal of Photogrammetry and Remote Sensing, 230. https://doi.org/10.1016/j.isprsjprs.2025.10.007

Taghinezhad, J., & Sheidaei, S. (2022). Prediction of operating parameters and output power of ducted wind turbine using artificial neural networks. Energy Reports, 8. https://doi.org/10.1016/j.egyr.2022.02.065

Toknok, B., Hulu, A. E., Purnama, R., Panuntun, M. D., Zamani, I. S., & Hasibuan, D. K. A. (2026). Assessing mangrove health index as a basis for degradation mitigation planning. Journal of Degraded and Mining Lands Management, 13(2), 9953–9962. https://doi.org/10.15243/jdmlm.2026.132.9953

Xia, Y., Liu, C., Li, Y. Y., & Liu, N. (2017). A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring. Expert Systems with Applications, 78. https://doi.org/10.1016/j.eswa.2017.02.017

Xu, H. (2006). Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14). https://doi.org/10.1080/01431160600589179

Yan, H., Jiang, Y., Zheng, J., Peng, C., & Li, Q. (2006). A multilayer perceptron-based medical decision support system for heart disease diagnosis. Expert Systems with Applications, 30(2). https://doi.org/10.1016/j.eswa.2005.07.022

Yani, R. A., Naharuddin, N., Toknok, B., Malik, A., Akhbar, A., Massiri, S. D., & Suleman, S. M. (2024). Analysis of changes and criticality level of mangrove forest ecosystem as a basis for rehabilitation downstream of Poso Watershed Area, Central Sulawesi, Indonesia. Biodiversitas Journal of Biological Diversity, 25(9). https://doi.org/10.13057/biodiv/d250940

Ye, L., & Weng, Q. (2025). A hybrid neural network for mangrove mapping considering tide states using Sentinel-2 imagery. Remote Sensing of Environment, 329, 114917. https://doi.org/10.1016/j.rse.2025.114917

Zha, Y., Gao, J., & Ni, S. (2003). Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International Journal of Remote Sensing, 24(3). https://doi.org/10.1080/01431160304987

Zhen, J., Mao, D., Shen, Z., Zhao, D., Xu, Y., Wang, J., Jia, M., Wang, Z., & Ren, C. (2024). Performance of XGBoost Ensemble Learning Algorithm for Mangrove Species Classification with Multisource Spaceborne Remote Sensing Data. Journal of Remote Sensing, 4. https://doi.org/10.34133/remotesensing.0146