Peningkatan Akurasi Klasifikasi Tutupan Lahan Menggunakan Random Forest pada Data Sentinel-2 di Jambi
DOI:
https://doi.org/10.37859/jf.v15i1.8886
Abstract
Klasifikasi tutupan lahan yang akurat memainkan peran penting dalam pemantauan lingkungan, perencanaan perkotaan, dan pengelolaan sumber daya berkelanjutan. Dengan meningkatnya kekhawatiran terhadap perubahan penggunaan lahan dan degradasi ekologis, pengembangan metode klasifikasi yang efektif menjadi semakin penting, terutama di wilayah yang mengalami transformasi lanskap secara cepat. Penelitian ini mengevaluasi kinerja tujuh algoritma machine learning (Random Forest, Extra Trees, Logistic Regression, Decision Tree, Naive Bayes, SGD Classifier, dan LightGBM) untuk klasifikasi tutupan lahan menggunakan data satelit Sentinel-2 di wilayah Jambi. Studi ini menggunakan 23 fitur, termasuk 10 band spektral dan 13 indeks spektral, dengan data yang dikumpulkan selama Q4 2024. Hasil menunjukkan bahwa Random Forest mencapai kinerja terbaik secara keseluruhan dengan akurasi 85.91% dan weighted F1-score 85.48%, diikuti oleh Extra Trees dengan akurasi 84.45%. Algoritma berbasis pohon keputusan menunjukkan kemampuan yang lebih unggul dalam membedakan area perkotaan, vegetasi, dan badan air, meskipun semua algoritma menghadapi tantangan dengan kelas minoritas. Temuan ini merepresentasikan peningkatan signifikan dibandingkan pendekatan sebelumnya yang hanya mencapai akurasi 37.7%-66.9% menggunakan indeks vegetasi tunggal. Peningkatan akurasi klasifikasi memungkinkan pemantauan yang lebih efektif terhadap deforestasi, ekspansi perkotaan, dan perubahan ekosistem di wilayah tropis, memberikan dukungan penting bagi kebijakan pengelolaan lahan berbasis bukti dan strategi konservasi di lanskap kompleks seperti Jambi.
Downloads
References
Nasution, A. A., Muslih, A. M., Ar-Rasyid, U. H., & Anhar, A., 2022. Land cover classification using Landsat 8 OLI in West Langsa Sub district, Langsa City, 3rd International Conference on Agriculture and Bio-industri. Banda Aceh, 13-14 Oktober 2021, IOP Publishing.
Swetanisha, S., Panda, A. R., & Behera, D. K., 2022. Land use/land cover classification using machine learning models. International Journal of Electrical and Computer Engineering, 12 (2), pp.2040-2046.
Hermosilla, T., Wulder, M. A., White, J. C., & Coops, N. C., 2022. Land cover classification in an era of big and open data: Optimizing localized implementation and training data selection to improve mapping outcomes. Remote Sensing of Environment, 268 (2022), doi.org/10.1016/j.rse.2021.112780.
Maruddani, R. F., Somantri, L., & Panjaitan, F., 2024. Analisis Spasial Perubahan Tutupan Lahan Pasca Kebakaran Hutan dan Lahan di Kabupaten Muaro Jambi. Jurnal Tanah dan Sumberdaya Lahan, 11 (2), pp. 443–453.
Zhao, J., Zhang, Z., Yao, W., Datcu, M., Xiong, H., & Yu, W., 2020. OpenSARUrban: A Sentinel-1 SAR Image Dataset for Urban Interpretation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, pp.187–203. https://doi.org/10.1109/JSTARS.2019.2954850.
Hariyono, M. I., Rokhmatuloh, Tambunan, M. P., & Dewi, R. S., 2021. Support Vector Machine for Land Cover Classification using Lidar Data. The 3rd Southeast Asian Conference on Geophysics. Online, 3-5 November 2020, IOP Publishing.
Indarto, I., Nadzirah, R., & Belagama, H. R., 2020. Pemetaan Lahan Sub-Optimal Berbasis Nilai NDVI Sentinel 2a: Studi Pendahuluan. Jurnal Presipitasi: Media Komunikasi dan Pengembangan Teknik Lingkungan, 17 (3), pp.194-204.
Nadzirah, R., Rizqon, M. K., & Indarto, I., 2024. Application of Sentinel-2A Images for Land Cover Classification Using NDVI in Jember Regency. Geosfera Indonesia, 9 (1), 41. https://doi.org/10.19184/geosi.v9i1.28846.
Heryadi, Y., & Miranda, E. 2020. Land cover classification based on sentinel-2 satellite imagery using convolutional neural network model: A case study in Semarang Area, Indonesia. Intelligent Information and Database Systems: Recent Developments 11, pp.191-206.
Yan, X., Li, J., Smith, A. R., Yang, D., Ma, T., & Su, Y., 2023. Rapid Land Cover Classification Using a 36-Year Time Series of Multi-Source Remote Sensing Data. Land, 12 (12). https://doi.org/10.3390/land12122149.
Fu, X., Chen, Y., Xu, F., Chen, Y., & Yan, J., 2023. BGRF: A broad granular random forest algorithm. Journal of Intelligent & Fuzzy Systems, 44 (2023), pp. 8103–8117.
Daddala, Y. O., & Shaik, K. (2024). Cardiovascular Disease Prediction: Employing Extra Tree Classifier-Based Feature Selection and Optimized RNN with Artificial Bee Colony. Revue d’Intelligence Artificielle, 38(2), 643–653. https://doi.org/10.18280/ria.380228.
Strzelecka, A., KurdyS-Kujawska, A., & Zawadzka, D., 2020. Application of logistic regression models to assess household financial decisions regarding debt. Procedia Computer Science, 176 (2020), pp.3418–3427.
Mienye, I. D., & Jere, N., 2024. A Survey of Decision Trees: Concepts, Algorithms, and Applications. IEEE Access, 12, pp.86716–86727, doi.org/10.1109/ACCESS.2024.3416838.
Peretz, O., Koren, M., & Koren, O., 2024. Naive Bayes classifier-An ensemble procedure for recall and precision enrichment. Engineering Applications of Artificial Intelligence, 136 (2024), pp.1-12. doi.org/10.1016/j.engappai.2024.108972.
Admojo, F. T., & Sulistya, Y. I., 2022. Analisis performa algoritma Stochastic Gradient Descent (SGD) dalam mengklasifikasi tahu berformalin. Indonesian Journal of Data and Science (IJODAS), 3 (1), pp.01-08.
Li, S., Jin, N., Dogani, A., Yang, Y., Zhang, M., & Gu, X. (2024). Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm. Processes, 12(1). https://doi.org/10.3390/pr12010221.
Downloads
Published
Issue
Section
License
Copyright Notice
An author who publishes in the Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) agrees to the following terms:
- Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
- Author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgement of its initial publication in this journal.
- Author is permitted and encouraged to post his/her work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).
Read more about the Creative Commons Attribution-ShareAlike 4.0 Licence here: https://creativecommons.org/licenses/by-sa/4.0/.
_(1).png)
