Analisis Tumpahan Minyak Di Laut Menggunakan Pemodelan Random Forest Berbasis Data Sentinel -1 SAR
Bilah Samping Artikel
Isi Artikel Utama
Abstrak
Tumpahan minyak di laut merupakan salah satu bentuk pencemaran yang memberikan dampak signifikan terhadap ekosistem pesisir, aktivitas perikanan, serta keselamatan pelayaran. Penginderaan jauh berbasis Synthetic Aperture Radar (SAR) menjadi teknologi yang banyak digunakan untuk mendeteksi tumpahan minyak karena mampu melakukan observasi tanpa dipengaruhi kondisi awan maupun pencahayaan. Penelitian ini bertujuan mengembangkan metode klasifikasi tumpahan minyak menggunakan citra Sentinel-1 Single Polarization (VV) melalui integrasi fitur statistik lokal dan algoritma Random Forest. Data yang digunakan terdiri atas citra Sentinel-1 dan mask hasil interpretasi sebagai data referensi. Fitur yang diekstraksi meliputi nilai backscatter VV, Local Mean, dan Local Standard Deviation menggunakan jendela 5×5 piksel. Sebanyak 400.000 sampel yang terdiri atas kelas minyak dan non-minyak digunakan untuk pelatihan model Random Forest dengan 200 pohon keputusan. Evaluasi dilakukan menggunakan confusion matrix, precision, recall, F1-score, dan overall accuracy. Hasil penelitian menunjukkan bahwa penggunaan fitur statistik lokal meningkatkan akurasi klasifikasi dari 84% menjadi 91,52%. Nilai precision mencapai 0,93 pada kelas non-minyak dan 0,90 pada kelas minyak, sedangkan recall masing-masing sebesar 0,89 dan 0,94. Model berhasil mengidentifikasi sekitar 1.969.436 piksel sebagai tumpahan minyak dengan estimasi luas 196,94 km². Dibandingkan dengan mask referensi, hasil klasifikasi masih menunjukkan kecenderungan over-estimation sehingga diperlukan pengembangan fitur tekstur yang lebih kompleks pada penelitian selanjutnya. Secara keseluruhan, integrasi fitur statistik lokal terbukti mampu meningkatkan kemampuan Random Forest dalam membedakan area minyak dan permukaan laut pada citra Sentinel-1 sehingga berpotensi digunakan sebagai metode operasional untuk pemantauan pencemaran minyak secara cepat dan otomatis.
Rincian Artikel
Artikel ini berlisensi Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Referensi
[1] C. Brekke and A. H. S. Solberg, “Oil spill detection by satellite remote sensing,” Remote Sens. Environ., vol. 95, no. 1, pp. 1–13, 2005, doi: 10.1016/j.rse.2004.11.015.
[2] A. H. S. Solberg, C. Brekke, and P. O. Husøy, “Oil spill detection in Radarsat and Envisat SAR images,” IEEE Trans. Geosci. Remote Sens., vol. 45, no. 3, pp. 746–754, 2007, doi: 10.1109/TGRS.2006.887019.
[3] H. A. Harahsheh, “Oil spill detection and monitoring of Abu Dhabi coastal zone using KOMPSAT-5 SAR imagery,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. - ISPRS Arch., vol. 41, no. July, pp. 1115–1121, 2016, doi: 10.5194/isprsarchives-XLI-B8-1115-2016.
[4] F. M. Bianchi, M. M. Espeseth, and N. Borch, “Large-scale detection and categorization of oil spills from sar images with deep learning,” Remote Sens., vol. 12, no. 14, pp. 7–11, 2020, doi: 10.3390/rs12142260.
[5] M. Krestenitis, G. Orfanidis, K. Ioannidis, K. Avgerinakis, S. Vrochidis, and I. Kompatsiaris, “Oil spill identification from satellite images using deep neural networks,” Remote Sens., vol. 11, no. 15, pp. 1–22, 2019, doi: 10.3390/rs11151762.
[6] J. S. Murugan, K. Ramkumar, P. R. Kshirsagar, and T. K. Tak, “Satellite-based oil spill detection using an explainable ViR-SC hybrid deep learning ensemble for improved accuracy and transparency,” Sci. Rep., vol. 16, no. 1, pp. 1–29, 2026, doi: 10.1038/s41598-026-37081-1.
[7] Y. Yang, S. Singha, and R. Goldman, “A near real-time automated oil spill detection and early warning system using Sentinel-1 SAR imagery for the Southeastern Mediterranean Sea,” Int. J. Remote Sens., vol. 45, no. 6, pp. 1997–2027, 2027, doi: 10.1080/01431161.2024.2321468.
[8] M. I. Habibie et al., A comparative study of fully automatic and semi ‑ automatic methods for oil spill detection using Sentinel ‑ 1 data. Springer International Publishing, 2025.
[9] M. Gade, W. Alpers, H. Hühnerfuss, V. R. Wismann, and P. A. Lange, “On the reduction of the radar backscatter by oceanic surface films: Scatterometer measurements and their theoretical interpretation,” Remote Sens. Environ., vol. 66, no. 1, pp. 52–70, 1998, doi: 10.1016/S0034-4257(98)00034-0.
[10] P. Singh and R. Shree, “Speckle noise: Modelling and implementation,” Int. J. Control Theory Appl., vol. 9, no. 17, pp. 8717–8727, 2016.
[11] A. A. Putra, D. Oktaviani, R. R. N. Syifa, S. A. Aliyan, and A. Fadhilah, “Deteksi Tumpahan Minyak Menggunakan Sentinel-1A Synthetic Aperture Radar dan Adaptive Threshold di Perairan Lhokseumawe,” J. Geogr. Sci. Educ., vol. 4, no. 2, pp. 162–172, 2026, doi: 10.69606/geography.v4i2.518.
[12] M. Mansourpour, M. A. Rajabi, and J. A. R. Blais, “Performance of Speckle Noise Reduction Filters on Active Radar and SAR Images,” Int. J. Technol. Eng. Syst., vol. 2, no. 1, pp. 111–114, 2011.
[13] H. Choi and J. Jeong, “Speckle noise reduction technique for sar images using statistical characteristics of speckle noise and discrete wavelet transform,” Remote Sens., vol. 11, no. 10, 2019, doi: 10.3390/rs11101184.
[14] Z. Yu, W. Wang, C. Li, W. Liu, and J. Yang, “Speckle noise suppression in SAR images using a three-step algorithm,” Sensors (Switzerland), vol. 18, no. 11, 2018, doi: 10.3390/s18113643.
[15] F. Nunziata, A. Gambardella, and M. Migliaccio, “On the degree of polarization for SAR sea oil slick observation,” ISPRS J. Photogramm. Remote Sens., vol. 78, pp. 41–49, 2013, doi: 10.1016/j.isprsjprs.2012.12.007.
[16] N. Pinel, C. Bourlier, I. Sergievskaya, N. Longépé, and G. Hajduch, “Asymptotic Modeling of Three-Dimensional Radar Backscattering from Oil Slicks on Sea Surfaces,” Remote Sens., vol. 14, no. 4, pp. 1–27, 2022, doi: 10.3390/rs14040981.
[17] S. A. Ermakov et al., “New Features of Bragg and Non-Polarized Radar Backscattering from Film Slicks on the Sea Surface,” J. Mar. Sci. Eng., vol. 10, no. 9, 2022, doi: 10.3390/jmse10091262.
[18] H. Zheng, J. Zhang, A. Khenchaf, and X. M. Li, “Study on non‐bragg microwave backscattering from sea surface covered with and without oil film at moderate incidence angles,” Remote Sens., vol. 13, no. 13, 2021, doi: 10.3390/rs13132443.
[19] H. Zheng, J. Zhang, Y. Zhang, A. Khenchaf, and Y. Wang, “Theoretical Study on Microwave Scattering Mechanisms of Sea Surfaces Covered with and without Oil Film for Incidence Angle Smaller Than 30°,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 1, pp. 37–46, 2021, doi: 10.1109/TGRS.2020.2993861.
[20] M. R. A. Conceição et al., “Sar oil spill detection system through random forest classifiers,” Remote Sens., vol. 13, no. 11, 2021, doi: 10.3390/rs13112044.