SavedAdd your journal

Journals / Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi / 2026 / Cilt: 41 Sayı: 1

Oil Spill Detection Using Sentinel-1 SAR Data

Sentinel-1 SAR Verileri Kullanılarak Petrol Sızıntısı Tespiti

Abdurahman Yasin Yiğit(MERSİN ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ, HARİTA MÜHENDİSLİĞİ BÖLÜMÜ, HARİTA MÜHENDİSLİĞİ PR.)0000-0002-9407-8022
Halil İbrahim Şenol(HARRAN ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ, HARİTA MÜHENDİSLİĞİ BÖLÜMÜ, KARTOGRAFYA ANABİLİM DALI)0000-0003-0235-5764
Pages
120–132
Publication Date
2025-04-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The model demonstrated an overall accuracy of 80% for MV Wakashio and 81% for MK Princess Empress, with an Intersection over Union (IoU) of 76% and 74.8%, respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Oil spills present a substantial threat to marine ecosystems and coastal economies, necessitating efficient and accurate detection methods.
📊
Key Findings & Data:Driven by the necessity for dependable monitoring in a variety of environmental conditions, this study utilizes Sentinel-1 Synthetic Aperture Radar (SAR) data and the Mask R-CNN deep learning model to detect and delineate oil spills.
💡
Conclusion & Impact:The model demonstrated an overall accuracy of 80% for MV Wakashio and 81% for MK Princess Empress, with an Intersection over Union (IoU) of 76% and 74.8%, respectively.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Petrol Sızıntısı Tespiti · Sentinel-1 · Çevresel Koruma

Abstract

Oil spills present a substantial threat to marine ecosystems and coastal economies, necessitating efficient and accurate detection methods. Driven by the necessity for dependable monitoring in a variety of environmental conditions, this study utilizes Sentinel-1 Synthetic Aperture Radar (SAR) data and the Mask R-CNN deep learning model to detect and delineate oil spills. Sentinel-1 was selected for its capacity to acquire data irrespective of weather conditions or time of day, thereby ensuring consistent monitoring. The Mask R-CNN model was selected for its ability to perform precise, pixel-level segmentation, enabling accurate spill boundary detection. The model's performance was evaluated using a dataset comprising 381 Sentinel-1 images from diverse geographic and environmental contexts. The model demonstrated an overall accuracy of 80% for MV Wakashio and 81% for MK Princess Empress, with an Intersection over Union (IoU) of 76% and 74.8%, respectively. These results underscore the model's efficacy in discerning oil spills from false positives, such as algal blooms and sediment patterns. The proposed methodology demonstrates a clear advantage over traditional techniques and exhibits scalability for real-time applications.

Özet

Petrol sızıntıları, deniz ekosistemleri ve kıyı ekonomileri için önemli bir tehdit oluşturmakta ve etkili ve doğru tespit yöntemleri gerektirmektedir. Çeşitli çevresel koşullarda güvenilir izleme gerekliliğinden hareketle, bu çalışmada petrol sızıntılarını tespit etmek ve tanımlamak için Sentinel-1 Sentetik Açıklıklı Radar (SAR) verileri ve Mask R-CNN derin öğrenme modeli kullanılmıştır. Sentinel-1, hava koşullarından veya günün saatinden bağımsız olarak veri elde etme kapasitesi nedeniyle seçilmiştir, böylece tutarlı bir izleme sağlanmıştır. Mask R-CNN modeli, hassas, piksel düzeyinde segmentasyon yapabilmesi ve doğru sızıntı alanı tespitine olanak sağlaması nedeniyle seçilmiştir. Modelin performansı, farklı coğrafi ve çevresel bağlamlardan alınan 381 Sentinel-1 görüntüsünden oluşan bir veri seti kullanılarak değerlendirilmiştir. Model, MV Wakashio için %80 ve MK Princess Empress için %81 genel doğruluk gösterirken, IoU sırasıyla %76 ve %74,8 olmuştur. Bu sonuçlar, modelin petrol sızıntılarını alg patlamaları ve tortu örüntüleri gibi yanlış pozitiflerden ayırt etmedeki etkinliğinin altını çizmektedir. Önerilen metodoloji, geleneksel tekniklere göre açık bir avantaj sağlamakta ve gerçek zamanlı uygulamalar için ölçeklenebilirlik sergilemektedir.

🔖

Cite This Article

Yiğit, A. Y., Şenol, H. İ. (2025). Oil Spill Detection Using Sentinel-1 SAR Data. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, Cilt: 41 Sayı: 1, 120–132. https://ajindex.com/articles/1266683

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (41)

  1. Raut, R. D., Narkhede, B., Gardas, B. B. 2017. To identify the critical success factors of sustainable supply chain management practices in the context of oil and gas industries: ISM approach. Renewable and Sustainable Energy Reviews, 68, 33-47.
  2. Khan, S. A. R., Godil, D. I., Yu, Z., Abbas, F., Shamim, M. A. 2022. Adoption of renewable energy sources, low‐carbon initiatives, and advanced logistical infrastructure—an step toward integrated global progress. Sustainable Development, 30(1), 275-288.
  3. Cheng, L., Li, Y., Qin, M., Liu, B. 2024. A marine oil spill detection framework considering special disturbances using Sentinel-1 data in the Suez Canal. Marine Pollution Bulletin, 208, 117012.
  4. Caporusso, G., Gallo, C., Tarantino, E. 2022. Change detection analysis using sentinel-1 satellite data with SNAP and GEE regarding oil spill in Venezuela. In International Conference on Computational Science and Its Applications (pp. 387-404). Cham: Springer International Publishing.
  5. Ahmed, S., ElGharbawi, T., Salah, M., El-Mewafi, M. 2023. Deep neural network for oil spill detection using Sentinel-1 data: application to Egyptian coastal regions. Geomatics, Natural Hazards and Risk, 14(1), 76-94.
  6. Dehghani-Dehcheshmeh, S., Akhoondzadeh, M., Homayouni, S. 2023. Oil spills detection from SAR Earth observations based on a hybrid CNN transformer networks. Marine Pollution Bulletin, 190, 114834.
  7. Houali, Y., Tounsi, Y., El Ghandour, F. E., Habib, A., Labbassi, Y., Labbassi, K. 2024. Implementation of a semi-automatic approach for detection and extraction of oil slicks using Sentinel-1: case study of the Moroccan exclusive economic zone. Remote Sensing Applications: Society and Environment, 101375.
  8. Anderson, K., Ryan, B., Sonntag, W., Kavvada, A., Friedl, L. 2017. Earth observation in service of the 2030 Agenda for Sustainable Development. Geo-spatial Information Science, 20(2), 77-96.
  9. Das, K., Janardhan, P., Narayana, H. 2024. Mauritius oil spill detection using transfer learning approach for oil spill mapping and wind impact analysis using Sentinel-1 data. International Journal of Hydrology Science and Technology, 18(4), 421-444.
  10. Emery, W., Camps, A. 2017. Introduction to satellite remote sensing: atmosphere, ocean, land and cryosphere applications. Elsevier.
  11. Ahn, Y. J., Yu, Y. U., Kim, J. K. 2021. Accident cause factor of fires and explosions in tankers using fault tree analysis. Journal of Marine Science and Engineering, 9(8), 844.
  12. Bhattacharjee, S., Dutta, T. 2022. An overview of oil pollution and oil-spilling incidents. Advances in Oil-Water Separation, 3-15.
  13. Temitope Yekeen, S., Balogun, A. L. 2020. Advances in remote sensing technology, machine learning and deep learning for marine oil spill detection, prediction and vulnerability assessment. Remote Sensing 12(20), 1-31.
  14. Vekariya, D., Vaghasiya, M., Tomar, Y., Laad, P., Parmar, K. 2024. A Survey on Oil Spill Detection using SAR images in Machine Learning. In 2024 Parul International Conference on Engineering and Technology (PICET) (pp. 1-7). IEEE.
  15. Fu, G., Xie, X., Jia, Q., Tong, W., Ge, Y. 2020. Accidents analysis and prevention of coal and gas outburst: Understanding human errors in accidents. Process Safety and Environmental Protection, 134, 1-23.
  16. Han, W., Chen, J., Wang, L., Feng, R., Li, F., Wu, L., Tian T., Yan, J. 2021. Methods for small, weak object detection in optical high-resolution remote sensing images: A survey of advances and challenges. IEEE Geoscience and Remote Sensing Magazine, 9(4), 8-34.
  17. Beisl, C. H., Mello, M. R., Elias, V., Becker, S., Carmo Jr, G. 2021. The Use of Radarsat-1 and Sentinel-1 Images for Seepage Slick Detection in Support of Deep-Water Petroleum Exploration in the Santos Basin, Brazil.
  18. Orhan, O., Oliver-Cabrera, T., Wdowinski, S., Yalvac, S., Yakar, M. 2021. Land subsidence and its relations with sinkhole activity in Karapınar region, Turkey: a multi-sensor InSAR time series study. Sensors, 21(3), 774.
  19. Karabörk, H., Makineci, H. B., Orhan, O., Karakus, P. 2021. Accuracy assessment of DEMs derived from multiple SAR data using the InSAR technique. Arabian Journal for Science and Engineering, 46(6), 5755-5765.
  20. Hoeser, T., Kuenzer, C. 2020. Object detection and image segmentation with deep learning on earth observation data: A review-part i: Evolution and recent trends. Remote Sensing, 12(10), 1667.
  21. Karunathilake, A., Ohashi, M., Kaneta, S. I., Chiba, T. 2022. Monitoring the spatial dispersion of an oil slick by enhancing and noise-filtering SAR images using SENTINEL-1 satellite repeat-pass observations. International Journal of Remote Sensing, 43(11), 4187-4207.
  22. Zhao, Z. Q., Zheng, P., Xu, S. T., Wu, X. 2019. Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems, 30(11), 3212-3232.
  23. Baghdady, S. M., Abdelsalam, A. A. 2024. Ten years of oil pollution detection in the Eastern Mediterranean shipping lanes opposite the Egyptian coast using remote sensing techniques. Scientific Reports, 14(1), 18057.
  24. Ghorbani, Z., Behzadan, A. H. 2020. Identification and instance segmentation of oil spills using deep neural networks. In 5th World Congress on Civil, Structural, and Environmental Engine.
  25. Tian, Y., Yang, G., Wang, Z., Li, E., Liang, Z. 2020. Instance segmentation of apple flowers using the improved mask R–CNN model. Biosystems engineering, 193, 264-278.
  26. Salau, J., Krieter, J. 2020. Instance segmentation with Mask R-CNN applied to loose-housed dairy cows in a multi-camera setting. Animals, 10(12), 2402.
  27. Guo, Z., Shi, Y., Ahmad, I. 2024. Design of smart citrus picking model based on Mask RCNN and adaptive threshold segmentation. PeerJ Computer Science, 10, e1865.
  28. Zhou, T., Li, Z., Zhang, C. 2019. Enhance the recognition ability to occlusions and small objects with Robust Faster R-CNN. International Journal of Machine Learning and Cybernetics, 10, 3155-3166.
  29. Pirinen, A., Sminchisescu, C. 2018. Deep reinforcement learning of region proposal networks for object detection. In proceedings of the IEEE conference on computer vision and pattern recognition (6945-6954).
  30. Nilsson, D., Pirinen, A., Gärtner, E., Sminchisescu, C. 2021. Embodied visual active learning for semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence (2373-2383).
  31. Mohammadiun, S., Hu, G., Gharahbagh, A. A., Li, J., Hewage, K., Sadiq, R. 2021. Intelligent computational techniques in marine oil spill management: A critical review. Journal of Hazardous Materials, 419, 126425.
  32. de Moura, N. V. A., de Carvalho, O. L. F., Gomes, R. A. T., Guimarães, R. F., de Carvalho Júnior, O. A. 2022. Deep-water oil-spill monitoring and recurrence analysis in the Brazilian territory using Sentinel-1 time series and deep learning. International Journal of Applied Earth Observation and Geoinformation, 107, 102695.
  33. Zhang, J., Feng, H., Luo, Q., Li, Y., Zhang, Y., Li, J., Zeng, Z. 2022. Oil spill detection with dual-polarimetric Sentinel-1 SAR using superpixel-level image stretching and deep convolutional neural network. Remote Sensing, 14(16), 3900.
  34. Yang, Y. J., Singha, S., Mayerle, R. 2022. A deep learning based oil spill detector using Sentinel-1 SAR imagery. International Journal of Remote Sensing, 43(11), 4287-4314.
  35. Arslan, N. 2018. Assessment of oil spills using Sentinel 1 C-band SAR and Landsat 8 multispectral sensors. Environmental monitoring and assessment, 190(11), 637.
  36. Aksoy, İ., Erenoğlu, R. C. 2020. Sentinel-1 Uydu Verileriyle Petrol Sızıntısı Tespiti Üzerine Bir İnceleme: İzmir Aliağa Örneği. Lapseki Meslek Yüksekokulu Uygulamalı Araştırmalar Dergisi, 1(1), 80-87.
  37. Makineci, H. B. 2023. Spatio-temporal change detection of built-up areas with Sentinel-1 SAR data using random forest classification for Arnavutköy Istanbul. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 12(2), 626-636.
  38. Öçer, N. E., Avdan, U. 2024. Mask R-CNN İle Uydu Görüntülerinde Gemi Tespiti. GSI Journals Serie C: Advancements in Information Sciences and Technologies, 7(1), 40-50.
  39. Şenol, H. İ. 2023. Gelişmiş Deniz Gözlemi: SAR Tabanlı Gemi Tespiti için CNN Algoritmalarının Kullanımı. Türkiye Lidar Dergisi, 5(1), 1-7.
  40. Doğanalp, S., Coşkuner, B., Makineci, H. B. 2024. Analysis of short-term Sentinel-1 data using the DInSAR method for monitoring displacement following the earthquakes of 6 and 20 February in Hatay city. Bulletin of Geophysics and Oceanography Vol, 65(4), 491-512.
  41. Arslan, N., Majidi Nezhad, M., Heydari, A., Astiaso Garcia, D., Sylaios, G. 2023. A principal component analysis methodology of oil spill detection and monitoring using satellite remote sensing sensors. Remote Sensing, 15(5), 1460.