Journal of Analytical and Applied Computer Sciences | Volume 2 Issue 2 | Pages: 1-12 | Doi : 10.67914/jaacs/rsa/2.2/1-12

Research Article

OPEN ACCESS | Published on : 20-Aug-2026

An Enhanced Oil Spill Detection System Using Explainable Ai (XAI) and Transfer Learning on Synthetic Aperture Radar (SAR) Imagery

• Sadiya Idris Gwaisam
• Department of Computer Science, Federal University Kashere, Gombe State, Nigeria.

Peter Buba Zirra
• Department of Computer Science, Federal University of Agriculture, Mubi, Adamawa State.

Abstract

Marine petroleum spills caused serious ecological degradation. It is urgent for automation early oil spill detection and identification. Although SAR is an active microwave sensor providing continuous day-and-night operation in adverse conditions such as cloudy days or night, the difficulty for differentiating between oil slicks and natural ocean look-alike has increased since their SAR backscatter properties are quite similar. This paper presents an interpretable deep neural network model for pixel-level oil slick segmentation that leverages a U-Net with a ResNet50 (pre-trained) feature extractor and Spatial/Channel Squeeze-and-Excitation (SCSE) attention modules. Gradient-weighted Class Activation Mapping (Grad-CAM) was used in the meantime to improve the visual transparency of automatic decisions to find important input regions by showing where and why the decision was made (for example, a pixel-level region of an oil spill region was found because its internal convolutional layer recognized a particular pattern). Through utilizing an official Sentinel-1 SAR dataset for testing and validation, the model reached an overall accuracy of 98.65% and mean Intersection over Union (mIoU) of 0.894, showing that accurate and reliable remote sensing-based oil spill monitoring is improved by the combination of attention processes and transfer learning.

Keywords

ResNet50, Explainable Artificial Intelligence, Semantic Segmentation, Transfer Learning, Oil Spill Detection, Synthetic Aperture Radar (SAR)

References

• Ahn, B., Kim, J., & Choi, B. (2019). Artificial intelligence-based machine learning considering flow and temperature of the pipeline for leak early detection using acoustic emission. Engineering Fracture Mechanics, 210, 381–392.

  Akpan, E. (2022). Environmental consequences of oil spills on marine habitats and the mitigating measures: The Niger Delta perspective. Journal of Geoscience and Environment Protection, 10, 191–203.

  Almulihi, A., Alharithi, F., Bourouis, S., Alroobaea, R., Pawar, Y., & Bouguila, N. (2021). Oil spill detection in SAR images using online extended variational learning of Dirichlet process mixtures of Gamma distributions. Remote Sensing, 13(15), 2991.

  Barzegar, M., Mohammadzadeh, A., & Valadan Zoej, M. J. (2023). Deep learning-based oil spill detection from Sentinel-1 SAR imagery using DenseNet architecture. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, X-4/W1-2022, 95–101.

  Bovenga, F. (2020). Special issue “Synthetic Aperture Radar (SAR) techniques and applications.” Sensors, 20(5), 1–10.

  Chen, Y., & Wang, Z. (2022). Marine oil spill detection from SAR images based on attention U-Net model using polarimetric and wind speed information. International Journal of Environmental Research and Public Health, 19(12), 12315.

  Chen, Y. T., Chang, L., & Wang, J. H. (2023). Full-scale aggregated MobileUNet: An improved U-Net architecture for SAR oil spill detection. Sensors, 24(7), 3724.

  Dehghani-Dehcheshmeh, S., Akhoondzadeh, M., & Homayouni, S. (2023). Oil spills detection from SAR Earth observations based on a hybrid CNN transformer network. Marine Pollution Bulletin, 190, 114834.

  Dey, V., Zhang, Y., & Zhong, M. (2023). A review on image segmentation techniques with remote sensing perspective. ISPRS Journal of Photogrammetry and Remote Sensing, 194, 1–20.

  Elahi, M., Afolaranmi, S. O., Martinez Lastra, J. L., & Perez Garcia, J. A. (2023). A comprehensive literature review of the applications of AI techniques through the lifecycle of industrial equipment. Discover Artificial Intelligence, 3(1).

  Environmental Protection Agency. (2020). Oil spill response guidelines. https://www.epa.gov

  Fan, Y., Rui, X., Zhang, G., Yu, T., Xu, X., & Poslad, S. (2021). Feature merged network for oil spill detection using SAR images. Remote Sensing, 13(16), 3174.

  Fang, Y., Tian, J., Dai, S., & Xing, X. (2024). Advancements in remote sensing technologies for oil spill detection. Frontiers in Environmental Science and Technology Journal, 12(2), 45–62.

  Fezzai, O., Taibeche, A., & Karima, R. (2023). Deep learning for product quality inspection: State of the art. Journal of Manufacturing Systems, 67, 100–115.

  Hamza, M. S., Jauro, S. S., & Ismail, M. (2023). Oil spill detection using convolutional neural network. Bima Journal of Science and Technology, 7(4), 15–28.

  Hashimoto-Beltrán, R., García-Pedrero, Á., & González-Audícana, M. (2023). Multi-channel deep neural network for oil spill detection in SAR imagery. Remote Sensing, 15(3), 675.

  Hohl, A., Obadic, I., Fernández-Torres, M.-A., Najjar, H., Oliveira, D., Akata, Z., Dengel, A., & Zhu, X. X. (2024). Opening the black-box: A systematic review on explainable AI in remote sensing. arXiv. https://arxiv.org/abs/2402.13791

  Huang, X., Yang, J., Li, Y., & Wang, H. (2022). A deep learning framework for marine oil spill detection from synthetic aperture radar imagery. Marine Pollution Bulletin, 182, 113939.

  Huang, Z., Zhang, X., Tang, Z., Xu, F., Datcu, M., & Han, J. (2024). Generative artificial intelligence meets synthetic aperture radar: A survey. IEEE Geoscience and Remote Sensing Magazine, 12(1), 1–15.

  Khan, M. A., Khan, S., & Ahmed, A. (2022). Research methodology: A review. Journal of Advanced Research in Social Sciences, 5(1), 12–20.

  Kumar, R. (2022). Research methodology: An introduction. Journal of Research Methodology, 1(1), 1–12.

  Li, B., Xu, J., Pan, X., Ma, L., Zhao, Z., Chen, R., Liu, Q., & Wang, H. (2022). Marine oil spill detection with X-band shipborne radar using GLCM, SVM and FCM. Remote Sensing, 14(15), 3715.

  Li, C., Yang, Y., Yang, X., Chu, D., & Cao, W. (2023). A novel multi-scale feature map fusion for oil spill detection of SAR remote sensing. Remote Sensing, 16, 1684.

  Li, H., Chen, J., & Zhao, Y. (2022). Oil spill detection in SAR images using deep convolutional neural networks and semantic segmentation. Remote Sensing of Environment, 268, 112761.

  Li, Y., Chen, X., Zhang, H., & Liu, Q. (2023). A deep learning-based self-evolving oil spill detection algorithm using Sentinel-1 SAR imagery. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (pp. 1–4). IEEE.

  Liu, Q., Huang, T., Dong, Y., Yang, J., & Xiang, W. (2024). From pixels to images: Deep learning advances in remote sensing image semantic segmentation. arXiv.

  Mahmoud, A. S., Mohamed, S. A., & El-Khoriby, R. A. (2023). Oil spill identification based on dual attention UNet model using synthetic aperture radar images. Journal of the Indian Society of Remote Sensing, 51, 121–133.

  Nguyen, D.-T., Nguyen, T.-K., Ahmad, Z., & Kim, J.-M. (2024). Remaining useful life prediction for pressurized fluid pipelines based on acoustic emission monitoring and an adaptive fuzzy similarity measure. IEEE Access, 12, 104518–104530.

  Rios, L. M., Jones, P. R., & Wiggins, J. (2022). The role of public engagement in reducing marine litter. Marine Policy, 139, 104–112.

  Rios, M. P., Caiado, R. G. G., Vignon, Y. R., Corseuil, E. T., & Santos, P. I. N. (2024). Optimising maintenance planning and integrity in offshore facilities using machine learning and design science: A predictive approach. Applied Sciences, 14, 10902.

  Robles-Velasco, A., Cortés, P., Muñuzuri, J., & Onieva, L. (2024). A novel hybrid internal pipeline leak detection and location system based on modified real-time transient modelling. Modelling, 5, 1135–1157.

  Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Müller, K.-R. (2022). Explaining deep neural networks and beyond: A review of methods and applications. Proceedings of the IEEE, 109(3), 247–278.

  Shaban, M., Mahmoud, A., Al-Maadeed, S., & Aouada, D. (2021). A deep learning-based framework for oil spill detection in SAR images. IEEE Access, 9, 84272–84283.

  Singh, R., Kumar, A., & Singh, P. (2020). Research methodology: A systematic review. Journal of Social Science, 5(2), 1–10.

  Wang, J., Zhang, Y., & Liu, J. (2022). Microplastics in the marine environment: Sources, fate, and impacts. Environmental Science & Technology, 56(3), 1501–1510.

  Xu, J., Wang, H., Cui, C., Zhao, B., & Li, B. (2020). Oil spill monitoring of shipborne radar image features using SVM and local adaptive threshold. Algorithms, 13, 69.

  Yang, Y.-J., Singha, S., & Goldman, R. (2024). A near-real-time automated oil spill detection and early warning system using Sentinel-1 SAR imagery for the Southeastern Mediterranean Sea. International Journal of Remote Sensing, 45(6), 1997–2027.

  Yekeen, S. T., & Balogun, A.-L. (2020). Automated marine oil spill detection using deep learning instance segmentation model. ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B3-2020, 1271–1276.

  Zakzouk, M., Abdulaziz, A. M., Abou El-Magd, I., Dahab, A. S., & Ali, E. M. (2025). Automated oil spill detection using deep learning and SAR satellite data for the northern entrance of the Suez Canal. Scientific Reports, 15, 20107.

  Zakzouk, M., El-Mashad, S., & El-Shafie, A. (2025). Deep learning-based oil spill detection in SAR satellite imagery using DeepLabV3+. Scientific Reports, 15, 3028.

  Zakzouk, M., El-Sayed, M., & Abd-Elrahman, A. (2025). Deep learning-based oil spill detection using SAR satellite imagery. Ocean Engineering, 295, 116981.

  Zeng, K., & Wang, Y. (2020). A deep convolutional neural network for oil spill detection from spaceborne SAR images. Remote Sensing, 12(6), 1015.

  Zhang, Y., Li, X., & Wang, J. (2023). Deep learning approaches for oil spill detection in synthetic aperture radar imagery. Remote Sensing, 15(6), 1587.

  Zhang, Y., Liu, X., Chen, Z., & Wang, L. (2024). Improved DeepLabV3+ network for oil spill detection in SAR images. Sensors, 24(17), 5460.

  Zhang, Z., Sun, H., & Guo, Y. (2024). The impact of marine oil spills on the ecosystem. International Journal of Engineering Science and Technology, 2(1), 1–10.

  Zheng, J., Wang, C., Liang, Y., Liao, Q., Li, Z., & Wang, B. (2022). Deeppipe: A deep-learning method for anomaly detection of multi-product pipelines. Energy, 259, 125025.

  Zhou, Y., Chen, L., & Hu, Y. (2021). The ecological impacts of oil spills: A review. Environmental Pollution, 286, 117–129.