EventsThe 2nd International Online Conference on Marine Science and Engineering
Published
This submission belongs to the session S5. Marine Environmental Science and Pollution of the event The 2nd International Online Conference on Marine Science and Engineering
Published date
18 Nov, 2026
Academic Editor
author-avatarChun-Feng Li
Citation
Xudong Huang, Detection and discrimination of marine oil spills and look-alike phenomena in synthetic aperture radar imagery, in Proceedings of The 2nd International Online Conference on Marine Science and Engineering, 23 November–25 November 2026, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

Detection and discrimination of marine oil spills and look-alike phenomena in synthetic aperture radar imagery

1. School of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing, China
Abstract

Marine oil spills and several visually similar oceanic phenomena, such as biogenic slicks, low-wind areas, rain cells, and sea ice, often appear as dark patches in wide-swath synthetic aperture radar (SAR) imagery. This visual similarity among dark patches poses significant challenges for the reliable detection and discrimination of oil spills. To address this issue, we propose the Multi-class Dark Object Detection Network (MDODNet), a dedicated deep learning framework designed to simultaneously identify and classify multiple categories of dark features in wide-swath SAR images. The model is trained and validated using a cross-validated dataset comprising 11,040 annotated dark patches extracted from 2,192 Sentinel-1 VV-polarization SAR scenes. The proposed architecture enhances feature representation through an extended backbone and multi-scale feature fusion, while improving detection robustness via an anchor-based head optimized with the Focal-EIoU loss. Evaluations on an independent test dataset demonstrate strong multi-class detection performance, with average precision (AP) values of 87.04% for biogenic slicks, 93.28% for low-wind areas, 88.82% for oil spills, 90.04% for rain cells, and 89.16% for sea ice. For oil spill scenarios, detected regions are further refined using the UNet++ segmentation model to enable precise boundary delineation and quantitative area estimation. Case studies and cross-platform validation experiments further demonstrate the generalization capability and robustness of MDODNet across diverse SAR data. These results indicate that the proposed framework provides a promising solution for operational, large-scale marine oil spill monitoring.

Keywords
oil spill,synthetic aperture radar,deep learning,detection,classification
Liver as a key matrix in ciguatera risk assessment: evidence from multi-method ciguatoxin characterization in Indian Ocean species.
Urbanisation does not influence trace metal contamination levels in sediments of recreational marinas of the northern Portuguese coast