Beyond Segmentation: An Oil Spill Change Detection Framework Using Synthetic SAR Imagery

2026-01-05

arXiv.org

AI Summary

This study addresses the high false alarm rates and poor generalization of conventional single-temporal SAR-based oil spill segmentation methods, which struggle to distinguish actual oil spills from look-alike phenomena. To overcome this limitation, the authors propose a novel oil spill change detection (OSCD) paradigm that leverages bi-temporal SAR imagery to capture changes before and after a spill event. When genuine pre-spill images are unavailable, they introduce the TAHI framework to synthesize spatiotemporally consistent, high-fidelity pre-event SAR images. This work presents the first formal definition of the OSCD task, establishes the first OSCD dataset and benchmark, and integrates hybrid image inpainting with temporal authenticity enhancement techniques. Experimental results demonstrate a significant reduction in false alarms and improved detection accuracy, confirming the reliability and scalability of temporal-aware approaches for oil spill monitoring.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Marine oil spills are urgent environmental hazards that demand rapid and reliable detection to minimise ecological and economic damage. While Synthetic Aperture Radar (SAR) imagery has become a key tool for large-scale oil spill monitoring, most existing detection methods rely on deep learning-based segmentation applied to single SAR images. These static approaches struggle to distinguish true oil spills from visually similar oceanic features (e.g., biogenic slicks or low-wind zones), leading to high false positive rates and limited generalizability, especially under data-scarce conditions. To overcome these limitations, we introduce Oil Spill Change Detection (OSCD), a new bi-temporal task that focuses on identifying changes between pre- and post-spill SAR images. As real co-registered pre-spill imagery is not always available, we propose the Temporal-Aware Hybrid Inpainting (TAHI) framework, which generates synthetic pre-spill images from post-spill SAR data. TAHI integrates two key components: High-Fidelity Hybrid Inpainting for oil-free reconstruction, and Temporal Realism Enhancement for radiometric and sea-state consistency. Using TAHI, we construct the first OSCD dataset and benchmark several state-of-the-art change detection models. Results show that OSCD significantly reduces false positives and improves detection accuracy compared to conventional segmentation, demonstrating the value of temporally-aware methods for reliable, scalable oil spill monitoring in real-world scenarios.

Problem

• oil spill detection
• SAR imagery
• false positives
• change detection
• bi-temporal analysis

Innovation

• Oil Spill Change Detection
• Synthetic SAR Imagery
• Temporal-Aware Hybrid Inpainting
• Bi-temporal Change Detection
• High-Fidelity Inpainting