Deep learning-based object detection of offshore platforms on Sentinel-1 Imagery and the impact of synthetic training data

TL;DR

This paper demonstrates that combining synthetic and real Sentinel-1 satellite imagery improves deep learning models for offshore platform detection, enhancing global transferability and addressing data scarcity issues in remote sensing.

Contribution

It introduces a novel approach of using synthetic training data with deep learning to improve offshore infrastructure detection across multiple regions.

Findings

Model achieved an F1 score of 0.85, improved to 0.90 with synthetic data.

Synthetic data helps balance class representation and enhances model generalization.

The approach demonstrates potential for scalable, global offshore infrastructure monitoring.

Abstract

The recent and ongoing expansion of marine infrastructure, including offshore wind farms, oil and gas platforms, artificial islands, and aquaculture facilities, highlights the need for effective monitoring systems. The development of robust models for offshore infrastructure detection relies on comprehensive, balanced datasets, but falls short when samples are scarce, particularly for underrepresented object classes, shapes, and sizes. By training deep learning-based YOLOv10 object detection models with a combination of synthetic and real Sentinel-1 satellite imagery acquired in the fourth quarter of 2023 from four regions (Caspian Sea, South China Sea, Gulf of Guinea, and Coast of Brazil), this study investigates the use of synthetic training data to enhance model performance. We evaluated this approach by applying the model to detect offshore platforms in three unseen regions (Gulf of Mexico, North Sea, Persian Gulf) and thereby assess geographic transferability. This region-holdout evaluation demonstrated that the model generalises beyond the training areas. In total, 3,529 offshore platforms were detected, including 411 in the North Sea, 1,519 in the Gulf of Mexico, and 1,593 in the Persian Gulf. The model achieved an F1 score of 0.85, which improved to 0.90 upon incorporating synthetic data. We analysed how synthetic data enhances the representation of unbalanced classes and overall model performance, taking a first step toward globally transferable detection of offshore infrastructure. This study underscores the importance of balanced datasets and highlights synthetic data generation as an effective strategy to address common challenges in remote sensing, demonstrating the potential of deep learning for scalable, global offshore infrastructure monitoring.