Spotting Offshore Platforms from Space—Better with Synthetic Data
AI spots offshore platforms from space—better with synthetic data
Offshore wind, oil & gas, and aquaculture are growing fast. Researchers trained a YOLOv10 model on ESA Sentinel‑1 radar images from the Caspian Sea, South China Sea, Gulf of Guinea, and Brazil—then boosted learning with synthetic examples to cover rare shapes and sizes. Tested on unseen waters (Gulf of Mexico, North Sea, Persian Gulf), it detected 3,529 platforms: 411 in the North Sea, 1,519 in the Gulf of Mexico, and 1,593 in the Persian Gulf.
- F1 score: 0.85 → 0.90 with synthetic data
- Generalises beyond training regions; balances underrepresented classes
- Potential for scalable, global monitoring of offshore infrastructure
Preprint: http://arxiv.org/abs/2511.04304v1
Paper: http://arxiv.org/abs/2511.04304v1
Register: https://www.AiFeta.com
RemoteSensing AI ComputerVision SyntheticData YOLOv10 Sentinel1 Maritime Offshore EarthObservation Geospatial SatelliteRadar
