Satellite-based oil spill detection using an explainable ViR-SC hybrid deep learning ensemble for improved accuracy and transparency.
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: ViR-SC combines a denoising autoencoder, U-Net++ localization and CNN/ResNet18/ViT/SVM/RF classifiers on 5,630 CSIRO Sentinel-1 patches with an 80/20 split; ensemble reports 98.45% accuracy and 98.37% F1.
Technology: ViR-SC combines a denoising autoencoder, U-Net++ localization and CNN/ResNet18/ViT/SVM/RF classifiers on 5,630 CSIRO Sentinel-1 patches with an 80/20 split; ensemble reports 98.45% accuracy and 98.37% F1.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- ViR-SC combines a denoising autoencoder, U-Net++ localization and CNN/ResNet18/ViT/SVM/RF classifiers on 5,630 CSIRO Sentinel-1 patches with an 80/20 split; ensemble reports 98.45% accuracy and 98.37% F1.
- Limitation / still unknown
- Held-out 1,126-patch test set and comparisons with five component classifiers; U-Net++ uses pseudo-labels because pixel masks are unavailable, and the evaluation is one public dataset without deployment.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.nature.com/articles/s41598-026-37081-1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.