All workCase study

SAR computer vision

Oil Spill Detection

A Sentinel-1 SAR semantic-segmentation pipeline for detecting marine oil spills, with model evaluation, georeferenced outputs, API serving and an interactive map UI.

Evidence domainDeep learning · computer vision · remote sensing · validation

Open public evidence
Compare / detectPublic repository evidence
MV Wakashio Sentinel-1 SAR oil-spill detection case-study output from the public Oil Spill Detection repository
0.566Oil IoU0.764Oil recall0.696Mean IoU0.802Macro F1
MV Wakashio case-study outputReal Sentinel-1 SAR case-study evidence with oil-class evaluation from the committed test run.

Evidence

What can actually be checked.

Oil IoU

0.566

Selected SegFormer mit-b2 result on the committed 110-image test split.

Oil recall

0.764

Oil-class recall from the same committed evaluation output.

Mean IoU

0.696

Five-class mean IoU; reported alongside, not instead of, oil-specific quality.

Real-event test

Wakashio

A previously unseen August 2020 Sentinel-1B scene over the MV Wakashio spill is included as a public case study.

The project

The hard class is oil, not background. The evaluation therefore has to reward finding oil instead of hiding behind headline pixel accuracy.

Oil slicks appear as dark patches in Sentinel-1 SAR, but low-wind zones, biogenic films and rain cells can look almost identical. The technical problem is distinguishing oil from those look-alikes while carrying the result from a trained model into georeferenced, usable output.

Role & scope

What this case study covers.

A five-class semantic-segmentation system spanning training and model comparison, oil-specific evaluation, ONNX export, Sentinel-1 ingestion/preprocessing, tiled inference, vectorized geospatial output, FastAPI serving and a React/MapLibre interface.

Approach

How the system earns the result.

01 — Frame

Model the confusing classes explicitly.

The task uses five classes — sea surface, oil spill, look-alike, ship and land — so look-alike confusion is represented rather than folded into background.

02 — Compare

Select on oil-specific evidence.

U-Net, DeepLabV3+ and SegFormer are evaluated on the committed test split. SegFormer mit-b2 is selected using oil IoU, oil recall and broader per-class metrics rather than background-dominated accuracy.

03 — Operationalize

Move from chips to full georeferenced scenes.

The selected model is exported to ONNX, reused for tiled scene inference and converted into GeoTIFF plus oil polygons before API delivery.

04 — Challenge

Run the pipeline on a real unseen event.

The public Wakashio case study applies the end-to-end pipeline to a Sentinel-1B scene over Mauritius and documents both the detected location and the limitations of measured area.

Limits & boundaries

What the case study does not pretend.

  • The official dataset is small and imbalanced: 1002 training images, 110 test images, with oil occupying roughly 1% of pixels.
  • Training uses a single VV SAR channel; dual-polarization information is not exploited.
  • The raw-scene case study crosses a preprocessing/domain gap, so detected area is presented as an approximate lower bound rather than false measurement certainty.

Public record

What is publishable, and where the evidence lives.

The modernized repository explicitly avoids using the original project's background-dominated accuracy as the headline result. The case study preserves that same metric discipline.

Public repositoryWakashio case studyCommitted results

From proof to useful work

Relevant service pathways.