~/projects/radar-flood-unet

Semantic segmentation of Sentinel-1 SAR imagery using a TensorFlow U-Net trained on 128×128 radar chips for all-weather flood mapping.

ACTIVE · 2024-05-01
SPECIFICATIONS // GEOAI · FLOOD MAPPING GeoAI · SAR · U-Net · TensorFlow
Architecture U-Net (16 / 32 / 48 / 64 filters)
Sensor Input Sentinel-1 SAR (128×128 patches)
Framework TensorFlow / Keras
Training Hardware RTX 2060 Super (6 GB VRAM)

Deep Learning U-Net for Radar Imagery Flood Mapping

Problem Context

During heavy rainfall and floods, cloud cover often blocks optical satellites. Sentinel-1 Synthetic Aperture Radar (SAR) can pass through clouds and measure surface roughness. Because calm floodwater acts like a flat mirror, it reflects the radar signal away and appears darker than surrounding vegetation or buildings.

Model & Chip Pipeline

The pipeline splits radar scenes into 128 × 128 pixel chips paired with binary flood masks from the Kaggle dataset (dimskeee/unet-segmentation-using-radar-imagery).

  • Encoder-Decoder Network: A compact U-Net using 16, 32, 48, and 64 filter blocks with skip connections to keep water boundaries sharp.
  • Memory-Friendly Training: Patch size and filter counts are kept light enough to train smoothly on a 6 GB VRAM GPU (RTX 2060 Super) without losing detail along narrow channels.
  • Visual Output Check: Stitched 512×512 cosine-blended predictions (IoU 0.74–0.83) can be compared pixel-by-pixel against SAR backscatter and ground truth in Plate 01 (/atlas/radar-flood-unet).

Engineering Notes

Keeping preprocessing and inference lightweight makes it easy to export predicted masks into standard GIS formats, such as GeoTIFF rasters or vector polygons, for flood response workflows.