Salvatore Prochilo
All projects
prototype

SAR Denoiser

A deep learning model that cleans a single Sentinel-1 radar image in one pass, trained on real multi-temporal references instead of synthetic noise. Presented as first author at ESA INSIGHT2026.

Code-drawn illustration of a radar-like scene of fields and lakes seen from above: grainy speckle on the left half, the same scene clean on the right, divided by a blue line.
Role
AI Engineer; first author and speaker at ESA INSIGHT2026
Organization
Starion Group
Period
2025 – 2026
  • SAR
  • Sentinel-1
  • denoising
  • PyTorch
  • Earth Observation
talk

Context

Radar satellites such as Sentinel-1 see through clouds and at night, but their images are covered in speckle, a grainy noise inherent to radar imaging. At Starion Group I worked on removing it with deep learning.

I presented the work as first author in an oral talk at ESA’s INSIGHT2026 workshop (ESRIN, Frascati, May 2026): From Temporal Stacking to Single-Pass Inference: A Deep Learning Framework for SAR Denoising with Real Sentinel-1 References.

The problem

Supervised denoising needs clean targets, and a speckle-free radar image does not exist.

Approach

The key idea: use temporal stacking only to train the model, not to run it.

  • Real references. For five geographic regions, 64 Sentinel-1 GRD passes of the same area over a three-year span are aligned at subpixel level (AROSICS) and averaged into a pseudo-clean reference, built only from real radar data. No synthetic speckle.
  • Supervised training. Each training pair is one single acquisition and the stack of the same area.
  • Single-pass inference. At deployment, one new acquisition goes through one forward pass, instead of 64 acquisitions. A single image also keeps what happens only once (a flood, a seasonal change), which a multi-year average erases.

My role

  • Built the subpixel co-registration and multi-temporal stacking pipeline that generates pseudo-clean Sentinel-1 GRD references from real acquisitions (five geographic regions, 64 passes each over a three-year span), removing the dependency on synthetic speckle for supervised training.
  • Trained a supervised SAR denoiser on real Sentinel-1 noisy–clean pairs: PSNR ≈ 30 dB, SSIM ≈ 0.85, EPI ≈ 0.92 on a held-out Sentinel-1 test set, with single forward-pass inference at deployment instead of 64 acquisitions.
  • Evaluated the downstream effect of denoising on land-cover classification against a Lee-filter baseline.
  • First author and oral presenter at the ESA INSIGHT2026 workshop.

Results

Metrics presented at ESA INSIGHT2026, on a held-out Sentinel-1 test set:

PSNR SSIM SNR ENL EPI
~30.3 dB ~0.85 ~25 dB ~41 ~0.92
  • PSNR / SSIM: how close one pass gets to the multi-temporal stack.
  • ENL (Equivalent Number of Looks): how smooth flat areas are. Higher means less speckle.
  • EPI (Edge Preservation Index): how well edges survive. 1.0 means perfect.

Stack

Python · PyTorch · Rasterio · GDAL · AROSICS · Sentinel-1 GRD · Copernicus Data Space

On stage at INSIGHT2026

  • Conference room at ESA-ESRIN: the title slide of the talk on the main screen, the session chairs at the table and Salvatore Prochilo at the lectern, next to large Earth observation images.
    Opening the talk at ESA-ESRIN, Frascati, 12 May 2026.
  • Salvatore Prochilo at the lectern during the talk. The screen shows the Motivation slide: speckle degrades SAR utility, no clean SAR references exist, multi-temporal stacking is expensive, and the proposed answer.
    The motivation slide: why a single-pass denoiser trained on real stacked references.
  • Salvatore Prochilo speaking at the lectern of the INSIGHT2026 workshop, in front of large Earth observation images.
    At the lectern, INSIGHT2026.