We are a small research lab building computer-vision systems that monitor the Peruvian Amazon from orbit — detecting illegal gold mining, forest clearing, and road incursions within hours of when they happen.
Custom U-Net and SegFormer architectures trained on labeled Sentinel-2 and PlanetScope tiles across the western Amazon. Specialized heads for mine pits, tailings, burn scars, and road scars.
Pixel-paired models that compare time-aligned tiles week over week, controlling for cloud cover, seasonality, and atmospheric noise — surfacing only the changes that signal human activity.
Detections are joined against concession boundaries, protected areas, Indigenous territories, and known infrastructure. Each alert carries the context an analyst needs to decide what to do next.
Sentinel-1 synthetic-aperture radar feeds into the same pipeline so detection continues through the rainy season, when optical satellites see only cloud. Loss happens year-round; so does monitoring.
Artisanal and informal gold mining has stripped tens of thousands of hectares from the Madre de Dios floodplain — leaving behind moonscapes of toxic ponds and mercury-contaminated rivers. The activity is fast-moving, remote, and almost invisible from the ground.
That's exactly what satellites and computer vision are good at. Our models tile the region every week, surface what's changed, and route alerts to the conservation NGOs and enforcement agencies who can act on them.
We ingest Sentinel-2 L2A tiles across the Peruvian Amazon, apply per-band atmospheric normalization, and mask clouds and shadows with a learned classifier (FMask + custom head). Tiles that fail QA are flagged for SAR fallback.
A SegFormer-B3 backbone, finetuned on ~42,000 labeled tiles across MdD, Ucayali, and Loreto, produces per-pixel disturbance masks for five classes: intact forest, secondary growth, recent clearing, mine pit, tailings/pond.
Paired tiles from consecutive Sentinel passes feed a Siamese change-detection model. Differences below threshold are discarded; the rest become candidate detections with provenance, confidence, and bounding geometry.
Each candidate is intersected with concession polygons, protected-area boundaries, Indigenous territories, and prior alerts in PostGIS. Detections inside protected or unlicensed terrain are escalated to priority.
Alerts are pushed to partner dashboards and email digests with the imagery, geometry, confidence, and a one-click link to a verification tile. Analysts confirm or dismiss; their labels flow back into the next training run.
Sentinel-2, Sentinel-1 SAR, and PlanetScope tiles are pulled within minutes of acquisition.
Atmospheric correction, cloud masking, geometric alignment to a common reference grid.
Segmentation + paired change detection produce candidate polygons with confidence scores.
Each polygon is enriched with protected-area, concession, and Indigenous-territory context.
Verified, prioritized alerts are delivered to NGOs, researchers, and enforcement agencies.
Including organizations focused on Indigenous land defense, primary-forest monitoring, and ecosystem restoration in the western Amazon.
Including the Peruvian protected-area authority and prosecutors investigating environmental crime under specialized units.
All datasets the lab produces are made available to academic collaborators under non-commercial research licenses.
We're a small team. We collaborate with NGOs, government agencies, journalists, and academic groups. We also publish tooling, datasets, and pretrained weights for non-commercial research.