Detection
The camera network and computer vision models flag smoke early enough for it to still be a small fire.
Pantera
The AI platform I lead end to end at 1.5°C — computer vision detection, satellite imagery, fire spread modeling, risk analysis, and the architecture underneath all of it.
Pantera — smoke detection
Actual system output
Smoke 0.0%
- Cameras
- 190 cameras in the network — 150 HaaS (hardware we run for landowners) and 40 SaaS (our software layered on infrastructure that's already there).
- Coverage
- 40M+ hectares under watch, including the Pantanal and indigenous territories.
- Accuracy
- 95% detection accuracy — measured in the field, not in a benchmark.
What it does
Risk
Weather, fuel, and terrain layered together to flag where a fire is likely to start or spread next.
Response
Turning a confirmed detection into a coordinated action on the ground — the part that actually stops a fire.
Impact
Measuring what changed afterward — area burned, land recovered — the case for doing this at all.
How it's built
A team of 8 — engineering, geospatial, and data science — running on Agile and OKRs. I've owned the architecture end to end as co-founder and CTO since 2020.
Python
FastAPI
AWS
Docker
PostGIS
PyTorch
Angular
umgrauemeio.com →
Get in touch
If you lead an early-stage climate or govtech team and want a technical second opinion, or you're building something in wildfire or geospatial monitoring, write to me.