Every individual tree, monitored.
We find and assess individual trees in satellite, aerial and drone imagery. We're building a record that follows each tree across captures, so changes can be examined over time.
A high-resolution capture establishes an initial estimate of each tree's location, crown and class.
Frequent, coarser imagery is read at those known crowns.
Link observations across dates and sources where alignment supports a match.
Mortality, decline, inventory and change, per tree.
What we can do on your imagery now, and what we are building toward.
Three things we can deliver on a new site within weeks, and two we are building.
Drone, aerial or 30 cm satellite. Each tree becomes a point with an estimated crown size and a confidence.
Identify likely dead trees for review. This is the most reliable thing we do.
Mature from young, one species group from another, using examples reviewed with your team.
Every capture of the same crown, across sensors and years, on one record.
We are researching whether repeated observations can reveal decline earlier.
Find and count the animals in your survey imagery.
A survey flight produces tens of thousands of frames, and the bulk of the work is looking at nothing. Our pipeline discards the empty frames, finds the animals in the rest, and sorts them by species.
It is built for surveys that change: new regions, seasons, aircraft and camera setups it has never seen, without retraining from scratch. Before Giganteum, our team built and ran this kind of pipeline on national-scale surveys.
Other problems we know how to solve.
Trees are the mission. When a project fits what we know and helps fund that mission, we take it on. What we know is building models that keep working after they leave the lab: in new places, new seasons, and on imagery nobody trained them for.
Before Giganteum, our team spent twenty years at this: identifying individual animals in photographs from camera traps, dive cameras, drones and survey aircraft; counting wildlife across whole landscapes from the air; mapping habitat from satellite; and building the datasets, pipelines and agentic research tooling behind it. That work is in daily use by thousands of researchers across more than a hundred species.
What that experience covers:
- ML systems that survive deployment. Inference, quality checks, monitoring and validation for models in daily use.
- Detection, classification and individual re-identification from overhead and ground imagery.
- Large scientific datasets. Curation, provenance, security and the tooling to review them.
- Feasibility, proposals and program strategy for conservation and remote-sensing work.
We show you how it works and how we check it.
Giganteum is a small nonprofit with a startup's metabolism: a small team, no bureaucracy, twenty years of conservation technology behind us and trees ahead.
Those years were spent building the whole stack: new algorithms and the research behind them, data gathered from every continent, and models for detection, classification and re-identification that run in the field every day. We're bringing that experience to individual-tree monitoring.
Try it on a place you care about
If there is a forest, a park or a city you care about and some imagery of it, we'll run a session and show you what comes out, and what it would take to run inside your own systems. If you are building tools of your own, or want to join the mission, we'd like to hear from you.