Status Quo: Field crews measure individual trees by hand to inventory carbon stocks over a small sample of a project’s area. This process costs tens to hundreds of thousands of dollars and can take months—or even years.

Pachama's Approach: We are building machine-learning models that integrate satellite data, field plots, and 3D airborne lidar imaging to map forest carbon over entire regions, and eventually, anywhere in the world. This satellite-based carbon mapping unlocks a more scalable, cost-efficient future for crediting.

Status Quo: In forest carbon markets, a baseline is a business-as-usual scenario used to estimate expected emissions without the incentive of carbon financing. Today, credit issuance relies on historical data and a complex set of subjective factors to set baselines.

Pachama's Approach: Using machine learning models, we match each satellite pixel in a project to a ‘control’ pixel outside the project with similar attributes. We then use satellite data to observe forest loss in the control pixels compared to the pixels in the project area.

Pachama’s suite of in-the-sky and on-the-ground technology, paired with machine learning, enables you to monitor progress and identify potential risks sooner.