The rate of tropical deforestation is continuing to increase, and with it comes an enormous loss of biodiversity and natural resources. Ideally we need a massive number of new conservation projects that will provide alternatives to deforestation in the regions worst affected in the tropical equatorial belt. How can we figure out where to focus our efforts, and to verify their progress?

I will discuss how we are using satellite remote sensing to construct a global view of tropical rainforests, and to measure the effectiveness of conservation interventions from a viewpoint of the additionality gained vs natural forest dynamics, the tracking of leakage due to negative externalities, and the permanence of resulting changes. We use these measurements to build up a quantitative model of the conservation efforts that share common baselines globally, and then combine with qualitative metrics such as biodiversity, local livelihood and justice to build up a complete project assessment that can be used as the basis for trustworthy, verifiable carbon credits.

I will also discuss the computer science challenges required to build this infrastructure: the need for planetary scale computations, the need for digital permanence so projects can be tracked over decades, and the need for decentralised trust to operate globally.

Departmental Seminar at Cambridge: https://talks.cam.ac.uk/talk/index/185282