[PROPL'24] Setting the stage for AI for biodiversity

Drew Purves

We are suddenly experiencing an unprecedented demand for actionable information on biodiversity from governments, NGOs, and corporations worldwide. These stakeholders require biodiversity information that is finer grained (in space and time), more accurate, and more comprehensive than anything available today. Obviously AI (by which we mean scaled up deep learning) has great potential to both provide and interpret this next generation of information – from gathering more ecological data; to integrating that data into more useful information; to helping groups of stakeholders to make informed decisions against that information. However, this kind of transformative progress in AI for biodiversity will require a new level of integration of data, organizations, people, and technology. After an expanded version of the above intro, touching on some specific opportunities and challenges, I’ll raise the (open!) question of how, and how deeply, we should try to build what we might call nature’s schemas (i.e. phylogeny, traits, interactions, geographic and environmental space, and ecological time) into the next generation of planetary computing platforms.