eBird modeling

eBird Abundance Models provide an unparalleled window into the full annual cycle of bird populations in the Western Hemisphere. These species distribution models have been specifically developed for eBird data by statisticians and researchers at the Cornell Lab of Ornithology. These models have been used in a number of papers and reports including three State of the Birds Reports, most recently in 2016.

eBird Abundance Models take eBird data from birdwatchers in the Western Hemisphere, add a suite of environmental variables, and generate predictions of where birds are on the landscape. The power of these models is the ability to standardize the variety of data that people collect in their eBirding, and also extrapolate beyond the data we have to make predictions in places where nobody has ever eBirded. Each 8km pixel in these models gives a specific prediction for the expected number of individuals you could expect to encounter in that region if you went birding for one hour at 7am covering one kilometer of distance.

Notable in these models is that they’re actually predicting the number of birds you’d encounter, which is why counting birds matters! Understanding abundances of birds is immensely more valuable for conservation, since it lets you know where the bulk of the population is at any given time, instead of just understanding whether any individuals of that species is present (which is all that you can know from an “X” on your checklist).

Our Help Center has more information on eBird models.