Platform: Happening in both android app and on website Description of problem: https://www.inaturalist.org/observations/233180389 When I prompt the computer vision for this observation of Buchnera america I get the following results, where the correct genus is suggested, but no species options in…

Click the “Include suggestions not expected nearby” button underneath where is suggests Phlox pilosa: [IMG_4545] I presume a Buchnera species would be shown then. This usually happens when the CV is fairly sure about a species but it isn’t predicted to occur in an area, so although the genus is s…

The species does have a lot of observations from the area though (check my second screenshot) which is why I think this is a bug.

This just means that the geomodel doesn’t predict the species in that specific area. It may change when version 2.15 of the CV comes out in about a month (Correction: the geomodel appears to be updated separately from the computer vision)

Here’s what the geomodel of Buchnera americana looks like: [IMG_4547]

Okay I think there are two different things going on here: For some reason iNat doesn’t think the species occurs locally even though there are dozens nearby, most uploaded years ago: [image] This seems like a bug perhaps due to all the nearby observations being obscured. The resulting behav…

Interestingly there are no observations of the species from that coloured region! But maybe this is just an example of the model not dealing well with a species with several extremely isolated populations.

[image] reuvenm: perhaps due to all the nearby observations being obscured I can’t tell if the obscuration is due to OP choice or because of the species’ conservation status. I assume the latter. But does CV and it’s suggestions work off of obscured locations or the precise (hidden) locatio…

[image] reuvenm: I’m not sure why it would be desirable to instead suggest the genus which also has no nearby observations? It seems like it would make much more sense to just exclude the species entirely, and have Prairie Phlox as the top suggestion. The vision score is 97 (max = 100) for Bu…

Computer vision suggests genus but no species within it

Bug Reports

reuvenm August 2, 2024, 6:44pm 10

It is auto-obscured.

I don’t think the algorithm has any kind of habitat-based suggestions like you are suggesting.

Topic		Replies	Views
CV Suggesting Out of Range Species Bug Reports computer-vision , cv	13	499	June 8, 2026
Better use of location in Computer Vision suggestions Feature Requests	53	8628	April 13, 2021
Inclusion of barely observed species in computer vision suggestions General	5	1025	June 30, 2021
Computer Vision top species suggestion doesn't match 'pretty sure' genus suggestion Bug Reports android-app	7	208	February 13, 2026
How do Computer Vision results get sorted in the Suggestions/Compare Pop-ups? General web , identify	18	340	October 1, 2025

Computer vision suggests genus but no species within it

Related topics