Cnemidophorus murinus consistently overlooked by CV

[petezani]

Platform:

App version number, if a mobile app issue:

Browser, if a website issue: Chrome

URLs (aka web addresses) of any relevant observations or pages:

https://www.inaturalist.org/observations/320287495

https://www.inaturalist.org/observations/320301562

https://www.inaturalist.org/observations/320300827

https://www.inaturalist.org/observations?captive=false&photos&subview=map&verifiable=any

Screenshots of what you are seeing:

Description of problem:

Step 1: A little backgound, each of the so-called A-B-C islands (Aruba, Bonaire, and Curacao) has an endemic species of Cnemidophorus lizard (C. arubensis, C. ruthveni, and C. murinus, respectively). Each species is included in the models with over 400 observations each. Furthermore, each island sits in its own cell on the map grid (see last screenshot of all observations).

Step 2: Regardless of the situation, I consistently notice the CV suggestions for Cnemidophorus from Curacao are excluding the only taxon match on the island. For example, first screenshot (320287495) shows an observation where the only suggestion is for the Bonaire species with the Curacao species nowhere to be found. Second screenshot (320301562) shows situation where C. murinus is not even in the top three suggestions with a mainland species offered instead. Third screenshot (320300827) shows situation where community ID is correct at C. murinus, but ONLY C. arubensis and C. ruthveni are suggested.

Step 3: I have never seen a CV suggestion for Cnemidophorus murinus.

[cthawley]

I don’t know that this is a bug per se, so I’m moving to General. I think this is likely in part a consequence of the geomodel for each species, which are all included in the CV, see:

Laurent’s: https://www.inaturalist.org/geo_model/38718/explain

Only predicted in two hexagons, one of which is the main one for Curacao (as it should be)

Aruba: https://www.inaturalist.org/geo_model/38751/explain

Predicts all of mainland and many islands

Ruthveni (Bonaire): https://www.inaturalist.org/geo_model/38720/explain

Predicts some of mainland and too many islands

[thomaseverest]

Yes this looks like a geomodel problem. Your three examples are from the northern part of the island, which isn’t included in the geomodel.

If you go further south, then that species is suggested.

[petezani]

Yesssss, that’s it.