iNaturalist Suggesting Rustic Quaker instead of Rustic Sphinx

Please fill out the following sections to the best of your ability, it will help us investigate bugs if we have this information at the outset. Screenshots are especially helpful, so please provide those if you can.

Platform (Android, iOS, Website): iOS

App version number, if a mobile app issue (shown under Settings or About): 15.7.1

Browser, if a website issue (Firefox, Chrome, etc) : n/a - Using the iNaturalist App

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

Screenshots of what you are seeing (instructions for taking a screenshot on computers and mobile devices: https://www.take-a-screenshot.org/):

Description of problem (please provide a set of steps we can use to replicate the issue, and make as many as you need.):

Step 1: My brother-in-law sent me a picture of a pupa he dug up. Using the web, he identified it as a Rustic Sphinx. I questioned the specificity of this observation. For that reason, I uploaded his picture into the iCloud and then uploaded his picture into iNaturalist. https://www.inaturalist.org/observations/144326855. You can see it there.

Step 2: I asked iNaturalist for a suggested id. You can go to that observation and request it to suggest a id.

Step 3: iNat gave me several suggestions, none of which were Rustic Sphinx or, for that matter, any other butterfly in the Family Sphingidae, if you have requested an id., you will see that neither Rustic Sphinx nor any other butterfly in the Family Sphingidae.

Step 4: iNaturalist displayed Rustic Quaker as the third on a list of possible species. You can see that when you repeat these steps.

Step 5: You can ask any of the iNaturalist butterfly experts such as @stomlins701 or @k8thegr8 for an id. and I feel sure they will tell you this is one of the sphinx moths. I will do that now.

Here’s what I think has happened. Someone has incorrectly associated the name of a Walnut Quaker with a Walnut Sphinx in the database used by the iNaturalist photo recognition tool. Where in all the lines of code or in the database accessed by the photo recognition tool that might be found you might find this error I don’t know. I don’t think it’s an accident that the name Walnut Quaker is suggested when Walnut Sphinx is met - suppositions on my part.

I don’t think this is a bug - I think it’s just that the model is not confident when it comes to brown moth pupae like this - it hasn’t been trained on enough of them, or they’re just too difficult to differentiate from each other with a photo. You’ll see the lack of confidence on the website if you try to get suggestions: “We’re not confident enough to make a recommendation”.

For what it’s worth, if I crop closer to the pupa (and still use the same date and location), I see rustic sphinx (Manduca rustica - if that’s the species you’re referring to) as a suggestion. Cropping can help a lot.

I don’t think this is related at all. However, without scientific names we don’t really know which species you’re referring to - the same common name can be associated with multiple taxa.

2 Likes