Most crayfish species make burrows, the mounds of which are largely similar among all species. In one area of the northeast in Michigan, it has been argued that the only possible species making them is Fallicambarus fodiens, the Digger Crayfish, and many burrow observations in that area have been identified to that species. Since then the computer vision has been trained on these and now throughout much of the united states it suggests that species for any observation of any burrow and most people seem to follow this suggestion. These for the most part have to be continually corrected to the family Cambaridae.
Is there any strategy moving forward that can somehow get computer vision to suggest identification to family rather than species? If we religiously mark that burrow family identifications as “no” in the following: , would that help? I haven’t been doing this.
This seems to be hard for the CV because as far as it can tell the observations could all be that species, and it doesn’t know whether they’re unidentifiable or just not identified yet. If I understand correctly, the only way to prevent it from suggesting that species all the time from burrows would be to get a few burrows of at least one other species identified to species level. Then it will try to compare the photos, hopefully find no differences between them, and suggest the lowest common taxon.
If that’s not possible (which wouldn’t be surprising) then the only thing to do is keep pushing them back and educating observers and identifiers. You might also add it to this wiki to possibly attract attention and get help identifying them.