I started working on a similar project - my approach was to train a model based on all of the geoguessr contest sets.

Geoguessr gives you both the street view _and_ the correct answer when you guess wrong.

They're all hand-curated so there are only so many points that you need to identify (the largest sets are 100k+ points) so the idea would be to run through it thousands of times with wrongs answers but use the correct answer to train the model

It's only a matter of time before the game has cheat bots and that problem, much in the same way online chess has that issue