0
$\begingroup$

I am working on a project, where I am trying to predict temperatures of various streets and I have their locations recorded. I was wondering if I could somehow train a model that could incorporate their relative positions and somehow account for it during the temperature predictions. I plan on using a temporal fusion transformer as there will be several variables and I will want to predict multi-step horizons. Does anyone have an idea how this could be achieved? I was thinking maybe graph neural networks, but I'm not sure where exactly they would be incorporated.

Improve this question
$\endgroup$

0

Reset to default

You must log in to answer this question.