How to approach a spatio-temporal forecasting?

I am dealing with a Spatio-temporal forecasting problem similar to the one dealing with the NYC Taxi Demand Prediction. This case is a good example since it has been already covered in different papers using different models and techniques.

The most recent I read were this one (GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction) were they trying to predict the taxi demand using a GSTN model as well as this one ( Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction) were they combined a CNN for the spatial aspect of the problem and a LSTM for the time problem. Both papers describing the process and achieved stunning results.

However due to the wide range of information available I am overwhelmed in which model I should choose. A simple GNN seems to have to much focus on space instead of time. Which model would you choose?