Im working with spatiotemporal data and I'm wondering if I train my model on a timeseries with a certain timestep, do I need to have the same timestep when I deploy the model and make predictions?
Currently I have data with a timestep of 1 second thats being used to train a CNN-LSTM model, but the data on which itll be used to predict may have a timestep of say 0.5s or 2s. How much can I expect this to affect my results? Would it be worth taking data at different timesteps and adding timestep as a feature to my model?
