I am trying to forecast a dynamic number of steps ahead depends on the user input. I tried to use a for loop but the error is increasing as the number of steps increase. I want to forecast up to 48 time steps only and I used a few LSTM layers along with TensorFlow.
My data is univariate (one column for date and the other for temperature).
Any idea on how can I forecast many steps ahead where they depend on each other without increasing the error?