Hello to all who have stopped to read my question,

I happen to be working with a neural network for oxygen time series regression (TensorFlow and Keras), I have oxygen, saturation, temperature and salinity data every 5 minutes from 2023-08-25 00:02:12 to 2024-06-18 15:38:36.

My question is, once my neural network has been trained and validated…. How can I use it to predict values beyond the data set I have? How should I do it if I want my network to forecast the next 24, 48 or 72 hours, if they are not present in my validation dataset?

I have already divided my data into the training and test set, and I have made the predictions for the test set, but I always need to have a “past data set”. Now I want to try to predict the steps t+24, t+48, but I don’t know how to proceed.