How do I consider temporal and spatial features together in a simple convolutional network?

Hello. Good morning. According to the Matlab code I wrote, I want to add the time channel as another channel to the features. But finally, the size of the X dimensions of the input of the convolutional network is equal to 884356x72x2 double and the size of the input egregor is equal to 1x884356 categorical. I get an error when running the network. Number of observations in X and Y disagree. How should I consider time? I want to consider spatial and temporal features together. Thank you.

[Matt J]

Please attach the layer array in a .mat file so that it can be analyzed.

[NGR MNFD]

Hello, yes, I sent it to you. But I couldn't send it as a .mat file because its size is more than 5 GB.