I have traffic jam intensity of many location in different times of eabch day. So I have kind of 3D data, where the intensities in each location is 2D like an image. Then there is time as a third dimension.

Now, I want to predict traffic jam intensity at a give location and time. The intensity is from 0.0 to 10.0. high the intensity means high traffic jam.

Example. Whats the jam intensity of X latitude and Y longitude on 3:45 PM?

My question is how to feed that 3D data to my neural network?

NB: both the time and location contextual data. The intensity of the traffic jam is behavioral.

  • 1
    $\begingroup$ Any chance of seeing one or two of these traffic intensity maps? $\endgroup$
    – Spacedman
    Apr 20, 2016 at 19:06

1 Answer 1


One approach would be to use a Convolutional Neural Network (CNN) since they are good at finding spatial patterns. You'll have to define a tensor for input (latitude, longitude, time, intensity).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.