Using DeepXDE to solve PDE's in a loss function as part of a training loop in tensorflow

[flipflop27]

Apologies if this isn't worded correctly as I am still relatively new to machine learning and the DeepXDE library.
I am trying to formulate a neural network that can estimate pressures and flowrates in a 1D pipeline as a function of time and space. The PDEs that govern transient flow are shown below:

My question is: is it possible to use DeepXDE to compute the PDE's within my existing training loop to try and reduce both F1 and F2 to as close to 0 as possible for every iteration in my training loop. The outputs of the neural network are q_hat and h_hat which are both functions of x and t.

[lululxvi]

Yes. Just learn how to use DeepXDE.