-
We should definitely organize the `examples` directory into subdirectories as this package becomes larger, but I am not sure if it makes sense to do so based on solver/mesh type the way Trixi.jl does.…
-
Dear all,
Thanks a lot for making the code available!
I have been running into some issues with `signature_kernel.compute_Gram()` as the output is not always positive semi-definite and thus I ru…
-
## Issue
Move class `AI4CFD` from script into a source code class. We may want to create a base class for a general class and then have classes inherit from this for each different case (advection di…
-
Hello, Doctor, in the case of the "Helmholtz acoustic hard scattering problem with absorption boundary conditions", the analytical solution was not given and the training result was wrong, why? Is it …
-
Hi,
In the Simulation3DDifferential class for the gravity PDE solver, function getRHS seems to return a sparse matrix (csr_matrix). This causes an error when trying to multiply by the simulation .sol…
-
When running the provided data generation code for 128x128 2D reaction diffusion, I am observing very high PDE residual at the beginning of the trajectory. The lowest that the residual gets is around …
-
# What is modulus?
From its official website, NVIDIA Modulus is `a neural network framework` that blends the power of `physics` (in the form of governing partial differential equations (PDEs)) with…
-
Hi,
I am using a python environment named Firedrake (PDE solver) together with another libraries called pygmsh to implement a dynamical system inside the function **f(x,u)**. When I try to run the…
-
After the pre-alpha development we need to design a suitable tests facilities. The library is aimed to be a general approximation (interpolation) tool thus the range of applications is quite wide. Nev…
-
Hi,
From the code it seems that PINN samples 30% of ground truth data from the solution domain and use them to supervise training. If I understand correctly, the original PINN does not require supe…