I've been working on solving Poisson problem using CNN model (you can ignore Poisson problem part if you not familiar and jump to image processing/CNN part). More specific, I am solving electric potential problem ($\phi$) by CNN algorithm with particle distribution ($\rho$) as the input in cartesian coordinate, similar to Study on a Fast Solver for Poisson’s Equation Based On Deep Learning Technique (PDF), but with no permitivity.

The training input ($\rho$) is 20x20 pixels matrix and the data label ($\phi$) is also 20x20 matrix. Either input and label is contain of 5000 matrix (5000, 20, 20, 1). The input-label data set was obtained from Gauss-Seidel method.

The goal is to obtain electric potential ($\phi$) from input data particle distribution (\rho) with CNN model.

With this regression case, how the best CNN architecture to use?

  • $\begingroup$ Could you please review my answer? Mark it if it fits. Thank You. $\endgroup$
    – Royi
    Jun 17, 2023 at 8:48

1 Answer 1


Currently, the classic architecture for pixel level regression over 2D / 3D / 4D data is U-Net and its extensions.

They are simple to implement. See Image Segmentation Using Deep Learning for a reference MATLAB code.

Since you solve basically a differential equation I'd actually go another path.
Look at the work ML-Assisted Tooling for Model Acceleration in Julia's SciML.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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