Sample Dataset and Trained Model Parameters for Back-Projection Diffusion

We have uploaded a sample dataset for training and testing Back-Projection Diffusion. Trained model parameters for the dataset are also provided in tmp.zip.

For a formal description of the dataset, please refer to our paper:

Zhang, B., Guerra, M., Li, Q., & Zepeda-Núñez, L. (2025). Back-Projection Diffusion: Solving the wideband inverse scattering problem with diffusion models. Computer Methods in Applied Mechanics and Engineering, 443, 118036. https://doi.org/10.1016/j.cma.2025.118036

In 10hsquares_trainingdata and 10hsquares_testdata, perturbations are stored as eta.h5 with the following structure:

eta.h5/
      ├── /eta

The scattering data are stored as scatter.h5, or as scatter_order_n.h5 (n indicates the order of the stencil used for data generation) with the following structure:

scatter.h5/
      ├── /scatter_imag_freq_1
      ├── /scatter_real_freq_1
      ├── /scatter_imag_freq_2
      ├── /scatter_real_freq_2
      ├── /scatter_imag_freq_3
      ├── /scatter_real_freq_3

The tmp folder contains the trained model parameters.

For usage instructions, please refer to our GitHub repository:

https://github.com/borongzhang/back_projection_diffusion

If this dataset is useful to your research, please cite our paper:
@article{ZHANG2025118036,
title = {Back-Projection Diffusion: Solving the wideband inverse scattering problem with diffusion models},
journal = {Computer Methods in Applied Mechanics and Engineering},
volume = {443},
pages = {118036},
year = {2025},
issn = {0045-7825},
doi = {https://doi.org/10.1016/j.cma.2025.118036},
url = {https://www.sciencedirect.com/science/article/pii/S0045782525003081},
author = {Borong Zhang and Martin Guerra and Qin Li and Leonardo Zepeda-Núñez},
keywords = {Machine learning, Inverse scattering, Generative modeling, Wave propagation, Diffusion models}
}