The source code and data for the article J. Hayford, J. Goldman-Wetzler, E. Wang & L. Lu. Speeding up and reducing memory usage for scientific machine learning via mixed precision. Computer Methods in Applied Mechanics and Engineering, Volume 428, 2024, 117093, ISSN 0045-7825, https://doi.org/10.1016/j.cma.2024.117093.

The dataset used for solving the problems associated with this paper. Some of the datasets are available on this repository. Others are available on google drive through the attached link.

• Advection equation
• Linear Instability wave equation Refer to the original paper for this dataset:
  URL: https://www.sciencedirect.com/science/article/pii/S0021999122008567

• Inverse problem of flow in a rectangular domain
• Inverse problem of hemodynamics

The code used for generating results in the paper.

• Loss landscape and gradient analysis
• Burgers equation
• Inverse Navier-Stokes
• Kovasznay flow
• Hemodynamics
• POD DeepONet
• Physics-informed DeepONet

If you use this data or code for academic research, you are encouraged to cite the following paper:

@article{HAYFORD2024117093,
author = {Joel Hayford and Jacob Goldman-Wetzler and Eric Wang and Lu Lu},
title = {Speeding up and reducing memory usage for scientific machine learning via mixed precision},
journal = {Computer Methods in Applied Mechanics and Engineering},
volume = {428},
pages = {117093},
year = {2024},
doi = {https://doi.org/10.1016/j.cma.2024.117093},

To get help on how to use the data or code, simply open an issue in the GitHub "Issues" section.