AI4Science-WestlakeU/le-pde-uq

[AAAI24] LE-PDE-UQ endows deep learning-based surrogate models with robust and efficient uncertainty quantification capabilities for both forward and inverse problems.

31
/ 100
Emerging

This project helps scientists and engineers accurately quantify the uncertainty in their simulations involving physical systems, especially for long-term predictions. It takes in existing deep learning models trained on physical data governed by Partial Differential Equations (PDEs) and outputs a more reliable simulation with quantified uncertainty. This is useful for researchers in fields like physics, engineering, and climate science who rely on predictive models.

No commits in the last 6 months.

Use this if you need to understand the reliability of your deep learning-based physical simulations, particularly for complex systems or long-term forecasting where uncertainty accumulates.

Not ideal if your primary goal is to simply speed up PDE solving without needing a rigorous measure of prediction uncertainty.

physical-modeling scientific-computing predictive-simulation uncertainty-analysis numerical-methods
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AI4Science-WestlakeU/le-pde-uq"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.