tomoleary/dino

Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning

31
/ 100
Emerging

This project helps scientists and engineers quickly understand how complex systems behave when parameters change, especially when dealing with many variables. It takes in descriptions of physical models and system parameters, then rapidly predicts how changes in these parameters will affect the system's derivatives or sensitivities. Researchers and practitioners in fields like computational physics or engineering design would use this to accelerate analysis and optimization.

No commits in the last 6 months.

Use this if you need to efficiently calculate and understand the impact of numerous input variables on the behavior of complex physical systems described by partial differential equations.

Not ideal if your problem does not involve high-dimensional parametric analysis of systems or if you primarily need to solve basic forward/inverse problems without a focus on derivative information.

computational-physics engineering-design parametric-analysis uncertainty-quantification numerical-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

18

Forks

2

Language

Python

License

LGPL-2.1

Last pushed

Jan 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tomoleary/dino"

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