kailaix/ADCME.jl

Automatic Differentiation Library for Computational and Mathematical Engineering

48
/ 100
Emerging

This project helps scientists and engineers solve complex inverse modeling problems using gradient-based optimization. You provide observational data and a mathematical model of your system (like a physics simulation), and it outputs the unknown parameters or functions within your model that best explain the observed data. It's designed for researchers and practitioners in fields such as geophysics, fluid dynamics, and solid mechanics.

317 stars. No commits in the last 6 months.

Use this if you need to determine unknown causes or properties of a system from its observed effects, especially in scientific and engineering simulations.

Not ideal if your problem does not involve differential equations, numerical simulations, or requires symbolic differentiation instead of automatic differentiation.

inverse-modeling computational-science numerical-simulation physics-constrained-learning engineering-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

317

Forks

62

Language

Julia

License

MIT

Last pushed

Oct 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kailaix/ADCME.jl"

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