dlanzo/CRANE
Convolutional Recurrent Approximation of Nanoscale Evolution
This project helps materials scientists and engineers predict how material microstructures evolve over time due to processes like phase separation, which is described by complex partial differential equations (PDEs). It takes in data describing the initial state of a microstructure and outputs predictions of its future states. This tool is for researchers and engineers in materials science who need to simulate microstructure evolution efficiently.
Use this if you need to rapidly simulate the nanoscale evolution of material microstructures, especially for 2D and 3D data, and want to leverage machine learning for faster predictions than traditional PDE solvers.
Not ideal if you require interpretable, first-principles physical models for microstructure evolution or if you lack existing datasets for training the neural network models.
Stars
8
Forks
—
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dlanzo/CRANE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE