physicsnemo and physics-driven-ml
About physicsnemo
NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
This framework helps scientists and engineers build, train, and fine-tune AI models that combine real-world data with known physics principles. It takes scientific and engineering data (like point clouds or meshes) and physics equations as input to produce predictive AI models for complex systems. Researchers and domain experts in fields like climate science or computational fluid dynamics would use this to create models that offer real-time predictions.
About physics-driven-ml
nbouziani/physics-driven-ml
Physics-driven machine learning using PyTorch and Firedrake
This project helps researchers and engineers who work with physics-based simulations by generating data and training machine learning models that integrate directly with partial differential equations (PDEs). It takes parameters for physical systems and observed data, then produces trained machine learning models capable of solving inverse problems like inferring material properties. The end-users are computational scientists, physicists, and engineers working on complex simulation and modeling tasks.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work