Physics
AI and machine learning applications in physics — from physics-informed neural networks to simulation.
Overview
Physics and ML intersect in several key areas:
- Physics-Informed ML — Neural networks that respect physical laws
- Simulation Acceleration — ML surrogate models for simulations
- Quantum ML — ML for quantum systems
- Scientific Discovery — Finding physical laws from data
Quick Start
| Goal | Resource |
|---|---|
| Browse datasets | Datasets |
| Learn foundational ML | Foundations |
| Related: Materials physics | Materials |
Key Areas
Physics-Informed Neural Networks (PINNs)
Incorporating physical constraints (PDEs, conservation laws) into neural networks. See Methods Resources for tools and tutorials.
Simulation Surrogates
ML models that accelerate physics simulations — from CFD to weather prediction. Benchmark datasets available in Datasets.
Symbolic Regression
Discovering equations from data using techniques like genetic programming and neural symbolic regression.
Want to contribute? If you have resources to share for physics-focused AI/ML, we’d love to include them.