A navigation hub for Physical AI and Scientific Machine Learning: systematically indexing five resource families — datasets & benchmarks, tools & frameworks, industrial cases, learning paths and papers & surveys — alongside original in-depth guides, company research reports, a glossary, a weekly arXiv digest and a knowledge graph. Bilingual search and community submissions supported.
A beginner-friendly PINN library with thorough Chinese docs and TensorFlow/PyTorch/JAX/PaddlePaddle backends - a common starting point for scientific machine learning and PDE solving.
NewGNU Lesser General Public License v2.1PINNBeginnerChinese Docs
Open-source CFD solver as a physics-AI data backbone: principles, case structure, getting started, alternatives, cost accounting and failure boundaries.
NVIDIA's physics-ML framework (formerly Modulus, renamed in 2025), a PyTorch-based library for PINN, neural operators and physics-constrained training - architecture, versions, comparisons and failure boundaries.
A graph-neural-network medium-range weather forecasting model from Google DeepMind that outperforms the ECMWF operational deterministic system on 90 percent of 1380 verification targets and completes a 10-day global forecast in under a minute on a single accelerator, with code and weights now consolidated in the WeatherNext repository.
NewPaper is copyright of Science; code and notebooks are Apache-2.0, model weights permit commercial use since 2026-08-06, other materials are CC BY 4.0WeatherGraph Neural NetworkMedium-Range Forecasting
An open-source equivariant graph-neural-network potential framework from the Csanyi group that unifies atomic cluster expansion with high-order equivariant message passing, reaching high accuracy with only two interaction layers, and now shipping several generations of foundation weights (MACE-MP, MH, OMOL, POLAR) for out-of-the-box molecular dynamics of crystals, liquids, gases, surfaces and reactive systems.
NewMIT (code); some weights are released under the Academic Software License (ASL) for academic use onlyMolecular DynamicsMachine-Learned PotentialEquivariant Neural Network
A free online textbook from TU Munich covering physics + deep learning: differentiable physics, PINNs, neural operators and turbulence modeling, with runnable code.
Presents a branch-trunk architecture realizing a deep learning version of the universal operator approximation theorem - the first systematic architecture for learning nonlinear operators and still a mainstream baseline.
arXiv preprint (copyright held by authors)DeepONetNeural OperatorFoundational
DeepCAD reframes CAD modeling as a sequence-generation problem, learns a latent space with an autoencoder and trains a latent GAN (WGAN-GP) for random generation and editing. It is the most-cited baseline in generative CAD and sits upstream of the design-to-simulation pipeline.
NewMIT LicenseGenerative CADGeometric Deep LearningCAD Sequence
Open-source FEM-based multiphysics framework; describes variational problems in UFL and auto-generates efficient C++ discretization code - a standard academic tool for solids and coupled physics, also a high-fidelity reference for surrogates.
Google Research's differentiable incompressible-flow solver in JAX; the whole time-stepping loop is differentiable and JIT-compilable on GPU/TPU. A PNAS 2021 learned-interpolation result reached ~80x/40x speedups at equal accuracy, but the project is now unmaintained - treat it as a research prototype and reference.
Fully auto-differentiable CFD solver built on JAX for CPU/GPU/TPU, focused on end-to-end differentiable fluid simulation that couples seamlessly with neural networks.
NewGNU General Public License v3.0JAXDifferentiable CFDDifferentiable Physics
CADFit uses IoU-driven hybrid optimization to incrementally fit and validate executable CadQuery construction programs (extrude, revolve, fillet, chamfer, Boolean) from watertight meshes, recovering editable parametric CAD. It is modality-agnostic (mesh, point cloud, image-to-3D) and directly relevant to CAE workflows.
NewCC BY-NC 4.0 (non-commercial; academic and research use only, commercial use requires author permission)Mesh-to-CADReverse EngineeringCadQuery
Google's open-source NumPy-style numerical computing library built on XLA with autodiff and functional transformations (grad/jit/vmap/pmap) - the substrate behind differentiable solvers and neural operators.
An open-source physics engine maintained by Google DeepMind, pairing generalised coordinates with soft convex contact dynamics for robotics, biomechanics and reinforcement learning, with MJCF, MJX, MuJoCo Warp and the 4.0 release.
NewApache-2.0 for source code; CC BY 4.0 for documentation, images and videos in the doc directoryPhysics EngineContact DynamicsRobot Simulation
Open-source CFD solver as a physics-AI data backbone: principles, case structure, getting started, alternatives, cost accounting and failure boundaries.
ETH Zurich CAM lab's PDE foundation model and downstream fine-tuning suite, using semigroup augmentation to mine abundant training pairs and cover 15 downstream tasks with mesh-invariant inference.
NewNo LICENSE file in the repository; the official model weights are labelled CC BY-NC 4.0 on HuggingFace and marked as research modelsFoundation ModelNeural OperatorDownstream Tasks
Python 3D visualization and mesh-processing framework wrapping VTK; a concise API for field data, mesh rendering and animation. The de-facto standard for simulation post-processing, ML dataset construction and QA, used as the output layer by FEniCSx / PyMAPDL.
Open-source CFD and discrete-adjoint solver with built-in aerodynamic shape optimization; PDE-constrained gradients at a cost independent of design-variable count, a high-fidelity reference for surrogates.
NewGNU Lesser General Public License v2.1CFDAdjointShape Optimization