physics-informed-ml

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

Code accompanying my blog post: So, what is a physics-informed neural network?

[NeurIPS 2024] Codebase for PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs.

A Physics-Informed Neural Network to solve 2D steady-state heat equations.

Introductory workshop on PINNs using the harmonic oscillator

Applications of PINOs

No need to train, he's a smooth operator

[PNAS 2025] Code of "Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design".

Learning function operators with neural networks.

Tutorials for doing scientific machine learning (SciML) and high-performance differential equation solving with open source software.

This repo contains the code for solving Poisson Equation using Physics Informed Neural Networks

Repository for NeurIPS 2025 paper, "Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers."

[ICML 2025] A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems

Empirical quantum simulation experiments and robustness studies on Dense Evolution: Ising phase transitions, VQE, error mitigation, and a critical replication study of the traversable-wormhole

Margam is Physics-informed neural network (PINN) library.

Supporting code for "reduced order modeling using advection-aware autoencoders"

🛰️ Production-ready ML system for geomagnetic storm prediction | 98% AUC, 70% recall | Threshold-optimized ensemble with real-time inference | 29-year dataset (1996-2025) | NOAA SWPC operational standards | Complete MLOps pipeline

Going through the tutorial on Physics-informed Neural Networks: https://github.com/madagra/basic-pinn

Physics-Constrained Fine-Tuning (PCFT) for flow-matching generative models, with code for PDE-constrained generation and inverse problems from the ICLR 2026 paper.

Physics Informed Neural Networks - research in problem solving, architecture improvements, new applications