Satellite-Based Plasma Reconstruction Toolkit using PINNs (Grad–Shafranov & MHS)

This repository provides a computational toolkit for satellite-based plasma equilibrium reconstruction using Physics-Informed Neural Networks (PINNs). The toolkit is designed to load pretrained models, generate predictions across training epochs, and visualize reconstructed Grad–Shafranov and magneto-hydrostatic equilibria. It serves as a post-processing and analysis framework for reproducing and analyzing the results presented in the paper “Physics-Informed Neural Networks (PINNs) for Satellite Trajectory-Based Reconstruction: Applications to Grad–Shafranov and Magneto-Hydrostatic Equilibria”.