We are pleased to announce the public release of STAR-PINN v1.0.0, an open-source implementation of the Stacked Adaptive Residual Physics-Informed Neural Network framework for solving magnetic diffusion problems.

Core Concept

Instead of relying on a single monolithic PINN, STAR-PINN progressively refines the solution through a sequence of residual-learning PINNs:

• PINN₀ learns the initial physical solution
• Additional PINNs learn residual corrections
• Adaptive mixing progressively refines predictions
• Each stage improves accuracy, stability, and physical consistency

This approach treats learning as an iterative physics-aware refinement process, enabling more accurate solutions for challenging electromagnetic diffusion problems.

Related Publication

This repository accompanies our paper:

Dodge et al., “STAR-PINN: Stacked Adaptive Residual Physics-Informed Neural Networks for Magnetic Diffusion Problems”, IEEE Access, 2026. [Link]

Repository Features

• Physics-informed deep learning framework
• Residual-based stacked PINN architecture
• Adaptive network weighting strategy
• Magnetic diffusion benchmarks
• Reproducible training and evaluation scripts
• Open-source implementation for research and education

We hope this repository will be useful for researchers and engineers working in Scientific Machine Learning, Computational Physics, and Computational Electromagnetics.

Contributions, suggestions, and feedback are always welcome.

We are pleased to announce the release of the GitHub repository for Version v1.0.0 of the Hybrid BEM-PINN project.

💡 What makes this approach interesting?

It’s based on a 𝗱𝗼𝗺𝗮𝗶𝗻 𝗱𝗲𝗰𝗼𝗺𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻 𝘀𝘁𝗿𝗮𝘁𝗲𝗴𝘆:

Instead of choosing between:

• traditional numerical methods
• or neural networks

We combine both — each where it works best:

🔵 Physics-Informed Neural Networks (𝗣𝗜𝗡𝗡) → learn the solution in the most relevant regions of the domain

🔴 Boundary Element Method (𝗕𝗘𝗠) → focuses on boundary interactions, avoiding full-domain computation in less critical regions

This implementation reproduces and extends the methodology presented in:

Barmada, Dodge et al., A Novel Hybrid Boundary Element—Physics Informed Neural Network Method for Numerical Solutions in Electromagnetics, IEEE ACCESS, 2024. [Link]

🔜 More advanced versions (complex geometries, improved coupling) are coming soon.

We are pleased to announce the release of the GitHub repository for Version v1.0.0 of the FELINES project.

This version focuss on:

• Lightning strike geolocation (x, y estimation)
• Channel-base peak current regression
• Deep learning–based modeling of lightning-induced voltages on overhead transmission lines
• Induced Voltage Waveforms → {Strike Location (x, y), Peak Current}

This implementation reproduces and extends the methodology presented in:

𝘋𝘰𝘥𝘨𝘦 𝘦𝘵 𝘢𝘭., 𝘈 𝘥𝘦𝘦𝘱 𝘭𝘦𝘢𝘳𝘯𝘪𝘯𝘨 𝘣𝘢𝘴𝘦𝘥 𝘭𝘪𝘨𝘩𝘵𝘯𝘪𝘯𝘨 𝘭𝘰𝘤𝘢𝘵𝘪𝘰𝘯 𝘴𝘺𝘴𝘵𝘦𝘮, 𝘌𝘭𝘦𝘤𝘵𝘳𝘪𝘤 𝘗𝘰𝘸𝘦𝘳 𝘚𝘺𝘴𝘵𝘦𝘮𝘴 𝘙𝘦𝘴𝘦𝘢𝘳𝘤𝘩, 2025. [Link]

🔜 𝘝𝘦𝘳𝘴𝘪𝘰𝘯 𝘷2.0.0 will be released soon, expanding the project toward early-stage classification and protection-oriented applications.