I work at the intersection of physics and artificial intelligence, developing advanced computational frameworks that combine high-fidelity numerical solvers with modern machine learning.

⚡ Bridging first-principles physics and artificial intelligence for next-generation electromagnetic systems.

⚙️ AI for Electromagnetics: PINNs · Neural Operators · Inverse Modeling
📡 Computational Electromagnetics: FEM · FDTD · BEM · Multiphysics
⚡ Lightning & Power Systems: Localization · Induced Overvoltages
🧬 Bioelectromagnetics: TMS · SAR · Hyperthermia
🚀 High-Performance Computing: CUDA · GPU Acceleration · Parallel Solvers

💻 Languages: Python · MATLAB · C++
🤖 Machine Learning: TensorFlow · PyTorch · JAX
📊 Scientific Computing: NumPy · SciPy · CUDA
🧲 EM Software: ANSYS Maxwell · CST Studio · SimNIBS · Onelab
🐧 Environment: Linux · Git

Design of physics-consistent neural architectures (PINNs) for forward and inverse electromagnetic field problems, including nonlinear and time-domain systems.
🔗 Best Paper: A STacked Adaptive Residual PINN (STAR-PINN) Approach to 2D Time-Domain Magnetic Diffusion, IEEE Access, 2025, Link

Integration of classical numerical solvers (BEM, FEM) with neural networks to accelerate and stabilize electromagnetic simulations.
🔗 Best Paper: A Novel Hybrid Boundary Element–Physics Informed Neural Network Method, IEEE Access, 2024, Link

Development of deep learning frameworks for lightning location, peak current estimation, and induced overvoltage prediction in electrical networks.
🔗 Best Paper: A Deep Learning Based Lightning Location System, Electric Power Systems Research, 2025, Link

Computational modeling of electromagnetic interactions in biological systems, including transcranial magnetic stimulation (TMS) and SAR prediction in biomedical applications.
🔗 Best Paper: A Deep Learning Based Prediction of Specific Absorption Rate Hot-Spots, IET Science, Measurement & Technology, 2025, Link

GPU-accelerated FDTD solvers for electromagnetic wave propagation and plasma modeling.
🔗 Best Paper: Application of GPU-Accelerated FDTD Method to Electromagnetic Wave Propagation in Plasma, Link

📧 Email: dodgeshayan@gmail.com, shayan.dodge@ing.unipi.it
🆔 ORCID: 0000-0002-8323-2290
🔗 Linkedin: linkedin.com/in/shayan-dodge-441453204
🎓 Google Scholar: Google Scholar/Shayan Dodge

1. A Comparison of Machine Learning and Classical Numerical Approaches for the Resolution of Electromagnetics Problems
   IET Science, Measurement & Technology, 2025.
   DOI: https://doi.org/10.1049/smt2.70034

2. Weak Formulation for Physics-Informed Neural Networks in the Resolution of Analysis Problems in Electromagnetics
   IEEE Transactions on Magnetics, 2025.
   DOI: 10.1109/TMAG.2025.3626152

3. Unilateral EMG-Guided Botulinum Toxin for Retrograde Cricopharyngeus Dysfunction
   Toxins, 2025.
   DOI: https://doi.org/10.3390/toxins17090458

4. Relating Transmission Line Overvoltages and Lightning Location: A Machine Learning–Based Procedure
   COMPEL, 2025.
   DOI: https://doi.org/10.1108/COMPEL-12-2024-0521

5. A STacked Adaptive Residual PINN (STAR-PINN) Approach to 2D Time-Domain Magnetic Diffusion in Nonlinear Materials
   IEEE Access, 2025.
   DOI: 10.1109/ACCESS.2025.3597869

6. A Deep Learning Based Prediction of Specific Absorption Rate Hot-Spots Induced by Broadband Electromagnetic Devices
   IET Science, Measurement & Technology, 2025.
   DOI: https://doi.org/10.1049/smt2.70009

7. A Deep Learning Based Lightning Location System
   Electric Power Systems Research, 2025.
   https://doi.org/10.1016/j.epsr.2025.111437

8. Preliminary Breakdown Pulses (PBP): A Review on Available Data and Models
   Electric Power Systems Research, 2025.
   DOI: https://doi.org/10.1016/j.epsr.2025.111463

9. A Novel Hybrid Boundary Element–Physics Informed Neural Network Method for Numerical Solutions in Electromagnetics
   IEEE Access, 2024.
   DOI: 10.1109/ACCESS.2024.3500039

10. Characterization of Microwave Heating for Hyperthermia Cancer Treatment
    Waves in Random and Complex Media, 2024.
    DOI: https://doi.org/10.1080/17455030.2021.1905911

11. Application of GPU-Accelerated FDTD Method to Electromagnetic Wave Propagation in Plasma
    arXiv, 2022.
    https://arxiv.org/abs/2211.05647