Speakers:
Eleftherios Christofi, PhD Student, CyI
Dr. Andreas Demou, Computational Scientist, CyI


The introduction of physical insight into AI workflows for scientific and engineering applications enhances predictive accuracy and generalizability, thereby improving model reliability and enabling more realistic solutions. In recent years, many neural network frameworks have emerged, aiming to enforce underlying physics through different approaches, such as neural operators (NOs) and physics-informed neural networks (PINNs), among others. This training event aims to provide an overview of these various approaches, along with hands-on exercises, applying Physics informed Machine Learning methodologies to different fields of research, including molecular dynamics, microfluidics, and weather forecasting.