CASUS Institute Seminar, Karan Shah, PhD candidate, Center for Advanced Systems Understanding CASUS, Helmholtz-Zentrum Dresden-Rossendorf (HZDR)
Abstract of the talk// Time-dependent density functional theory (TDDFT) is an important method for simulating dynamical processes in quantum many-body systems. Karan and his colleagues are investigating the feasibility of physics-informed neural networks (PINNs) as a replacement for TDDFT. The team examines the computational efficiency and convergence behavior of of these solvers to state-of-the-art numerical techniques on toy systems. The method developed has the potential to accelerate the TDDFT workflow, enabling the simulation of large-scale calculations of electron dynamics in matter exposed to strong electromagnetic fields, high temperatures, and pressures.
In the first part of the talk, Karan will introduce PINNs as a type of partial differential equation (PDE) solver that incorporates PDE constraints as optimization targets for neural networks. He will discuss their advantages, such as the fact that they are mesh-free and generalizable, as well as their limitations compared to numerical methods. Secondly, Karan will demonstrate the usefulness of PINNs by presenting a proof-of-concept workflow for solving the non-relativistic time-dependent Schrödinger equation.
Karan will be talking live in Görlitz. However, as the event is organized in a hybrid format that includes a videoconferencing tool by Zoom Inc., people interested in the topic have the chance to also join the talk remotely. Please ask for the login details via contact@casus.science.