The End-to-End AI for Science Bootcamp provides a step-by-step overview of the fundamentals of deep neural networks, walks attendees through the hands-on experience of building and improving deep learning models using a framework that uses the fundamental laws of physics to model the behavior of complex systems, and enables attendees to visualize the outputs of the trained model. Some notable lab session topics are found via the
event page and include:
- Forecasting weather using Navier-Stokes PDE
- Solving the Darcy-Flow problem using AFNO
- Forecasting weather using FourCastNet
- Modeling Magnetohydrodynamics with Physics Informed Neural Operator
The event will use
Perlmutter GPU nodes at NERSC for the Bootcamp, which are highly similar to Derecho’s architecture. Training accounts for Perlmutter will be provided for non-NERSC users and NSF NCAR users are encouraged to
apply by the deadline of Wednesday, November 12.
