NERSC, in collaboration with NVIDIA and the OpenACC organization, will host an End-to-End AI for Science bootcamp on December 10 - 11, 2025.
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.
We will be using Perlmutter GPUs for the Bootcamp. This event has limited capacity, so please apply early. Training accounts for Perlmutter will be provided for non-NERSC users.
Prerequisites
- Proficient in Python programming
- Understanding of AI applied to CFD and numerical modeling
Apply to Attend
For detailed information on how to apply, please refer to the Open Hackathons' Bootcamp Events page. The application deadline is November 12, 2025. This event has limited capacity, please apply early and note that acceptance is not confirmed until you have received a confirmation email.
Agenda
Day 0: December 9
| Time | Topic |
|---|---|
| 10 - 11 a.m. | Cluster Dry Run |
Day 1: December 10
| Time | Topic |
|---|---|
| 9 - 9:15 a.m. | Welcome |
| 9:15 - 9:30 a.m. | Connecting to a cluster |
| 9:30 - 10 a.m. | Introduction to NVIDIA Modulus and Physics-Informed approach to an AI for Scientific application |
| 10 - 10:10 a.m. | Break |
| 10:10 - 10:30 a.m. | Quick Overview on Lab 1 and 2 |
| 10:30 - 12 p.m. | Physics-Informed approach to an AI for Scientific application |
| Lab 1: Simulating Projectile Motion | |
| Lab 2: Steady State Diffusion in a Composite Bar using PINNs | |
| Lab 3: Forecasting weather using Navier-Stokes PDE |
Day 2: December 11
| Time | Topic |
|---|---|
| 8:30 - 10:30 a.m. | Data-driven approach to an AI for Scientific application. |
| Lab 1 : Solving the Darcy-Flow problem using FNO | |
| Lab 2: Solving the Darcy-Flow problem using AFNO | |
| Lab 3: Forecasting weather using FourCastNet | |
| Lab 4: Modeling Magnetohydrodynamics with Physics Informed Neural Operator | |
| 10:30 - 10:45 a.m. | Break |
| 10:45 - 11:30 a.m. | Data-driven approach using Modulus Core |
| Lab 1: Training Physics-ML Models using Modulus Core | |
| Lab 2 : Training Weather forecasting Models using Modulus Core | |
| 11:30 - 12:15 p.m. | Project Discussion |
| 12:15 - 12:30 p.m. | Wrap up and Q&A |