Skip to content

Added GSOC project #207

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bigfooted merged 1 commit into from
Jan 28, 2026
Merged

Added GSOC project #207

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions _gsoc/Introduction.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,3 +43,13 @@ Expected Outcome (deliverables): Performance profiling report, custom complex ar
- Expected Project Size (90 hrs/ small , 175 hrs/medium, 350 hrs/large): 175 hrs (medium)
- Difficulty rating: **medium**

## Project PIML: Towards physics-informed machine learning with SU2
Project Description (max. 5 Sentences)
SU2 uses algorithmic differentiation (AD) for the adjoint solver and has the ability to use multi-layer perceptrons in data-driven equation of state models through the [MLPCpp](https://github.com/EvertBunschoten/MLPCpp.git) submodule. The aim of this project is to combine these two functionalities to enable physics-informed machine learning (PIML) in SU2 by updating the weights and biases of multi-layer perceptrons using AD for sensitivity calculation. PIML would enable data-driven turbulence modeling, solving partial differential equations without a mesh, and open the door to many other interesting research opportunities.
Expected Outcome (deliverables): Demonstration of training a MLP for a reference data set within SU2 and comparison, MLP training library including at least one commonly used training algorithm (e.g. Adam), and documentation explaining usage.
- Skills Required: C++, experience with machine learning
- Possible Mentors: Evert Bunschoten (lead)
- Expected Project Size (90 hrs/ small , 175 hrs/medium, 350 hrs/large): 175 hrs (medium)
- Difficulty rating: **medium-hard**