still trying to make the leaderboard
Browse files
app.py
CHANGED
|
@@ -66,8 +66,33 @@ def gradio_interface() -> gr.Blocks:
|
|
| 66 |
with gr.TabItem("About", elem_id="boundary-benchmark-tab-table"):
|
| 67 |
gr.Markdown(
|
| 68 |
"""
|
| 69 |
-
|
| 70 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
"""
|
| 72 |
)
|
| 73 |
|
|
|
|
| 66 |
with gr.TabItem("About", elem_id="boundary-benchmark-tab-table"):
|
| 67 |
gr.Markdown(
|
| 68 |
"""
|
| 69 |
+
## About This Challenge
|
| 70 |
+
|
| 71 |
+
**Welcome to the ConStellaration Leaderboard**, a community-driven effort to accelerate fusion energy research using machine learning.
|
| 72 |
+
|
| 73 |
+
In collaboration with [Proxima Fusion](https://www.proximafusion.com/), we're inviting the ML and physics communities to optimize plasma configurations for stellarators—a class of fusion reactors that offer steady-state operation and strong stability advantages over tokamaks.
|
| 74 |
+
|
| 75 |
+
This leaderboard tracks submissions to a series of open benchmark tasks focused on:
|
| 76 |
+
|
| 77 |
+
- **Geometrically optimized stellarators**
|
| 78 |
+
- **Simple-to-build quasi-isodynamic (QI) stellarators**
|
| 79 |
+
- **Multi-objective, MHD-stable QI stellarators**
|
| 80 |
+
|
| 81 |
+
Participants are encouraged to build surrogate models, optimize plasma boundaries, and explore differentiable design pipelines that could replace or accelerate slow traditional solvers like VMEC++.
|
| 82 |
+
|
| 83 |
+
### Why It Matters
|
| 84 |
+
|
| 85 |
+
Fusion promises clean, abundant, zero-carbon energy. But designing stellarators is computationally intense and geometrically complex. With open datasets, reference baselines, and your contributions, we can reimagine this process as fast, iterative, and ML-native.
|
| 86 |
+
|
| 87 |
+
### How to Participate
|
| 88 |
+
|
| 89 |
+
- Clone the [ConStellaration dataset](https://huggingface.co/datasets/proxima-fusion/constellaration)
|
| 90 |
+
- Build or train your model on the provided QI equilibria
|
| 91 |
+
- Submit your predicted boundaries and results here to benchmark against others
|
| 92 |
+
- Join the discussion and help expand the frontier of fusion optimization
|
| 93 |
+
|
| 94 |
+
Let's bring fusion down to Earth—together.
|
| 95 |
+
|
| 96 |
"""
|
| 97 |
)
|
| 98 |
|