SG separation challenge » History » Version 7
SG separation challenge¶
Now that several people are testing their own approaches:
- Cut-based with DESDM info (Eli, Diego, Nacho, Ryan...).
- Multi-class (Maayane)
- Random Forests (Ryan)
- Boosted Decision Trees (Nacho)
- Alternative Neural Network with probabilistic output (Chris Bonnett).
I think the time is right and the codes are mature to launch a specific SG separation challenge, mimicking the successful photo-z WG exercise.
We have to establish:
- The training/validation/testing sample (COSMOS, others).
- Only stars and galaxies? What about QSOs, image artifacts?
- The metrics (Fixed cut, Fixed purity, Fixed Efficiency, ROC -- see example below).
- SVA1 systematics: correlations with depth, Galactic latitude, seeing, etc.
- Who/how to run it.
- The schedule.