Project

General

Profile

SG separation challenge » History » Version 17

Ignacio Sevilla, 12/09/2013 09:59 AM

1 1 Ignacio Sevilla
h1. SG separation challenge
2 1 Ignacio Sevilla
3 1 Ignacio Sevilla
Now that several people are testing their own approaches:
4 1 Ignacio Sevilla
5 1 Ignacio Sevilla
* Cut-based with DESDM info (Eli, Diego, Nacho, Ryan...).
6 1 Ignacio Sevilla
* Multi-class (Maayane)
7 1 Ignacio Sevilla
* Random Forests (Ryan)
8 1 Ignacio Sevilla
* Boosted Decision Trees (Nacho)
9 1 Ignacio Sevilla
* Alternative Neural Network with probabilistic output (Chris Bonnett).
10 13 Basilio Santiago
* Probability based on spread model and photometry (DES-Brazil)
11 14 Basilio Santiago
* Others...
12 1 Ignacio Sevilla
13 1 Ignacio Sevilla
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.
14 1 Ignacio Sevilla
15 1 Ignacio Sevilla
We have to establish:
16 1 Ignacio Sevilla
17 1 Ignacio Sevilla
* The training/validation/testing sample (COSMOS, others).
18 17 Ignacio Sevilla
I have prepared a 70/30 training/testing with the deep COSMOS field matched to ACS imaging. About 280 parameters, up to each tester to choose which.
19 17 Ignacio Sevilla
Besides new datasets, also consider shallower COSMOS. Also consider fixed set of parameters as Eduardo suggests. Also need to add SLR corrections though I think not very important now.
20 6 Ignacio Sevilla
* Only stars and galaxies? What about QSOs, image artifacts?
21 17 Ignacio Sevilla
Star/galaxy for round 1.
22 3 Ignacio Sevilla
* The metrics (Fixed cut, Fixed purity, Fixed Efficiency, ROC -- see example below).
23 17 Ignacio Sevilla
I would prefer to use ROC, i.e., completeness vs purity curve formed changing the threshold.
24 7 Eli Rykoff
* SVA1 systematics: correlations with depth, Galactic latitude, seeing, etc.
25 4 Ignacio Sevilla
* Who/how to run it.
26 17 Ignacio Sevilla
I suggest each group providing an output file with id (or ra,dec on first round) plus galaxy probability or binary value.
27 8 Ignacio Sevilla
* Is there any gain combining them (a committee)?
28 1 Ignacio Sevilla
* The schedule.
29 9 Maayane Soumagnac
30 9 Maayane Soumagnac
h1. The metric
31 9 Maayane Soumagnac
32 9 Maayane Soumagnac
We suggest to use the same metric as in the DES star/galaxy separation (on simulation) paper (arXiv:1306.5236).
33 9 Maayane Soumagnac
34 10 Maayane Soumagnac
h2. Completeness and Purity provided by a given classifier
35 10 Maayane Soumagnac
36 9 Maayane Soumagnac
We define the parameters used to quantify the quality of a star/galaxy classifier. For a given class of objects, X (stars or galaxies), we distinguish the surface density of well classified ob jects, N_X , and the misclassified objects, M_X .
37 9 Maayane Soumagnac
38 9 Maayane Soumagnac
* The galaxy completeness c^g is defined as the ratio of the number of true galaxies classified as galaxies to the total number of true galaxies. 
39 9 Maayane Soumagnac
* The stellar contamination f_s is defined as the ratio of stars classified as galaxies to the total amount of ob jects classified as galaxies. 
40 9 Maayane Soumagnac
* The purity p^g is defined as 1-f_s
41 9 Maayane Soumagnac
42 11 Maayane Soumagnac
!{width:400px}metric.png! 
43 10 Maayane Soumagnac
44 10 Maayane Soumagnac
h2. Plots
45 10 Maayane Soumagnac
46 10 Maayane Soumagnac
Bellow are three different plots we suggest to use to assess the performances of each classifier.
47 10 Maayane Soumagnac
48 10 Maayane Soumagnac
h3. Histograms
49 10 Maayane Soumagnac
50 10 Maayane Soumagnac
Example, on simulations, from arXiv:1306.5236
51 11 Maayane Soumagnac
!{width:400px}histo.png!
52 10 Maayane Soumagnac
53 10 Maayane Soumagnac
h3. purity as a function of magnitude (for fixed completeness, the threshold/cut is let free)
54 1 Ignacio Sevilla
55 12 Eli Rykoff
!{width:800px}Emma.png!
56 10 Maayane Soumagnac
57 16 Ignacio Sevilla
!{width:400px}sg_separation_purity_vs_magauto_50.0_efficiency.png! !{width:400px}sg_separation_purity_vs_magauto_90.0_efficiency.png! 
58 16 Ignacio Sevilla
59 15 Ignacio Sevilla
h3. completeness as a function of magnitude (for fixed purity, the threshold/cut is let free )
60 15 Ignacio Sevilla
61 15 Ignacio Sevilla
!{width:400px}sg_separation_efficiency_vs_magauto_95.0_purity.png! !{width:400px}sg_separation_efficiency_vs_magauto_99.0_purity.png!