| | |
Summary: Object Classification at the Nearby Supernova Factory
S. Bailey,1
, C. Aragon,1
, R. Romano,1,2
, R. C. Thomas,1
, B. A. Weaver1,3
, and D. Wong1
1
Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720
2
Luis W. Alvarez Fellow, National Energy Research Scientific Computing Center, 1 Cyclotron Road, Berkeley, CA 94720
3
University of California, Space Sciences Laboratory, Berkeley, CA 94720
The dates of receipt and acceptance should be inserted later
Key words methods: data analysis -- methods: statistical -- techniques: image processing
We present the results of applying new object classification techniques to the supernova search of the Nearby Supernova
Factory. In comparison to simple threshold cuts, more sophisticated methods such as boosted decision trees, random
forests, and support vector machines provide dramatically better object discrimination: we reduced the number of non-
supernova candidates by a factor of 10 while increasing our supernova identification efficiency. Methods such as these
will be crucial for maintaining a reasonable false positive rate in the automated transient alert pipelines of upcoming large
|
