The Finding Luminous and Exotic Extragalactic Transients (FLEET) pipeline is a machine learning pipeline designed to predict the probability, P(SLSN), of any new transient being a SLSN. FLEET uses a random forest algorithm trained on every classified transient from the TNS to derive a P(SLSN) value. The features used to separate SLSNe from other transients include light curve information, as well as contextual (host galaxy) information. We find that maximum classification accuracy can be achieved for transients with P(SLSN) > 0.8, where we expect ~85% of them to be SLSNe; for events with P(SLSN) > 0.5 we expect ~50% of them to be SLSNe. FLEET is described in detail in Gomez et al. 2020 (ApJ in press; arXiv:2009.01853).
Here we present the first results from FLEET. We used the pipeline to generate a list of SLSN candidates, and obtained optical spectroscopy of six SLSN candidates using the MMT 6.5-m telescope. We classified the spectra using template matching with SNID (Blondin & Tonry, 2007, ApJ, 666, 1024). We find the classifications to be in agreement with the predictions from our random forest classifier: The 2 objects with P(SLSN) > 0.8 are both classified as SLSNe, and 4 of the 6 of objects with P(SLSN) > 0.5 are classified as SLSNe.
Gomez, S. Berger, E., Blanchard, P. K., et al. FLEET: A Redshift-Agnostic Machine Learning Pipeline to Rapidly Identify Hydrogen-Poor Superluminous Supernovae. 2020, Accepted to ApJ. https://ui.adsabs.harvard.edu/abs/2020arXiv200901853G
Catalog | Name | Reported RA | Reported DEC | Reported Obj-Type | Reported Redshift | Host Name | Host Redshift | P(SLSN) | Obs. Date | Peak abs. mag. | Remarks | TNS RA | TNS DEC | TNS Obj-Type | TNS Redshift |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
TNS | 2020jii | 15:34:55.291 | +02:51:11.66 | SLSN-I | 0.396 | 0.91 | 2020-07-15 | -22.2 | 15:34:55.291 | +02:51:11.66 | SLSN-I | 0.396 | |||
TNS | 2020myh | 23:37:30.549 | +21:42:42.81 | SLSN-I | 0.283 | 0.81 | 2020-09-15 | -21.5 | 23:37:30.549 | +21:42:42.81 | SLSN-I | 0.283 | |||
TNS | 2020hvw | 17:58:29.929 | +23:56:21.27 | SN II | 0.093 | 0.70 | 2020-09-17 | -19.1 | 17:58:29.929 | +23:56:21.27 | SN II | 0.093 | |||
TNS | 2020mad | 14:15:52.740 | +05:26:35.63 | SLSN-II | 0.123 | 0.66 | 2020-07-19 | -20.1 | 14:15:52.740 | +05:26:35.63 | SLSN-II | 0.123 | |||
TNS | 2020oqy | 20:37:45.829 | +69:55:08.52 | SN Ia | 0.135 | 0.64 | 2020-08-19 | -19.3 | 20:37:45.829 | +69:55:08.52 | SN Ia | 0.135 | |||
TNS | 2020onb | 14:23:00.600 | +49:10:40.69 | SLSN-I | 0.153 | 0.49 | 2020-07-17 | -20.1 | 14:23:00.600 | +49:10:40.69 | SLSN-I | 0.153 |