The Dark Energy Survey (DES) is using four probes to investigate the dynamics of the expansion of the Universe. The DES Supernova Program (DES-SN) is observing 27 square degrees with a 6-day cadence to obtain a large sample of type Ia supernovae for cosmology. In collaboration with DES, OzDES is using the AAT to obtain redshifts and classifications for objects in the DES fields. While probing dark energy using type Ia supernovae is the prime aim of the supernova survey, the observing strategy enables us to conduct a number of other investigations, such as AGN reverberation mapping and galaxy properties.

 

In this talk, I will present the DES supernova survey and the preliminary cosmological parameter constraints from the first 3-years of the DES-SN survey and the first results of OzDES. I will also discuss about the future analysis with the DES 5-year supernova sample. In particular, I will discuss a photometric classification method based on recurrent neural networks that can classify quickly large number of supernovae with high accuracy using only photometric measurements and time as input. This method includes a bayesian interpretation of classification probabilities which will be fundamental for a cosmology analysis.