Machine learning techniques for analysis of photometric data from the Open Supernova catalog

International audienceThe next generation of astronomical surveys will revolutionize our understandingof the Universe, raising unprecedented data challenges in the process. One ofthem is the impossibility to rely on human scanning for the identification ofunusual/unpredicted astrophysical objects. Moreover, given that most of theavailable data will be in the form of photometric observations, suchcharacterization cannot rely on the existence of high resolution spectroscopicobservations. The goal of this project is to detect the anomalies in the OpenSupernova Catalog (http://sne.space/) with use of machine learning. We willdevelop a pipeline where human expertise and modern machine learning techniquescan complement each other. Using supernovae as a case study, our proposal isdivided in two parts: the first developing a strategy and pipeline whereanomalous objects are identified, and a second phase where such anomalousobjects submitted to careful individual analysis. The strategy requires aninitial data set for which spectroscopic is available for training purposes, butcan be applied to a much larger data set for which we only have photometricobservations. This project represents an effective strategy to guarantee weshall not overlook exciting new science hidden in the data we fought so hard toacquire