Orateur
Description
In the upcoming LSST survey, transient detection—including events like Type Ia supernovae (SNe Ia)—will be conducted through Difference Image Analysis (DIA). A major challenge in this method is that many detections are actually "bogus", arising from noise, artifacts, imperfect image subtraction, cosmic rays, bad pixels, or atmospheric effects. Currently, distinguishing real transients from bogus detections involves a combination of physical flags generated by algorithms and manual human inspection.
In this talk, we introduce a machine learning-based approach for classifying bogus and transient events using unlabelled datasets. By injecting synthetic transients into the data, we eliminate the need for human labelling. Additionally, we present an improved injection process leveraging the Gen3 LSST pipelines.
