摘要：Context. In the present era of large-scale surveys in the time domain, the processing of data, from procurement up to the detection of sources, is generally automated. One of the main challenges in the astrophysical analysis of their output is contamination by artifacts, especially in the regions of high surface brightness of unresolved emission.
Aims. We present a novel method for identifying candidates for variable and transient sources from the outputs of optical time-domain survey data pipelines. We use the method to conduct a systematic search for novae in the intermediate Palomar Transient Factory (iPTF) observations of the bulge part of M 31 during the second half of 2013.
Methods. We demonstrate that a significant fraction of artifacts produced by the iPTF pipeline form a locally uniform background of false detections approximately obeying Poissonian statistics, whereas genuine variable and transient sources, as well as artifacts associated with bright stars, result in clusters of detections whose spread is determined by the source localization accuracy. This makes the problem analogous to source detection on images produced by grazing incidence X-ray telescopes, enabling one to utilize the arsenal of powerful tools developed in X-ray astronomy. In particular, we use a wavelet-based source detection algorithm from the Chandra data analysis package CIAO.
Results. Starting from ~2.5 × 105 raw detections made by the iPTF data pipeline, we obtain approximately 4000 unique source candidates. Cross-matching these candidates with the source-catalog of a deep reference image of the same field, we find counterparts for ~90% of the candidates. These sources are either artifacts due to imperfect PSF matching or genuine variable sources. The remaining approximately 400 detections are transient sources. We identify novae among these candidates by applying selection cuts to their lightcurves based on the expected properties of novae. Thus, we recovered all 12 known novae (not counting one that erupted toward the end of the survey) registered during the time span of the survey and discovered three nova candidates. Our method is generic and can be applied to mining any target out of the artifacts in optical time-domain data. As it is fully automated, its incompleteness can be accurately computed and corrected for.
关键词：methods: data analysis;surveys;novae, cataclysmic variables;galaxies: individual: M 31
