Effective Image Differencing with Convolutional Neural Networks for Real-time Transient Hunting

Nima Sedaghat, A. Mahabal
Monthly Notices of the Royal Astronomical Society, 2017
Abstract: Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying point-spread function (PSF) and small brightness variations in many sources, as well as artefacts resulting from saturated stars and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artefacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image-subtraction pipeline -- image registration, background subtraction, noise removal, PSF matching and subtraction -- in a single real-time convolutional network. Once trained, the method works lightening-fast and, given that it performs multiple steps in one go, the time saved and false positives eliminated for multi-CCD surveys like Zwicky Transient Facility and Large Synoptic Survey Telescope will be immense, as millions of subtractions will be needed per night.
Paper Publisher's link

Images and movies


See also

Material (network architecture, trained model, some code) available on the GitHub page.

BibTex reference

  author       = "Nima Sedaghat and Ashish Mahabal",
  title        = "Effective Image Differencing with Convolutional Neural Networks for Real-time Transient Hunting",
  journal      = "Monthly Notices of the Royal Astronomical Society",
  month        = " ",
  year         = "2017",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2017/Sed17"

Other publications in the database