We are proud to present MaxiMask and MaxiTrack, a set of softwares using convolutional neural networks to detect problematic pixels and problematic astronomical images. MaxiMask has been trained to identify:
- cosmic rays
- dead/hot pixels, including dead/hot columns or rows
- persistence effects
- satellite trails
- fringes
- nebulosity / extended emission
- saturated stars and associated blooming artifacts
- diffraction spikes
It was designed from the beginning to be very versatile and can deal equally well with CCD or infrared detectors.It is now extensively used with a broad range of astronomical cameras, including for example CFHT/Megacam, CTIO/Decam, Subaru/HSC, VST/Omegacam, as well as many other cameras.
The satellite constellation plague
Megaconstellations of low-orbit communication satellites such as Starlink or OneWeb will include tens of thousands of satellite and will heavily contaminate the data astronomers collect. These constellations are therefore a major source of concern, and might lead to 30% of wasted pixels in regular astronomical survey images. Maximask can efficiently detect and mask the pixels affected by such satellite trails, as illustrated in the Figure below showing a DECam image plagued with Starlink satellite trails and the mask detected by MaxiMask.
