Point Source Detection Software in the SKA Era

TL;DR

This paper discusses the need for and challenges of developing a fast, scalable point source detection software for large sky images in the SKA era, emphasizing the importance of efficient algorithms for calibration.

Contribution

It analyzes the scalability issues of existing point source detection methods and discusses trade-offs for adapting them to SKA-scale image sizes.

Findings

Current implementations do not scale well with large images.

Thresholding approaches are common for point source detection.

Scaling algorithms for SKA-level images requires addressing computational trade-offs.

Abstract

The generation of a sky model for calibration of Square Kilometre Array observations requires a fast method of automatic point source detection and characterisation. In recent years, point source detection in two-dimensional images has been implemented by using several thresholding approaches. In the first phase of the SKA we will need a fast implementation capable of dealing with very large images (80,000 x 80,000 pixels). While the underlying algorithms scale suitably with image size, the present implementations do not. We make some comments on the pertinent trade-offs for scaling these implementations to SKA-levels.