DECORAS: detection and characterization of radio-astronomical sources using deep learning
This work addresses source detection for radio astronomers, offering a scalable solution for future wide-field VLBI surveys, but it is incremental as it applies a known deep learning architecture to a specific domain.
The paper tackles the problem of detecting and characterizing radio-astronomical sources from VLBI observations using a deep learning approach called DECORAS, achieving improved completeness and purity compared to traditional methods, with specific metrics such as completeness at 7.5σ and enhanced reliability at 5.5σ.
We present DECORAS, a deep learning based approach to detect both point and extended sources from Very Long Baseline Interferometry (VLBI) observations. Our approach is based on an encoder-decoder neural network architecture that uses a low number of convolutional layers to provide a scalable solution for source detection. In addition, DECORAS performs source characterization in terms of the position, effective radius and peak brightness of the detected sources. We have trained and tested the network with images that are based on realistic Very Long Baseline Array (VLBA) observations at 20 cm. Also, these images have not gone through any prior de-convolution step and are directly related to the visibility data via a Fourier transform. We find that the source catalog generated by DECORAS has a better overall completeness and purity, when compared to a traditional source detection algorithm. DECORAS is complete at the 7.5$σ$ level, and has an almost factor of two improvement in reliability at 5.5$σ$. We find that DECORAS can recover the position of the detected sources to within 0.61 $\pm$ 0.69 mas, and the effective radius and peak surface brightness are recovered to within 20 per cent for 98 and 94 per cent of the sources, respectively. Overall, we find that DECORAS provides a reliable source detection and characterization solution for future wide-field VLBI surveys.