PNet -- A Deep Learning Based Photometry and Astrometry Bayesian Framework
This work addresses the need for faster and more accurate detection of variable celestial objects in astronomy, though it appears incremental as it builds on existing deep learning methods for a specific domain.
The authors tackled the problem of detecting celestial objects and determining their magnitudes and positions in time-domain astronomy by developing PNet, an end-to-end deep learning framework that also estimates photometry uncertainty, and demonstrated its ability to deliver consistent and reliable outcomes using simulated and real data.
Time domain astronomy has emerged as a vibrant research field in recent years, focusing on celestial objects that exhibit variable magnitudes or positions. Given the urgency of conducting follow-up observations for such objects, the development of an algorithm capable of detecting them and determining their magnitudes and positions has become imperative. Leveraging the advancements in deep neural networks, we present the PNet, an end-to-end framework designed not only to detect celestial objects and extract their magnitudes and positions but also to estimate photometry uncertainty. The PNet comprises two essential steps. Firstly, it detects stars and retrieves their positions, magnitudes, and calibrated magnitudes. Subsequently, in the second phase, the PNet estimates the uncertainty associated with the photometry results, serving as a valuable reference for the light curve classification algorithm. Our algorithm has been tested using both simulated and real observation data, demonstrating the PNet's ability to deliver consistent and reliable outcomes. Integration of the PNet into data processing pipelines for time-domain astronomy holds significant potential for enhancing response speed and improving the detection capabilities for celestial objects with variable positions and magnitudes.