PNet -- A Deep Learning Based Photometry and Astrometry Bayesian Framework

TL;DR

PNet is a deep learning framework that detects celestial objects, extracts their photometric and astrometric data, and estimates uncertainties, thereby enhancing real-time analysis in time-domain astronomy.

Contribution

The paper introduces PNet, a novel end-to-end deep learning framework for simultaneous detection, measurement, and uncertainty estimation of celestial objects in astronomical data.

Findings

Demonstrates reliable detection and measurement on simulated data

Achieves consistent results with real observational data

Enhances pipeline speed and detection accuracy in time-domain astronomy

Abstract

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.