A photometry pipeline for SDSS images based on convolutional neural networks

Abstract

ABSTRACT In this paper, we propose a convolutional neural network (CNN)-based photometric pipeline for the Sloan Digital Sky Survey (SDSS) images. The pipeline includes three main parts: the target source detection, the target source classification, and the photometric parameter measurement. The last part is completed using traditional methods. The paper mainly focuses on the first two parts and does not present the last. In the 1st part, a network named TSD-YOLOv4 is proposed to detect new sources missed by the SDSS photometric pipeline according to the PhotoObjAll catalogue of SDSS. In the second part, a target source classification network named TSCNet is constructed to classify sources into galaxies, quasars, and stars directly from photometric images. Experiments show that TSD-YOLOv4 outperforms other networks (Faster-RCNN, YOLOv4, YOLOX, etc.) in all metrics, with an accuracy of 0.988, a recall of 0.997, and an F1-score of 0.992, and TSCNet has good performance with a classification accuracy of 0.944 on the test set with 23 265 sources, and precision rates of 0.98, 0.908, and 0.918 for galaxies, quasars, and stars, respectively. On the other hand, the recall rates are 0.982, 0.903, and 0.921 for galaxies, quasars, and stars, respectively. The TSCNet has higher accuracy, fewer parameters, and faster inference speed than the leading astronomical photometric source classification network, the APSCNet model. In addition, the effect of magnitude distribution on the classification results is discussed in the experiments. The experiments prove that the proposed pipeline can be used as a powerful tool to supplement the SDSS photometric catalogue.