基于深度学习的天文图像主波束效应校正方法分析  

Analysis of Main Beam Effect Correction Method for Astronomical Images Based on Deep Learning

作　　者：苏晓宇 项兆佳 赵寒琼 张利 SU Xiaoyu;XIANG Zhaojia;ZHAO Hanqiong;ZHANG Li(School of Big Data and Information Engineering,Guizhou University,Guizhou 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵州550025

出　　处：《集成电路应用》2024年第11期86-87,共2页Application of IC

摘　　要：阐述平方公里阵列作为世界上拟建设的超大型射电望远镜,将提供详细的观测数据用于干涉成像,但目前SKA阵列成像结果并不理想。设计一种深度学习网络模型,用于校正成像过程中产生的主波束效应。通过对模拟的天文数据集进行学习和训练,此模型可以有效重建主波束效应的天文图像,并且结果优于其他方法。This paper describes that the Square Kilometer Array,as a proposed ultra large radio telescope in the world,will provide detailed observational data for interferometric imaging.But currently,the imaging results of SKA array are not ideal.It designs a deep learning network model for correcting the main beam effect generated during the imaging process.By learning and training from simulated astronomical datasets,this model can effectively reconstruct astronomical images of the main beam effect,and its results are superior to other methods.

关 键 词：深度学习 波束误差 平方公里阵列 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]