arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.12975astro-ph.GAastro-ph.CO
收藏

用于发现强引力透镜的神经网络的系统性比较

Systematic comparison of neural networks used in discovering strong gravitational lenses

Anupreeta More, Raoul Canameras, Anton T. Jaelani, Yiping Shu, Yuichiro Ishida, Kenneth C. Wong, Kaiki Taro Inoue, Stefan Schuldt, Alessandro Sonnenfeld

AI总结:

本研究首次对四个分析HSC巡天数据的团队的引力透镜搜寻神经网络开展系统性基准测试,对比了不同网络、训练样本对性能的影响,为未来巡天的透镜搜寻工作提供参考。

摘要:

随着大规模成像巡天项目不断增多,研究人员正在开发高效算法以搜寻强引力透镜系统。过去几年间,神经网络已成功应用于千度巡天(Kilo Degree Survey)、超广域主焦点相机(Hyper-Suprime Cam, HSC)巡天、暗能量巡天(Dark Energy Survey)等成像巡天中的星系尺度透镜系统发现工作。由于多数这类网络都采用监督学习算法,因此厘清不同网络的性能对比、各自优势以及训练数据集的作用已变得十分必要。\n在本研究中,我们对四个已分析过HSC巡天数据的团队所开发的网络开展了首次系统性比较与基准测试。各团队独立设计训练样本并开发神经网络,但事先已达成协调,严格预留特定数据集仅用于测试。测试样本包含来自不同来源的模拟透镜、真实(候选)透镜以及真实非透镜天体,用于对各网络的性能进行基准测试与表征。结果显示,各团队的网络在自行构建的测试样本上的表现均远优于在其他团队构建的测试样本上的表现,但在包含真实(候选)透镜与非透镜天体的测试样本上,所有网络的表现相当。\n我们还研究了在保持网络架构不变的前提下,在各团队间交换训练样本带来的影响,发现这一操作使部分网络的性能得到提升。这些结果对鲁宾空间与时间遗留巡天(Rubin-Legacy Survey of Space and Time)、Roman、Euclid等即将开展的成像巡天的透镜搜寻工作所需采取的措施具有直接参考意义。

英文摘要:

Efficient algorithms are being developed to search for strong gravitational lens systems owing to increasing large imaging surveys. Neural networks have been successfully used to discover galaxy-scale lens systems in imaging surveys such as the Kilo Degree Survey, Hyper-Suprime Cam (HSC) Survey and Dark Energy Survey over the last few years. Thus, it has become imperative to understand how some of these networks compare, their strengths and the role of the training datasets as most of the networks make use of supervised learning algorithms. In this work, we present the first-of-its-kind systematic comparison and benchmarking of networks from four teams that have analysed the HSC Survey data. Each team has designed their training samples and developed neural networks independently but coordinated apriori in reserving specific datasets strictly for test purposes. The test sample consists of mock lenses, real (candidate) lenses and real non-lenses gathered from various sources to benchmark and characterise the performance of each of the network. While each team's network performed much better on their own constructed test samples compared to those from others, all networks performed comparable on the test sample with real (candidate) lenses and non-lenses. We also investigate the impact of swapping the training samples amongst the teams while retaining the same network architecture. We find that this resulted in improved performance for some networks. These results have direct implications on measures to be taken for lens searches with upcoming imaging surveys such as the Rubin-Legacy Survey of Space and Time, Roman and Euclid.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑