arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.00188astro-ph.CO
收藏

用于强透镜搜索的深度学习:卷积神经网络测试和来自KiDS DR3的新候选者

Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3

Zizhao He, Xinzhong Er, Qian Long, Dezi Liu, Xiangkun Liu, Ziwei Li, Yun Liu, Wenqaing Deng, Zuhui Fan

摘要:

卷积神经网络已经成功地应用于寻找强透镜系统,从而从大型调查中发现了新的候选者。另一方面,系统的研究,他们的鲁棒性仍然缺乏。在本文中,我们首先构建了一个神经网络,并将其应用到$r$波段图像的发光红星系(LRGs)的千度巡天(KiDS)数据发布3搜索强透镜系统。我们构建了两组训练样本,一组完全来自模拟,另一组使用来自KiDS观测的LRG戳作为前景镜头图像。在前一个训练样本中,我们发现了48个经过人工检测的高概率候选者,其中27个是新识别的。使用后一个训练集,也发现了上述48个候选者中的约67%,并且还识别出11个新的强透镜候选者。然后,我们进行测试的鲁棒性的网络性能相对于PSF的变化。当测试样本的PSF在训练样本的中值PSF的0.4到2倍的范围内时,我们发现我们的网络表现得相当稳定,并且退化很小。我们还研究了训练集的数量如何影响我们的网络性能,从10万到80万不等。输出结果相当稳定,表明在所考虑的范围内,我们的网络性能对卷大小不是很敏感。

英文摘要:

Convolutional Neutral Networks have been successfully applied in searching for strong lensing systems, leading to discoveries of new candidates from large surveys. On the other hand, systematic investigations about their robustness are still lacking. In this paper, we first construct a neutral network, and apply it to $r$-band images of Luminous Red Galaxies (LRGs) of the Kilo Degree Survey (KiDS) Data Release 3 to search for strong lensing systems. We build two sets of training samples, one fully from simulations, and the other one using the LRG stamps from KiDS observations as the foreground lens images. With the former training sample, we find 48 high probability candidates after human-inspection, and among them, 27 are newly identified. Using the latter training set, about 67\% of the aforementioned 48 candidates are also found, and there are 11 more new strong lensing candidates identified. We then carry out tests on the robustness of the network performance with respect to the variation of PSF. With the testing samples constructed using PSF in the range of 0.4 to 2 times of the median PSF of the training sample, we find that our network performs rather stable, and the degradation is small. We also investigate how the volume of the training set can affect our network performance by varying it from 0.1 millions to 0.8 millions. The output results are rather stable showing that within the considered range, our network performance is not very sensitive to the volume size.

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。

↑