arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.07542astro-ph.IMcs.LG
收藏

对用于瞬变光曲线近似的神经网络方法性质的理解

Understanding of the properties of neural network approaches for transient light curve approximations

Max-Planck-Institut für Astronomie(马克斯·普朗克天文研究所);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Lomonosov Moscow State University(罗蒙诺索夫莫斯科国立大学);Moscow Institute of Physics and Technology(莫斯科物理技术学院);Moscow Polytechnic University(莫斯科理工大学);HSE University(高等经济大学)

Mariia Demianenko, Konstantin Malanchev, Ekaterina Samorodova, Mikhail Sysak, Aleksandr Shiriaev, Denis Derkach, Mikhail Hushchyn

AI总结:

本文研究用神经网络(多层感知机、贝叶斯神经网络、归一化流)近似不规则采样的瞬变光曲线,证明少量观测即可优于现有模型且比高斯过程更快,并发布Fulu Python库。

摘要:

现代时域测光巡天收集了大量各类天体的观测数据,而即将到来的大规模巡天时代将提供更多关于它们性质的信息。光谱后续观测对于超新星等瞬变天体尤为关键,但大多数此类天体尚未接受这类研究。通量时间序列被积极用作一种经济可行的替代方案,用于光度分类和性质表征,例如峰值识别和光度下降率估计。然而,所收集的时间序列是多维的、采样不规则的,同时还包含离群值,并且缺乏明确定义的系统误差。本文旨在寻找性能最佳的方法,以在时间和波长维度上近似观测到的光曲线,从而在每个通带内生成具有规则时间步长的时间序列。我们考察了多种基于神经网络的光曲线近似方法,包括多层感知机、贝叶斯神经网络和归一化流,用于近似单条光曲线的观测数据。测试数据集包括模拟的PLAsTiCC数据集和真实的Zwicky Transient Facility Bright Transient Survey瞬变光曲线。测试结果表明,与当前最先进的模型相比,即使仅有少量观测数据也足以拟合网络并提高近似质量。本文所述方法计算复杂度低,且显著快于高斯过程。此外,我们从后续峰值识别和瞬变分类的角度分析了这些近似技术的性能。研究结果已发布在一个开放且用户友好的Fulu Python库中,并可在GitHub上供科学界使用。

英文摘要:

Modern-day time-domain photometric surveys collect a lot of observations of various astronomical objects and the coming era of large-scale surveys will provide even more information on their properties. Spectroscopic follow-ups are especially crucial for transients such as supernovae and most of these objects have not been subject to such studies. }{Flux time series are actively used as an affordable alternative for photometric classification and characterization, for instance, peak identifications and luminosity decline estimations. However, the collected time series are multidimensional and irregularly sampled, while also containing outliers and without any well-defined systematic uncertainties. This paper presents a search for the best-performing methods to approximate the observed light curves over time and wavelength for the purpose of generating time series with regular time steps in each passband.}{We examined several light curve approximation methods based on neural networks such as multilayer perceptrons, Bayesian neural networks, and normalizing flows to approximate observations of a single light curve. Test datasets include simulated PLAsTiCC and real Zwicky Transient Facility Bright Transient Survey light curves of transients.}{The tests demonstrate that even just a few observations are enough to fit the networks and improve the quality of approximation, compared to state-of-the-art models. The methods described in this work have a low computational complexity and are significantly faster than Gaussian processes. Additionally, we analyzed the performance of the approximation techniques from the perspective of further peak identification and transients classification. The study results have been released in an open and user-friendly Fulu Python library available on GitHub for the scientific community.

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。

↑