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 1902.07215astro-ph.IMastro-ph.GAastro-ph.SRcs.LG
收藏

特征选择以改善光谱表征,或:我如何学会停止担忧并爱上集成方法

Feature Selection for Better Spectral Characterization or: How I Learned to Start Worrying and Love Ensembles

University of Florida(佛罗里达大学)

Sankalp Gilda

AI总结:

针对低中分辨率光谱中恒星参数化面临的维度灾难问题,提出迭代特征选择算法,从PHOENIX光谱中剔除冗余吸收线,发现多数特征实为噪声,去除后可提升参数检索精度。

摘要:

机器学习在天文学应用中始终面临的一个威胁是数据过拟合的危险,即所谓的“维度灾难”。当样本数量少于自变量数量时,就会发生这种情况。在本工作中,我们聚焦于从低到中分辨率光谱(其中包含混合吸收线)进行恒星参数化的问题。我们采用一种迭代算法,从合成的PHOENIX光谱中依次剔除冗余特征,并得出一组与每个输出变量——有效温度(T_eff)、表面重力(log g)和金属丰度([Fe/H])——相关性最强的最优波长集合。我们发现,在任何给定分辨率下,大多数特征(即吸收线)不仅冗余,而且实际上充当噪声,降低了参数检索的准确性。

英文摘要:

An ever-looming threat to astronomical applications of machine learning is the danger of over-fitting data, also known as the `curse of dimensionality.' This occurs when there are fewer samples than the number of independent variables. In this work, we focus on the problem of stellar parameterization from low-mid resolution spectra, with blended absorption lines. We address this problem using an iterative algorithm to sequentially prune redundant features from synthetic PHOENIX spectra, and arrive at an optimal set of wavelengths with the strongest correlation with each of the output variables -- T$_{\rm eff}$, $\log g$, and [Fe/H]. We find that at any given resolution, most features (i.e., absorption lines) are not only redundant, but actually act as noise and decrease the accuracy of parameter retrieval.

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。

↑