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 2212.02537astro-ph.GAastro-ph.IM
收藏

使用未标记观测改进机器学习导出的光度红移和物理性质估计

Improving machine learning-derived photometric redshifts and physical property estimates using unlabelled observations

A. Humphrey, P. A. C. Cunha, A. Paulino-Afonso, S. Amarantidis, R. Carvajal, J. M. Gomes, I. Matute, P. Papaderos

摘要:

在大规模天文调查的时代,机器学习为有效估计星系属性提供了有前途的解决方案。机器学习应用的传统“监督”范式涉及在标记数据上训练模型,并使用该模型来预测先前未标记数据的标签。半监督“伪标签”技术提供了一种替代范例,允许模型训练算法从标记数据和尚未标记的数据中学习。我们使用COSMOS 2015宽带测光和几种公开可用的机器学习算法之一,在估计红移,恒星质量和恒星形成率的问题上测试了伪标记方法,与纯监督学习相比,我们获得了显着的改进。我们发现,梯度提升树方法CatBoost,XGBoost和LightGBM受益最大,绝对误差的指标减少高达~15%。我们也发现类似的改善光度红移的灾难性离群分数。我们认为,伪标记技术将是有用的,在即将到来的大型成像调查,如欧几里德和LSST,这将提供光度数据的数十亿来源的星系的红移和物理性质的估计。

英文摘要:

In the era of huge astronomical surveys, machine learning offers promising solutions for the efficient estimation of galaxy properties. The traditional, `supervised' paradigm for the application of machine learning involves training a model on labelled data, and using this model to predict the labels of previously unlabelled data. The semi-supervised `pseudo-labelling' technique offers an alternative paradigm, allowing the model training algorithm to learn from both labelled data and as-yet unlabelled data. We test the pseudo-labelling method on the problems of estimating redshift, stellar mass, and star formation rate, using COSMOS2015 broad band photometry and one of several publicly available machine learning algorithms, and we obtain significant improvements compared to purely supervised learning. We find that the gradient-boosting tree methods CatBoost, XGBoost, and LightGBM benefit the most, with reductions of up to ~15% in metrics of absolute error. We also find similar improvements in the photometric redshift catastrophic outlier fraction. We argue that the pseudo-labellng technique will be useful for the estimation of redshift and physical properties of galaxies in upcoming large imaging surveys such as Euclid and LSST, which will provide photometric data for billions of sources.

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。

↑