Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because a) standard assumptions for machine-learned model selection procedures break down and b) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting (IW), co-training (CT), and active learning (AL). We argue that AL---where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up---is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and OGLE, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply active learning to classify variable stars in the ASAS survey, finding dramatic improvement in our agreement with the ACVS catalog, from 65.5% to 79.5%, and a significant increase in the classifier's average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.
A Large and Precise All-Sky Photometric Standard Star Dataset Across More Than 200 Passbands
University of Chinese Academy of Sciences（中国科学院大学）；Beijing Normal University（北京师范大学）；National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台）；The Johns Hopkins University（约翰斯·霍普金斯大学）；University of Notre Dame（圣母大学）；Beijing Electronic Science and Technology Institute（北京电子科技学院）
Photometric redshifts for the S-PLUS Survey: is machine learning up to the task?
南方光度局部宇宙巡天（Southern Photometric Local Universe Survey，S-PLUS）是一个新项目，旨在使用12个滤光片系统绘制南半球的地图，该系统包括5个类似SDSS的宽带滤光片和7个针对局部宇宙中重要恒星特征进行优化的窄带滤光片。在本文中，我们使用测光和形态信息的第一个S-PLUS数据发布（S-PLUS DR 1）交叉匹配unWISE数据和光谱红移从斯隆数字巡天DR 15。我们探索了三种不同的机器学习方法（使用GPz的高斯过程和使用TensorFlow制作的两个深度学习模型），并将它们与S-PLUS DR 1中当前使用的模板拟合方法进行比较，以解决机器学习方法是否可以利用十二个过滤器系统进行光度红移预测。使用单点估计的准确性测试，例如散点、偏倚和离群值分数的计算，以及概率分布函数（PDF），例如概率积分变换（PIT）、连续排序概率得分（CRPS）和赔率分布，我们得出结论，一个深-使用贝叶斯神经网络和混合密度网络相结合的学习方法为当前测试样本提供了最准确的光度红移。它实现了单点光度红移与散射（$σ_\text{NMAD}$）为0.023，归一化偏差为-0.001，0.64%的异常分数与r-自动星等之间的星系16和21。
An Automated Photometric Pipeline for the 80cm Xizang University Telescope
The Key Laboratry of Cosmic Rays (Xizang University), Ministry of Education（西藏大学宇宙射线教育部重点实验室）；Department of Physics, College of Science, Xizang University（西藏大学理学院物理系）；National Astronomical Observatories, Chinese Academic of Sciences（中国科学院国家天文台）；College of Physics and Optoelectronic Engineering, Leshan Normal University（乐山师范学院物理与光电工程学院）；Key Laboratory of Detection and Application of Space Effect in Southwest Sichuan（川西南空间效应探测与应用重点实验室）；Center for Applied Optics Research, Leshan Normal University（乐山师范学院应用光学研究中心）；The Experimental High School Attached to Beijing Normal University（北京师范大学附属实验中学）
